Paper Digest: KDD 2026 Papers & Highlights
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) is one of the top data mining conferences in the world. To help the community quickly catch up on the work presented in this conference, Paper Digest Team processed all accepted papers, and generated one highlight sentence (typically the main topic) for each paper. Readers are encouraged to read these machine generated highlights to quickly get the main idea of each paper.
Search within KDD-2026
Literature review on a topic
Generate a written review of KDD-2026 research on any topic, with each claim cited to specific papers.
Browse & explore
Browse ~ 7,200 authors (KDD-2026), or explore the “Best Paper” Digest listing the most influential KDD papers of recent years.
Note: KDD-2026 accepts more than 1,400 papers, this page only includes 500 of them selected by our daily paper digest algorithm. Interested users can choose to read All 1,400 KDD-2026 papers in a separate page, which takes quite some time to load.
Since 2018, Paper Digest has built a foundation of data spanning decades of conferences, journals, and research topics. The platform features a daily digest service that sifts through tens of thousands of new papers, clinical trials, news articles, and community posts, filtering the noise to highlight what matters most to specific interests. Beyond daily updates, dozens of built-in research tools streamline the academic workflow, supporting efficient reading and writing, comprehensive literature reviews, and automated research report generation.
Paper Digest Team
New York City, New York, 10017
team@paperdigest.org
TABLE 1: Paper Digest: KDD 2026 Papers & Highlights
| Paper | Author(s) | |
|---|---|---|
| 1 | IRLBench: A Multi-modal, Culturally Grounded, Parallel Irish-English Benchmark for Open-Ended LLM Reasoning Evaluation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Existing benchmarks often exhibit cultural bias, restrict evaluation to text-only, rely on multiple-choice formats, and, more importantly, are ineffectual for extremely low-resource languages. To address these gaps, we introduce IRLBench, presented in parallel English and Irish, which is considered definitely endangered by UNESCO. |
Khanh-Tung Tran; Duc-Hai Nguyen; Barry O’Sullivan; Hoang D. Nguyen; |
| 2 | VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: This paper introduces VideoRAG, a retrieval-augmented generation framework designed for processing extremely long-context videos. |
Xubin Ren; Lingrui Xu; Long Xia; Shuaiqiang Wang; Dawei Yin; Chao Huang; |
| 3 | Generating Realistic Human Mobility Data with Hybrid Large Language Model Agent Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, this problem is non-trivial since LLMs are not originally optimized for inferring human mobility behavior. To bridge this gap, we propose a novel data generator called Chain-of-Planned-Behavior (CoPB) that consists of three key components: (1) a behavior science-inspired agentic workflow that adapts LLMs for mobility intention reasoning, drawing on the Theory of Planned Behavior to integrate attitude, subjective norms, and perceived behavioral control to jointly decide the next mobility intention; (2) a conditional generative diffusion model that grounds abstract intents into physical space by generating intention-conditioned mobility trajectories; and (3) a lightweight data generator solution that provides a cost-effective alternative, where knowledge distillation is used to transfer the intent reasoning capability of LLMs to smaller language models. |
Chenyang Shao; Bingbing Fan; Jingtao Ding; Yuan Yuan; Meng Wang; Fengli Xu; |
| 4 | Domain-Specific Data Synthesis for LLMs Through Minimal Sufficient Representation Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we tackle the underexplored problem of domain-specific data synthesis through an inductive paradigm, where the target domain is defined only through a set of reference examples, particularly when domain characteristics are difficult to articulate in natural language. |
Tong Ye; Hang Yu; Tengfei Ma; Xuhong Zhang; Jianguo Li; Peng Di; Peiyu Liu; Jianwei Yin; Wenhai Wang; |
| 5 | MAC: A Conversion Rate Prediction Benchmark Featuring Labels Under Multiple Attribution Mechanisms Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: (3) Two architectural design principles are paramount: first, to fully learn the multi-attribution knowledge, and second, to fully leverage this knowledge to serve the main task. Motivated by these findings, we propose Mixture of Asymmetric Experts (MoAE), an effective MAL approach incorporating multi-attribution knowledge learning and main task-centric knowledge utilization. |
Jinqi Wu; Sishuo Chen; Zhangming Chan; Yong Bai; Lei Zhang; Sheng Chen; Chenghuan Hou; Xiang-Rong Sheng; Han Zhu; Jian Xu; Bo Zheng; Chaoyou Fu; |
| 6 | REALM-Bench: A Benchmark for Evaluating Multi-Agent Systems on Real-world, Dynamic Planning and Scheduling Tasks Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This benchmark suite provides a comprehensive evaluation framework for assessing both individual LLMs and multi-agent systems in real-world planning and scheduling scenarios. |
Longling Geng; Edward Y. Chang; |
| 7 | VideoExplorer: Advancing Long-Horizon Video Understanding Via Hierarchical Orchestration Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Current agentic frameworks for Long-Video Understanding (LVU) remain limited by two critical problems: ineffective control, where traditional monolithic agents struggle with high-branching, multi-granularity decision processes; and inefficient supervision, where sparse, outcome-based feedback fails to guide long-horizon reasoning. To resolve these challenges, we propose VideoExplorer, a novel agentic system designed to advance long-video reasoning on top of structured control and trajectory-level optimization. |
Huaying Yuan; Zheng Liu; Junjie Zhou; Hongjin Qian; Yan Shu; Nicu Sebe; Ji-Rong Wen; Zhicheng Dou; |
| 8 | MuSeL: A Multi-Scale Adaptive Graph Representation Learning Framework for Microbe-Drug Association Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, when confronted with extremely sparse biological networks with pronounced structural heterogeneity, existing methods often struggle to simultaneously model global topological dependencies and local structural disparities. To address these challenges, we propose MuSeL, a multi-scale adaptive graph representation learning framework that jointly mitigates the above issues from two complementary perspectives: global topology modeling and local structure optimization. |
Yuehu Wu; Lei Wang; Zhengwei Li; Mengmeng Wei; Bowei Zhao; |
| 9 | CoRank: LLM-Based Compact Reranking with Document Features for Scientific Retrieval Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: As a result, many relevant documents are excluded before reranking, constraining overall retrieval performance. To address these challenges, we explore semantic-feature-based compact document representations (e.g., categories, sections, and keywords) and propose CoRank, a training-free, model-agnostic reranking framework for scientific retrieval. |
Runchu Tian; Xueqiang Xu; Bowen Jin; SeongKu Kang; Jiawei Han; |
| 10 | FAT-TAG: Mitigating Forgetting in Task-Free Temporal Graph Class Incremental Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we introduce FAT-TAG, a task-free Temporal Graph Class Incremental Learning framework. |
Jiyuan Feng; Zhao Liu; Dongyi Zheng; Weihong Han; Binxing Fang; Qing Liao; |
| 11 | Condition-Gated Reasoning for Context-Dependent Biomedical Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing benchmarks do not evaluate such conditional reasoning, and retrieval-augmented or graph-based methods lack explicit mechanisms to ensure that retrieved knowledge is applicable to given context. To address this gap, we propose CondMedQA, the first benchmark for conditional biomedical QA, consisting of multi-hop questions whose answers vary with patient conditions. |
Jash Rajesh Parekh; Wonbin Kweon; Joey Chan; Rezarta Islamaj; Robert Leaman; Pengcheng Jiang; Chih-Hsuan Wei; Zhizheng Wang; Zhiyong Lu; Jiawei Han; |
| 12 | PIDSMaker: Building and Evaluating Provenance-based Intrusion Detection Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present PIDSMaker, an open-source framework for developing and evaluating PIDSs under consistent protocols. |
Tristan Bilot; Baoxiang Jiang; Thomas Pasquier; |
| 13 | Fourier Geometric Wind Power Forecasting with Numerical Weather Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing methods fail to effectively incorporate weather forecasting with wind turbine data (i.e., SCADA), leading to suboptimal solutions. To address this, we introduce a multimodal framework that integrates historical point-based SCADA data with grid-based Numerical Weather Prediction (NWP) forecasts, which is challenging due to heterogeneous input and the complex physical wind-turbine interactions. |
Shiyuan Piao; Zehui Fan; Yang Liu; Hong Cheng; Juepeng Zheng; Jie Zhou; Fugee Tsung; |
| 14 | LiveMCPBench: Can Agents Navigate An Ocean of MCP Tools? Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Unfortunately, there is still a large gap between real-world MCP usage and current evaluation: they typically assume single-server settings and directly inject tools into the model’s context, bypassing the challenges of large-scale retrieval and multi-tool composition. To bridge this gap, we propose LiveMCPBench, which evaluates 95 real-world daily tasks explicitly constructed to stress diverse tools and scaled multi-server routing. |
Guozhao Mo; Wenliang Zhong; Jiawei Chen; Qianhao Yuan; Xuanang Chen; Yaojie Lu; Hongyu Lin; Ben He; Xianpei Han; Le Sun; |
| 15 | ShadeBench: A Benchmark Dataset for Building Shade Simulation in Sustainable Society Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, accurately modeling and analyzing urban shade at scale remains difficult because of the lack of large-scale datasets and systematic evaluation frameworks. To address this challenge, we present ShadeBench, a comprehensive dataset and benchmark for urban shade understanding. |
Longchao Da; Mithun Shivakoti; Xiangrui Liu; T Pranav Kutralingam; Yezhou Yang; Hua Wei; |
| 16 | InfRL: Inference-time Reinforcement Learning for Research Idea Optimization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: InfRL thus offers a practical and domain-agnostic approach to harness reinforcement learning during inference, bridging the gap between static prompting and computationally intensive parameter-level fine-tuning. |
Sikun Guo; Amir Hassan Shariatmadari; Jiuqi Wang; Albert Huang; Stefan Bekiranov; Shangtong Zhang; Aidong Zhang; |
| 17 | Curiosity-Driven Questioning for Engine-Agnostic LLM Research Ideation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Yet, most LLM-based ideation systems optimize the idea text while leaving curiosity under-modeled, resulting in brittle, engine-specific gains. To address this, we propose Curiosity-Driven Questioning (CDQ), a training-free, engine-agnostic method that constructs a compact set of curiosity-driven questions from a topic corpus under black-box LLM access. |
Sikun Guo; Di Wang; Xiaohan Fan; Albert Huang; Aidong Zhang; |
| 18 | Reinforced Structural Reasoning for Receptive Field Optimization in GNN Toward Interpretable Graph Clustering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a novel reinforced structural reasoning framework, termed RGIGC, for interpretable graph clustering. |
Yue Yang; Dongxu Li; Hengchuang Yin; Ying Chang; Pengwei Hu; Lun Hu; |
| 19 | How Far Are Large Multimodal Models from Human-Level Spatial Action? A Benchmark for Goal-Oriented Embodied Navigation in Urban Airspace Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose EmbodiedNav-Bench, a benchmark to investigate whether LMMs can perform human-like spatial action through a challenging scenario: goal-oriented navigation in urban 3D spaces. |
Baining Zhao; Ziyou Wang; Jianjie Fang; Zile Zhou; Yanggang Xu; Yatai Ji; Jiacheng Xu; Qian Zhang; Weichen Zhang; Chen Gao; Xinlei Chen; |
| 20 | OrionInfer: Low-Overhead Parallelism Switching and Live Migration for Efficient LLM Serving Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present OrionInfer, an adaptive LLM serving system that aligns inference strategies with real-time demand. |
Jingqi Feng; Guang Yang; Yukai Huang; Sicheng Liang; Chunpu Huang; Ming Yan; Wu Jie; |
| 21 | SMES: Towards Scalable Multi-Task Recommendation Via Expert Sparsity Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we investigate parameter sparsification as a principled scaling paradigm and identify two critical obstacles when applying sparse Mixture-of-Experts (MoE) to multi-task recommendation: exploded expert activation that undermines instance-level sparsity and expert load skew caused by independent task-wise routing. |
Yukun Zhang; Si Dong; Xu Wang; Bo Chen; Qinglin Jia; Shengzhe Wang; Jinlong Jiao; Runhan Li; Jiaqiang Liu; Chaoyi Ma; Ruiming Tang; Guorui Zhou; |
| 22 | SENSE: Satellite-based ENergy Synthesis for Sustainable Environment Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To address them, we propose SENSE (Satellite-based ENergy Synthesis for Sustainable Environment), a unified generative UBEM framework that jointly synthesizes realistic urban satellite imagery and aligned high-quality building energy consumption and height maps. |
Kailai Sun; Mingyi He; Heye Huang; Can Rong; Alok Prakash; Baoshen Guo; Shenhao Wang; Jinhua Zhao; |
| 23 | PCA-OS: A Planetary Climate Adaptation Operating System Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose PCA-OS (Planetary Climate Adaptation Operating System), a decision-support operating abstraction built on an intervention-aware global causal knowledge graph. |
Chaoyue He; Xin Zhou; Di Wang; Hong Xu; Wei Liu; Chunyan Miao; |
| 24 | From Memorization to Creation: Evaluating The Cognitive Depth of LLM?Generated Educational Questions Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Using a hybrid human-AI evaluation protocol, we generate and analyze 20,700 questions across computer science, K-12 math, and social-science domains. |
Xiaolong Wang; Zhe Zhao; Song Lai; Chaoli Zhang; Zijie Geng; Yu Tong; Ye Wei; Qingsong Wen; |
| 25 | GLACIER: A Multimodal Student-Teacher Foundation Model for Molecular Property Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Most large-scale models are unimodal in nature and overlook the potential to leverage complementary molecular data modalities. To address these shortcomings, this paper introduces the Graph-Language Alignment for Chemical Inference and Exploration using Representations (GLACIER) model, a student-teacher framework that integrates molecular graphs, SMILES strings, and physicochemical descriptors to learn rich molecular embeddings. |
Emily Nguyen; Yongchan Hong; Harsh Toshniwal; Yan Liu; Andreas Luttens; |
| 26 | Learning to Reduce Search Space for Generalizable Neural Routing Solver Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While recent dynamic search space reduction (SSR) methods can improve inference efficiency through geometric distance-based pruning, they often struggle on complex instances with non-uniform distributions or when optimal solutions rely heavily on non-spatial constraints. To address this critical issue, we propose Learning to Reduce (L2R), which is the first learning-based dynamic SSR framework. |
Changliang Zhou; Xi Lin; Zhenkun Wang; Qingfu Zhang; |
| 27 | AbstainGNN: Teaching Graph Neural Networks to Abstain for Graph Classification Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing GNNs are typically forced to make predictions even under high uncertainty or unknown conditions, resulting in unreliable decisions that can severely impact downstream tasks, particularly in safety-critical scenarios. To address this critical limitation, we propose AbstainGNN, a novel and theory-driven framework for graph classification with abstention, which enables GNNs to reject uncertain predictions instead of producing incorrect decisions. |
Xixun Lin; Zhiheng Zhou; Zhengyin Zhang; Yancheng Chen; Shuai Zhang; Ge Zhang; Shichao Zhu; Lixin Zou; Chuan Zhou; Peng Zhang; Shirui Pan; Yanan Cao; |
| 28 | From Scaling to Structured Expressivity: Rethinking Transformers for CTR Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To restore alignment, we introduce the Field-Aware Transformer (FAT). |
Bencheng Yan; Yuejie Lei; Zhiyuan Zeng; Zheye Deng; Di Wang; Kaiyi Lin; Pengjie Wang; Chuan Yu; Jian Xu; Bo Zheng; |
| 29 | AutoSchema: Self-Prompted Schema Induction and Evidence-Grounded Extraction for Materials Science Literature Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present AutoSchema, an iterative literature-mining pipeline that bootstraps both retrieval and schema induction from a small set of seed papers, then freezes the induced schema for scalable, evidence-grounded extraction. |
Mingfang Zhu; Yixin Chen; Zhiling Zheng; |
| 30 | FORGE: Forming Semantic Identifiers for Generative Retrieval in Industrial Datasets Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, current studies in this field primarily (1) offer limited investigation into the construction strategies for better SIDs, and (2) their SID assessment typically relies on costly GR training. To address these challenges, we propose FORGE, a comprehensive benchmark for FOrming semantic identifieRs for Generative rEtrieval. |
Kairui Fu; Tao Zhang; Shuwen Xiao; Ziyang Wang; Xinming Zhang; Chenchi Zhang; Yuliang Yan; Junjun Zheng; Xiangheng Kong; Shengyu Zhang; Kun Kuang; Yuning Jiang; |
| 31 | EvoFEND: Dual Memory-Driven Self-Evolving Fake News Detection Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: As an alternative, we propose active, non-parametric evolution for fake news detection: instead of relying on repeated parametric updates (i.e., retraining) to handle changes, the model evolves by updating external memories as evidence and environments shift. |
Beizhe Hu; Qiang Sheng; Hao Mi; Jiaying Wu; Zhengjia Wang; Yuanlong Yu; Danding Wang; Xuming Hu; Juan Cao; |
| 32 | RAG Vs. GraphRAG: A Systematic Evaluation and Key Insights Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present a comprehensive benchmark study comparing RAG and GraphRAG on established text-based tasks, including question answering and query-based summarization. |
Haoyu Han; Li Ma; Yu Wang; Harry Shomer; Kai Guo; Yongjia Lei; Zhisheng Qi; Zhigang Hua; Bo Long; Hui Liu; Charu Aggarwal; Jiliang Tang; |
| 33 | Parallelizing LLM Agent Execution with Contrastive Task Allocation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose CoAct, a training-free framework that parallelizes agent workflows by casting execution as an online task allocation problem: CoAct prompts the LLM to generate a pool of discrete subtasks and performs online dispatch by selecting, whenever a worker becomes available, the next task that minimizes an incremental task-contrastive objective, encouraging high similarity among tasks executed on the same path (positive pairs) and low similarity across different paths (negative pairs) to reduce cross-worker interaction and synchronization. |
Yuyang Peng; Yanling Xu; Shuyi Wang; Xiaofei Liao; Qinbin Li; |
| 34 | Diffusion-based Spatio-temporal Interpolation with Dynamic Sensor Sets Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce DynaSTI, a diffusion-based generative framework that is fully inductive to unseen locations, trains directly on incomplete observations, and remains effective without retraining when sensor networks change with time. |
Mohammad Rafid Ul Islam; Prasad Tadepalli; Alan Fern; |
| 35 | MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose MemGraphRAG, a novel framework that introduces a memory-based multi-agent system to ensure high-quality graph construction. |
Chuanjie Wu; Zhishang Xiang; Yunbo Tang; Zerui Chen; Qinggang Zhang; Jinsong Su; |
| 36 | FinWorld: An All-in-One Open-Source Platform for End-to-End Financial AI Research and Deployment Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing platforms remain limited in task coverage, lack robust multimodal data integration, and offer insufficient support for the training and deployment of large language models (LLMs). In response to these limitations, we present FinWorld, an all-in-one open-source platform that provides end-to-end support for the entire financial AI workflow, from data acquisition to experimentation and deployment. |
Wentao Zhang; Yilei Zhao; Chuqiao Zong; Xinrun Wang; Bo An; |
| 37 | GraphSkill: Documentation-Guided Agentic Hierarchical Retrieval-Augmented Coding for Complex Graph Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To address them, we propose GraphSkill, an agentic hierarchical retrieval-augmented coding framework that exploits the document hierarchy through top-down traversal and early pruning, together with a self-debugging coding agent that iteratively refines code using automatically generated small-scale test cases. |
Fali Wang; Chenglin Weng; Xianren Zhang; Siyuan Hong; Hui Liu; Suhang Wang; |
| 38 | The Best of Both Worlds: Harmonizing Semantic and Hash IDs for Sequential Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Nevertheless, SID-based methods are hindered by a collaborative overwhelming phenomenon: commonly adopted quantization mechanisms compromise the identifier uniqueness needed to model head items, resulting in a performance trade-off between head and tail items. To address this challenge, we propose H2Rec, a novel framework that harmonizes SID and HID. |
Ziwei Liu; Yejing Wang; Wanyu Wang; Wang Zejian; Qidong Liu; Zijian Zhang; Wei Huang; Chong Chen; Xiangyu Zhao; |
| 39 | OTPCL: Optimal Transport Driven Pseudo-Labeling with Contrastive Learning for Social Bot Detection Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Unlabeled data are often underutilized, making supervision sparse. To address this, we propose OTPCL (Optimal Transport Driven Pseudo-Labeling with Contrastive Learning), a plug-in framework for GNN-based social bot detection. |
Ruixuan Xu; Mengting Hu; Xinqi Yang; Ming Jiang; Zhunheng Wang; Hang Gao; Renhong Cheng; |
| 40 | Offline Behavioral Data Selection Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we uncover the striking data saturation in offline behavioral data: policy performance rapidly saturates when trained on a small fraction of the dataset. |
Shiye Lei; Zhihao Cheng; Dacheng Tao; |
| 41 | Towards Efficient Embodied Reasoning: Mixture-of-Depth Compute Allocation for Vision-Language-Action Model Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In contrast, rate-distortion principles aim to reduce computation while retaining control-sufficient information. Inspired by this insight, we introduce Effective-Edge Flow, an action-aligned attribution measure that quantifies the marginal contribution of token interactions across network depth. |
Weiying Xie; Qingchen Zeng; Zihan Meng; Jiayun Tian; Sibo He; Danian Yang; Jie Du; Yunke Wang; Daixun Li; Hengyi Wang; Jitao Ma; Leyuan Fang; Yunsong Li; |
| 42 | DeepTaxon: An Interpretable Retrieval-Augmented Multimodal Framework for Unified Species Identification and Discovery Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Here we present DeepTaxon, a retrieval-augmented multimodal framework that unifies species identification and discovery through interpretable reasoning over retrieved visual evidence. |
Jiawei Wang; Ming Lei; Yaning Yang; Xinyan Lin; Yuquan Le; Qiwei Ma; Zhiwei Xu; Zheqi Lv; Yuchen Ang; Zhe Quan; Tat-Seng Chua; |
| 43 | LiveMedBench: A Contamination-Limited Medical Benchmark for LLMs with Automated Rubric Evaluation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a Multi-Agent Clinical Curation Framework that filters raw data noise and validates clinical integrity against evidence-based medical principles. |
Zhiling Yan; Dingjie Song; Zhe Fang; Yisheng Ji; Xiang Li; Quanzheng Li; Lichao Sun; |
| 44 | Rethinking and Red-Teaming Protective Perturbation in Personalized Diffusion Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we conduct an in-depth analysis of the fine-tuning process of PDMs through the lens of shortcut learning. |
Yixin Liu; Ruoxi Chen; Xun Chen; Lichao Sun; |
| 45 | Rethinking Scientific Modeling: Toward Physically Consistent and Simulation-Executable Programmatic Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, non-executable or physically inconsistent outputs remain prevalent under stringent engineering constraints. A framework for physics-consistent automatic building modeling is therefore proposed, integrating domain knowledge construction, constraint-oriented model alignment, and verification-driven evaluation. |
Yongqing Jiang; Jianze Wang; Zhiqi Shen; Zhenghong Lin; Jiayuan Wang; Yijian Yang; Kaoshan Dai; Haoran Luo; |
| 46 | Black-Box Embedding Inversion Attack on Vector Databases Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a novel black-box image embedding inversion attack that reconstructs high-fidelity images using only query access to the embedding model or API. |
Lichao Sun; Yuncheng Wu; Haichao Sha; Xinjian Luo; Mingyang Yi; Meihui Zhang; Cuiping Li; Hong Chen; |
| 47 | Reasoning Over Semantic IDs Enhances Generative Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Itemic tokens are not natively meaningful to LLMs; moreover, recommendation-oriented SID reasoning is hard to evaluate, making high-quality supervision scarce. To address these challenges, we propose SIDReasoner, a two-stage framework that elicits reasoning over SIDs by strengthening SID–language alignment to unlock transferable LLM reasoning, rather than relying on large amounts of recommendationspecific reasoning traces. |
Yingzhi He; Yan Sun; Junfei Tan; Yuxin Chen; Xiaoyu Kong; Chunxu Shen; Xiang Wang; An Zhang; Tat-Seng Chua; |
| 48 | Can Large Language Models Derive New Knowledge? A Dynamic Benchmark for Biological Knowledge Discovery Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Furthermore, the rapid release cycles of modern LLMs render static benchmarks quickly outdated, failing to assess the ability to discover truly new knowledge. To address these limitations, we propose DBench-Bio, a dynamic and fully automated benchmark designed to evaluate AI’s biological knowledge discovery ability. |
Chaoqun Yang; Xinyu Lin; Shulin Li; Wenjie Wang; Ruihan Guo; Fuli Feng; Tat-Seng Chua; |
| 49 | Devil’s Hand: Data Poisoning Attacks to Locally Private Graph Learning Protocols Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This work introduces the first data poisoning attack targeting locally private graph learning protocols. |
Longzhu He; Chaozhuo Li; Peng Tang; Li Sun; Sen Su; Philip S. Yu; |
| 50 | On The Memorization and Generalization of Generative Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Finally, we show that the two paradigms are complementary. We propose a simple memorization-aware indicator that adaptively combines them on a per-instance basis, leading to improved overall recommendation performance. |
Yijie Ding; Zitian Guo; Jiacheng Li; Letian Peng; Shuai Shao; Wei Shao; Xiaoqiang Luo; Luke Simon; Jingbo Shang; Julian McAuley; Yupeng Hou; |
| 51 | The Sim-to-Real Gap of Foundation Model Agents: A Unified MDP Perspective Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we set a comprehensive research agenda that translates classical discrepancies into the foundation model domain and advocates for adopting established solutions like domain randomization. |
Xiaoou Liu; Tiejin Chen; Weibo Li; Xiyang Hu; Hua Wei; |
| 52 | Interactive Recommendation Agent with Active User Commands Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: These fundamental limitations create a persistent gap between user intentions and system interpretations, ultimately undermining user satisfaction and harming system effectiveness. To address these limitations, we introduce the Interactive Recommendation Feed (IRF), a pioneering paradigm that enables natural language commands within mainstream recommendation feeds. |
Jiakai Tang; Wen Chen; Yujie Luo; Xunke Xi; Yi Chao; Dian Chen; Zhujin Gao; Yang Li; Fei Sun; Xueyang Feng; Sunhao Dai; Xu Chen; Jian Wu; Yuning Jiang; Bo Zheng; |
| 53 | OPBench: A Graph Benchmark to Combat The Opioid Crisis Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Through extensive experiments, we analyze the strengths and limitations of existing graph learning methods, thereby providing actionable insights for future research in combating the opioid crisis. |
Tianyi Ma; Yiyang Li; Yiyue Qian; Jiatan Huang; Zheyuan Zhang; Zehong Wang; Chuxu Zhang; Yanfang Ye; |
| 54 | Breaking The Listwise-Shuffle Dilemma: A Streaming-Compatible Listwise Framework for Industrial CTR Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose Decoupled Listwise Learning (DLL), a streaming-compatible paradigm that reconstructs session-level supervision without session batching. |
Junlin He; Rui Tang; Liyin Hong; |
| 55 | Evaluating Long-Horizon Memory for Multi-Party Collaborative Dialogues Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we introduce EverMemBench, the first benchmark designed for long-horizon collaborative memory, built from multi-party, multi-group conversations spanning over one million tokens with dense cross-topic interleaving, temporally evolving decisions, and role-conditioned personas. |
Chuanrui Hu; Tong Li; Xingze Gao; Hongda Chen; Yi Bai; Dannong Xu; Tianwei Lin; Xiaohong Li; Yunyun Han; Jian Pei; Yafeng Deng; |
| 56 | ProductWebGen: Benchmarking Multimodal Product Webpage Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, this paper introduces ProductWebGen to systematically benchmark the product webpage generation capacities of these models. |
Zhihong Liu; Siqi Kou; Zheng Li; Ye Ma; Quan Chen; Peng Jiang; Kai Yu; Zhijie Deng; |
| 57 | SWE-Bench Mobile: Can Large Language Model Agents Develop Industry-Level Mobile Applications? Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce SWE-Bench Mobile, a benchmark for evaluating coding agents on realistic software engineering tasks derived from a production iOS codebase. |
Muxin Tian; Zhe Wang; Zhenwei Tang; Blair Yang; Kunlun Zhu; Honghua Dong; Hanchen Li; Xinni Xie; Guangjing Wang; Jiaxuan You; |
| 58 | Component-based Reusable UI Code Generation for Complex Websites Via Semantic Segmentation and Fine-grained Feedback Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To systematically investigate and address these challenges, we introduce ComUIBench, a new multi-page complex webpage benchmark with component annotations, designed to evaluate MLLMs’ ability to generate reusable UI code in realistic website scenarios. Building upon this benchmark, we propose ComUICoder, a component-based UI code generation framework that emphasizes semantic-aware segmentation, code reuse, and fine-grained refinement. |
Jingyu Xiao; Jiantong Qin; Shuoqi Li; Man Ho Lam; Yuxuan Wan; Jen-tse Huang; Yintong Huo; Michael R. Lyu; |
| 59 | TimeDistill: Efficient Long-Term Time Series Forecasting with MLP Via Cross-Architecture Distillation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Our preliminary study reveals different models can capture complementary patterns, particularly multi-scale and multi-period patterns in the temporal and frequency domains. Based on this observation, we introduce TimeDistill, a cross-architecture KD framework that transfers these patterns from teacher models (e.g., Transformers, CNNs) to MLP. |
Juntong Ni; Zewen Liu; Shiyu Wang; Ming Jin; Wei Jin; |
| 60 | SDE : Scale-Difference Evolution Knowledge Distillation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, conventional methods typically rely on static, single-scale logit alignment, thereby overlooking the semantic evolution trajectory embedded in cross-scale prediction transitions. To bridge this gap, we propose Scale-Difference Evolution distillation (SDE), formulated in a structure-aware manner. |
Hejie Lu; |
| 61 | Scaling Recommender Transformers to One Billion Parameters Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we present a recipe for training large transformer recommenders with up to one billion parameters. |
Kirill Khrylchenko; Artem Matveev; Sergei Makeev; Vladimir Baikalov; |
| 62 | Agentic LLMs for Social Network Generation Using Explainable Adversarial Re-prompting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To address this, we introduce a paradigm shift by incorporating a discriminator based on social bot detection techniques for assessing network realism. Building upon this, we propose an innovative social network generation method that integrates agentic LLMs with eXplainable Adversarial Re-Prompting (X-ARP). |
Haorui Yan; Lixing Chen; Bo Zhang; Hongfu Liu; Hao Peng; Shenghong Li; Yang Bai; Zhe Qu; |
| 63 | Concord: Building Consensus Representations for Single Cells with Collaborative Random Projection Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose Concord, a novel single-cell FM that explicitly models relationships between gene identities and expression levels through a collaborative rotary attention (CRA) mechanism. |
Kaichen Xu; Mianpeng Liu; Hao Wu; Wenjing Ma; Xiaobo Sun; |
| 64 | AISE-Bench: A Full-Cycle Curated Benchmark for Information Seeking on Academic Knowledge Graphs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce AISE-Bench, a real-world, full-cycle annotated benchmark for information seeking on academic knowledge graphs. |
Fanjin Zhang; Zhengyang Wang; Ruixuan Huang; Kefan Zhang; Amy Xin; Yuanchun Wang; Shu Zhao; Evgeny Kharlamov; Jie Tang; Juanzi Li; |
| 65 | AlzheimerODE: A Knowledge-Guided Generative Model for Alzheimer’s Disease Progression Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing generative approaches either struggle to capture the continuous-time dynamics or neglect the biological constraints that govern disease evolution. To address these challenges, we present AlzheimerODE, a knowledge-guided generative framework that learns structured disease dynamics as a reaction–diffusion flow in continuous time. |
Yuhao Jiang; Junbo Ma; Guoqiu Wen; Xinjie Han; Hongqing He; Jiayang Su; Fan Yang; Minghan Chen; |
| 66 | GraphMind: Unveiling Scientific Reasoning Through Contextual Graphs for Novelty Assessment Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To address this gap, we introduce SciNova, a benchmark containing 3,063 papers from both ICLR and NeurIPS, with full content, bibliographies, and peer review scores for novelty prediction. Building on this benchmark, we propose GraphMind, a model that jointly processes micro- and macro-level structures for novelty prediction and rationale generation. |
Italo Luis da Silva; Hanqi Yan; Lin Gui; Yulan He; |
| 67 | Multi-Hop Diffusion-Wavelet Semantic Learning for Zero-Shot Circrna-Mirna Interaction Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose BioWave, a multi-hop diffusion-wavelet model that learns both structural and semantic representations for accurate CMI prediction. |
Mengmeng Wei; Lei Wang; Pengwei Hu; Yuan Huang; Zhian Huang; Bowei Zhao; Zhuhong You; |
| 68 | One Rounding Fits All: Memory-Efficient Approximation Algorithms for Partition-Constrained Influence Maximization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Despite its strong theoretical guarantee, RAMP is often hindered by its prohibitive memory overhead, as it must maintain 1/ε intermediate subsets during rounding, and sample inefficiency caused by requiring an additional RR set collection exclusively for solution evaluation. To overcome these limitations, we propose RBwA, a memory-efficient and sample-efficient progressive sampling algorithm for IM-PC. |
Qixin Zhang; Qirun Zeng; Hui Lu; Pingchuan Ma; Jinhang Zuo; Renqiang Luo; Yi Yu; Dacheng Tao; |
| 69 | From Clicks to Preference: A Multi-stage Alignment Framework for Generative Query Suggestion in Conversational System Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Generative query suggestion using large language models offers a powerful way to enhance conversational systems, but aligning outputs with nuanced user preferences remains a critical challenge. To address this, we introduce a multi-stage framework designed for progressive alignment between the generation policy and user intent. |
Junhao Yin; Haolin Wang; Peng Bao; Ju Xu; Yongliang Wang; |
| 70 | M3BERT: A Modern, Multi-lingual, Matryoshka Bidirectional Encoder Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This method is often suboptimal as the misalignment between pretraining and downstream usage prevents full realization of pretraining benefits. To address this limitation, we introduce m3BERT: a Modern, Multi-lingual, Matryoshka Bidirectional Encoder, which features a novel pretraining strategy that jointly optimizes representations across both transformer layers and multiple embedding dimensions. |
Yaoxiang Wang; Simiao Zuo; Qingguo Hu; Yucheng Ding; Yeyun Gong; Jian Jiao; Jinsong Su; |
| 71 | SAFT: Safety-Preserving Adaptation Via Fine-Tuning Transfer for Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose SAFT (Safety-preserving Adaptation via Fine-tuning Transfer), a safety-preserving adaptation framework that decouples task learning from alignment preservation by learning a safety-guided task update on the paired pretrained base model, rectifying task gradients to avoid conflicting directions with respect to a safety objective, and then transferring the update to the frozen instruction model via parameter-space grafting. |
Zhiwen Ruan; Yan Yang; Zhuocheng Liang; Yun Chen; Guanhua Chen; |
| 72 | Deterministic-Allocation and Anonymous Joint Advertising in E-commerce Platforms Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we prove that in all online advertising scenarios, previous non-deterministic allocation methods lead to the non-existence of feasible solutions, resulting in a gap between the rounded solution and the optimal solution. |
Zhen Zhang; Luowen Liu; Wanzhi Zhang; Zitian Guo; Kun Huang; Qi Qi; Qianlong Xie; Xingxing Wang; |
| 73 | OneRank: Unified Transformer-Native Ranking Architecture for Multi-Task Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose OneRank, a Transformer-native multi-task ranking framework that eliminates the encoder–predictor separation and introduces task-private channels for both forward representation learning and backward optimization, enabling task-specialized learning while minimizing inter-task interferences. |
Jiakai Tang; Sunhao Dai; Kun Wang; Zhiluohan Guo; Yu Zhao; Cong Fu; Kangle Wu; Yabo Ni; Anxiang Zeng; Xu Chen; Jun Xu; |
| 74 | CCD: Capturing Cross-Correlations with Deformable Convolutional Networks for Multivariate Time Series Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In summary, we propose a novel framework called CCD, which Captures Cross-Correlations with Deformable Convolutional Networks for Multivariate Time Series Forecasting. |
Hanyin Cheng; Xingjian Wu; Xiangfei Qiu; Yang Shu; Bin Yang; Chenjuan Guo; |
| 75 | Can Prompt Difficulty Be Online Predicted for Accelerating RL Finetuning of Reasoning Models? Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Appropriate online prompt selection methods reduce iteration steps by prioritizing informative prompts during training, while the pipeline’s reliance on exhaustive prompt evaluation and subset selection for optimization still incurs substantial computational overhead due to frequent LLM inference calls. |
Yun Qu; Qi Wang; Yixiu Mao; Vincent Tao Hu; Bj{\o}rn Ommer; Xiangyang Ji; |
| 76 | OnePiece: Bringing Context Engineering and Reasoning to Industrial Cascade Ranking System Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose OnePiece, a unified framework that seamlessly integrates LLM-style context engineering and reasoning into both retrieval and ranking models of industrial cascaded pipelines. |
Sunhao Dai; Jiakai Tang; Jiahua Wu; Kun Wang; Yuxuan Zhu; Bingjun Chen; Bangyang Hong; Yu Zhao; Cong Fu; Kangle Wu; Yabo Ni; Anxiang Zeng; Wenjie Wang; Xu Chen; Jun Xu; See-Kiong Ng; |
| 77 | Distribution-Value Coevolution for Adaptive RLHF Data Scheduling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We identify and formalize the Distribution-Value Coevolution principle: the training value of data is not intrinsic, but emerges dynamically from the interaction between data characteristics and the model’s evolving capability boundary. |
Zairun Yang; Yanbo Yang; Chenyi Zhou; Xinyu Guan; Baohua Dong; Meng Zhang; Keyan Ding; Hangcheng Zhu; Huajun Chen; Qiang Zhang; |
| 78 | Chat2Trade: Automating Financial RFQ Parsing with Fine-Tuned LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: The core task of this system is to automatically parse RFQs into structured data, which faces two key challenges: highly domain-specific jargon in RFQs and the rapid evolution of jargon patterns. To address these challenges, we propose an RFQ parsing method based on fine-tuned large language models (LLMs). |
Yixuan Cao; Chunhao Yang; Yifan Wang; Jian Wang; Kun Wan; Gang Xiao; Ping Luo; |
| 79 | PeroMAS: A Multi-agent System of Perovskite Material Discovery Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a multi-agent system for perovskite material discovery, named PeroMAS. |
Yishu Wang; Wei Liu; Yifan Li; Shengxiang Xu; Xujie Yuan; Ran Li; Yuyu Luo; Jia Zhu; Shimin Di; Min-Ling Zhang; Guixiang Li; |
| 80 | Dripper: Token-Efficient Main HTML Extraction with A Lightweight LM Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Conversely, well-pretrained generative Large Language Models (LLMs) offer superior document comprehension but remain impractical at web scale due to excessive computational costs, limited context windows, and hallucination risks. We present Dripper, a lightweight framework that resolves these bottlenecks through four contributions: (1) We reformulate extraction as a constrained sequence labeling task using SLMs (Small Language Models). |
Mengjie Liu; Jiahui Peng; Wenchang Ning; Pei Chu; Jiantao Qiu; Ren Ma; He Zhu; Rui Min; Lindong Lu; Linfeng Hou; Kaiwen Liu; Yuan Qu; Zhenxiang Li; Chao Xu; Zhongying Tu; Wentao Zhang; Conghui He; |
| 81 | MedJudge: Medical Multimodal Reward Modeling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce MedJudge, a multimodal medical reward modeling method that supports interpretable, evidence-grounded, and clinically-aligned decision evaluation. |
Yunhong He; Kai Zhang; Jiarong Qian; Zhengqing Yuan; Yanfang Ye; Jing Huang; Lichao Sun; |
| 82 | MACReD: A Multi-Agent Collaborative Reasoning Framework for Reaction Diagram Parsing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing Vision Language Models advance multimodal understanding but remain unreliable on complex reaction diagrams, where spatial coherence, condition attribution, and reaction-level structural consistency must be jointly resolved. To address these issues, we propose MACReD, a hierarchical multi-agent framework that coordinates specialized agents for molecular perception, arrow understanding, text extraction, and reaction reconstruction within a unified VLM-guided architecture. |
Chuang Tang; Chenhao Lin; Yin Xu; Hao Wang; Jinrui Zhou; Xin Li; Mingjun Xiao; Enhong Chen; |
| 83 | AnyPPG: An ECG-Guided PPG Foundation Model Trained on Over 100,000 Hours of Recordings for Holistic Health Profiling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, despite being a peripheral hemodynamic signal intrinsically coupled with systemic circulation, existing research has largely confined its scope to a narrow range of cardiovascular tasks, leaving a fundamental question underexplored: to what extent can PPG support holistic health profiling beyond traditional cardiovascular applications? To answer this question, we present AnyPPG, a foundation model-based framework designed to reveal the broader health-profiling potential of PPG. |
Guangkun Nie; Xiaocheng Fang; Gongzheng Tang; Yujie Xiao; Jun Li; Bo Liu; Hongyan Li; Shenda Hong; |
| 84 | TAMEing Long Contexts in Personalization: Towards Training-Free and State-Aware MLLM Personalized Assistant Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: As a strong baseline for LCMP, we introduce a novel training-free and state-aware framework TAME. |
Rongpei Hong; Jian Lang; Ting Zhong; Yong Wang; Fan Zhou; |
| 85 | Stabilizing Physics-Informed Consistency Models Via Structure-Preserving Training Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a physics-informed consistency modeling framework for solving partial differential equations (PDEs) via fast, few-step generative inference. |
Che-Chia Chang; Chen-Yang Dai; Te-Sheng Lin; Ming-Chih Lai; Chieh-Hsin Lai; |
| 86 | A Perturbation-Augmented Unsupervised Learning Framework for Integer Linear Programming Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing methods often converge prematurely to polarized probability distributions, losing solution diversity and trapping the process in local optima. To alleviate this, we propose PUMA, a Perturbation-augmented Unsupervised learning fraMework for integer linear progrAmming. |
Yufan Deng; Tianle Pu; Zhijing Hu; Zijie Geng; Li Zeng; Xingchen Hu; Kuihua Huang; Junjie Wu; Changjun Fan; |
| 87 | Learning Probabilistic Compositional Representation of Crystalline Materials Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we introduce PCRL, a novel approach that employs probabilistic modeling of composition to capture the diverse polymorphs from available structural information. |
Namkyeong Lee; Heewoong Noh; Gyoung S. Na; Jimeng Sun; Tianfan Fu; Marinka Zitnik; Chanyoung Park; |
| 88 | APEX-SQL: Talking to The Data Via Agentic Exploration for Text-to-SQL Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: The primary limitation lies in their reliance on static schema representations, which fails to resolve semantic ambiguity and scale effectively to large, complex databases. To address this, we propose APEX-SQL, an Agentic Text-to-SQL Framework that shifts the paradigm from passive translation to agentic exploration. |
Bowen Cao; Weibin Liao; Yushi Sun; Dong Fang; Haitao Li; Wai Lam; |
| 89 | Aura: Universal Multi-dimensional Exogenous Integration for Aviation Time Series Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we delve into an aviation maintenance scenario and identify three distinct types of exogenous factors that influence temporal dynamics through distinct interaction modes. |
Jiafeng Lin; Mengren Zheng; Simeng Ye; Yuxuan Wang; Huan Zhang; Yuhui Liu; Zhongyi Pei; Jianmin Wang; |
| 90 | HGenPush: A Heterogeneous Generative Recommendation Architecture for Industrial Push Notification Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose an end-to-end heterogeneous generative recommendation architecture called HGenPush. |
Xiao Liang; Jiali Feng; Xin Feng; Yiqing Wang; Baolin Ye; Siyao Feng; Zhihui Deng; Cunyi Zhang; Huajin Sun; Xuanping Li; Kaiqiao Zhan; Yanan Niu; Kun Gai; |
| 91 | Reinforcement Learning for Path Integrals in Quantum Statistical Physics Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we explore how reinforcement learning can be used to compute a class of Euclidean path integrals that yield the thermal density matrix of a quantum system, thereby enabling the computation of the free energy or other thermal expectation values. |
Timour Ichmoukhamedov; Dries Sels; |
| 92 | Slow-OCast: Slow-Varying Motion Inspired Transfer Learning for Regional High-Resolution Ocean Environmental Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, as data resolution increases, the training and computational costs of existing approaches increase substantially. To address this issue, we introduce Slow-OCast, a transfer-learning based model designed for high-resolution ocean environmental forecasting. |
Qixiu Li; Xiang Zhu; Xiaoyong Li; Haolong Xiang; Xiaolong Xu; |
| 93 | Learning and Editing Universal Graph Prompt Tuning Via Reinforcement Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we propose a novel model and paradigm, Learning and Editing Universal GrAph Prompt Tuning (LEAP), which preserves the theoretical foundation of universal graph prompt tuning while pursuing more ideal prompts. |
Jinfeng Xu; Zheyu Chen; Shuo Yang; Jinze Li; Hewei Wang; Yijie Li; Edith C. H. Ngai; |
| 94 | VI-MMRec: Similarity-Aware Training Cost-free Virtual User-Item Interactions for Multimodal Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we propose VI-MMRec, a model-agnostic and training cost-free framework that enriches sparse user-item interactions via similarity-aware virtual user-item interactions. |
Jinfeng Xu; Zheyu Chen; Shuo Yang; Jinze Li; Zitong Wan; Hewei Wang; Weijie Liu; Yijie Li; Edith C. H. Ngai; |
| 95 | A Physics-Aware Framework for Short-Term GPU Power Forecasting of AI Data Centers Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper we propose, to the best of our knowledge, the first physics-informed DLinear time-series model that can accurately forecast power utilization of an AI data center 5-80 minutes (short-term forecasting) into the future. |
Mohammad AlShaikh Saleh; Sanjay Chawla; Sertac Bayhan; Haitham Abu-Rub; Ali Ghrayeb; |
| 96 | Battery-Sim-Agent: Leveraging LLM-Agent for Inverse Battery Parameter Estimation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce a new paradigm that reframes the inverse problem as a reasoning task, and present Battery-Sim-Agent, the first framework to deploy a Large Language Model (LLM) agent in a closed loop with a high-fidelity battery simulator. |
Jiawei Chen; Xiaofan Gui; Shikai Fang; Shengyu Tao; Shun Zheng; Weiqing Liu; Jiang Bian; |
| 97 | Think Less, Act Warranted: Efficient Tool-Integrated Reasoning Via Dual-Efficiency Regularization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Despite these advances, existing methods often suffer from overthinking at both the action and reasoning levels: models tend to invoke tools redundantly and generate excessively long reasoning trajectories, resulting in high computational cost. To address this, in this paper, we propose LightTIR, a dual-penalty reward framework, to achieve efficient TIR. |
Yichen Xiao; Siyu Gong; Linan Yue; |
| 98 | LLaTTE: Scaling Laws for Multi-Stage Sequence Modeling in Large-Scale Ads Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present LLaTTE (LLM-Style Latent Transformers for Temporal Events), a scalable transformer architecture for production ads recommendation. |
Lee Xiong; Zhirong Chen; Rahul Mayuranath; Shangran Qiu; Ahmet Arda Ozdemir; Lu Li; Yang Hu; Dave Li; Jingtao Ren; Howard Cheng; Fabian Souto Herrera; Ahmed Agiza; Allen Lin; Baruch Epstein; Anuj Aggarwal; Julia Ulziisaikhan; Chao Wang; Dinesh Ramasamy; Parshva Doshi; Sri Reddy; Arnold Overwijk; |
| 99 | SOP-Bench: Complex Industrial SOPs for Evaluating LLM Agents Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce SOP-Bench, a benchmark of 2,000+ tasks from human expert-authored SOPs across 12 business domains (healthcare, logistics, finance, content moderation, etc.). |
Subhrangshu Nandi; Arghya Datta; Rohith Nama; Udita Patel; Nikhil Vichare; Indranil Bhattacharya; Shivam Asija; Arushi Gupta; Giuseppe Carenini; Jing Xu; Shayan Ray; Huzefa Raja; Aaron Chan; Francesco Carbone; Esther Xu Fei; Gaoyuan Du; Zuhaib Akhtar; Prince Grover; Sreyoshi Bhaduri; Weian Chen; Wei Zhang; Ming Xiong; Harshita Asnani; Jeetu Mirchandani; |
| 100 | GALS-Fold: Geometry-Aware Long-Short RNA Inverse Folding with Linear Scaling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose GALS-Fold, a Geometry-Aware Long-Short framework that reconciles local geometric fidelity with efficient global context. |
Xiangyu Wen; Yujing Bian; Hengrui Gu; Kaixiong Zhou; |
| 101 | Learning to Evaluate: Cost-Effective Model Evaluation on Unlabeled Data with Meta-Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce MetaEvaluator, a cost-effective, model-agnostic framework for fast, label-free evaluation of unseen models across diverse architectures and modalities. |
Trinh Pham; Viet Huynh; Hongzhi Yin; Quoc Viet Hung Nguyen; Thanh Tam Nguyen; |
| 102 | When Compilation Breaks Your GNN: A Numerical Stability Perspective Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Based on this analysis, we propose Numerics-Aware Graph Compilation (NAGC), which estimates per-aggregation numerical risk through lightweight profiling and selectively applies aggressive optimizations only to well-conditioned operations. |
Jiawei Gu; Zechao Li; |
| 103 | Mining Intrinsic Rewards from LLM Hidden States for Efficient Best-of-N Sampling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This creates a significant data challenge, as they overlook a rich, readily available data source: the LLM’s own internal hidden states. To address this data and efficiency gap, we introduce SWIFT (Simple Weighted Intrinsic Feedback Technique), a novel and lightweight method that learns a reward function directly from the rich information embedded in LLM hidden states. |
Jizhou Guo; Zhaomin Wu; Hanchen Yang; Philip S. Yu; |
| 104 | Why Retrieval-Augmented Generation Fails: A Graph Perspective Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a model-internal study of retrieval-augmented generation that examines how retrieved evidence influences answer generation. |
Kai Guo; Xinnan Dai; Zhibo Zhang; Nuohan Lin; Shenglai Zeng; Jie Ren; Haoyu Han; Jiliang Tang; |
| 105 | Breaking Information Cocoons: A Hyperbolic Framework for Balancing Exploration and Exploitation in Recommender Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing approaches face two fundamental limitations: Euclidean methods struggle to capture hierarchical structures, while hyperbolic methods, despite their superior hierarchical modeling, lack semantic understanding of user and item profiles and fail to provide a principled mechanism for balancing exploration and exploitation. To address these challenges, we propose HERec, a hyperbolic framework that effectively balances exploration and exploitation in recommender systems. |
Qiyao Ma; Menglin Yang; Mingxuan Ju; Tong Zhao; Neil Shah; Rex Ying; |
| 106 | CoPersona: Collaborative Persona Graphs for Robust LLM Personalization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: As a result, weakly observed user attributes are difficult to infer, leading to brittle personalization when test-time requests shift toward under-supported facets. Motivated by this limitation, we present CoPersona, a graph-based collaborative personalization framework that completes sparse user profiles by borrowing signals from behaviorally similar peers. |
Yangtian Zhang; Leyao Wang; Hiren Madhu; Ngoc Bui; Walter Roznyatovskiy; Rex Ying; |
| 107 | DocRetriever: A Plug-and-Play Framework for Multimodal Document Retrieval with Comprehensive Benchmark Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Furthermore, existing benchmarks often lack diverse assessment dimensions and comprehensive relevance annotations, limiting reliable evaluation. To address these challenges, we propose DocRetriever, a plug-and-play framework. |
Ruofan Hu; Menghui Zhu; Jieming Zhu; Bo Chen; Shengyang Xu; Minjie Hong; Xiaoda Yang; Sashuai Zhou; Li Tang; Tao Jin; Zhou Zhao; |
| 108 | TaoSR1: The Thinking Model for E-commerce Relevance Search Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, most still adopt discriminative paradigms or ultimately distill knowledge to BERT models for deployment. In this paper, we propose an optimization framework based on large language models and directly deploy these models in online systems. |
Chenhe Dong; Shaowei Yao; Pengkun Jiao; Jianhui Yang; Yiming Jin; Zerui Huang; Xiaojiang Zhou; Dan Ou; Haihong Tang; Bo Zheng; |
| 109 | Closing Reasoning Gaps in Clinical Agents with Differential Reasoning Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose Differential Reasoning Learning (DRL), a framework that improves clinical agents by learning from reasoning discrepancies. |
Jinsong Liu; Yuhang Jiang; Ramayya Krishnan; Rema Padman; Yiye Zhang; Jiang Bian; |
| 110 | RouteGoT: Node-Adaptive Routing for Cost-Efficient Graph of Thoughts Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We attribute this inefficiency to stage-wise and node-wise heterogeneity inside GoT-style reasoning pipelines: high-quality planning and final synthesis are globally coupled and typically benefit from strong models, whereas many intermediate subtasks are localized and can be solved accurately by lighter models with far fewer tokens. Motivated by these observations, we propose RouteGoT, a budget-controllable, node-adaptive routing framework for graph-structured reasoning. |
Yuhang Liu; Ruijie Wang; Yunlong Chu; Bing Hao; Yumeng Lin; Shengzhong Liu; Minglai Shao; |
| 111 | CausalT5k: Diagnosing Refusal and Failure Modes in Trustworthy Causal Reasoning Across Causal Rungs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce CTK, a diagnostic benchmark of 5,147 cases and growing, across 10 domains and all three levels of Pearl’s Ladder of Causation. |
Longling Geng; Andy Ouyang; Theodore Wu; Daphne Barretto; Matthew J. Hayes; Rachael Cooper; Yuqiao Zeng; Sameer Vijay; Gia Ancone; Ankit Rai; Matthew Wolfman; Patrick Flanagan; Edward Y Chang; |
| 112 | MGFRec: Towards Reinforced Reasoning Recommendation with Multiple Groundings and Feedback Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This has led to over-interpreting user interests and deviating from real items. Towards this research gap, we propose performing multiple rounds of grounding during inference to help the LLM better understand the actual item space, which could ensure that its reasoning remains aligned with real items. |
Shihao Cai; Chongming Gao; Haoyan Liu; Wentao Shi; Jianshan Sun; Ruiming Tang; Fuli Feng; |
| 113 | FedMed: Federated Learning-Based Personalized and Safe Medication Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, this setting exposes sensitive patient data to privacy risks and potential leakage. To address this issue, we propose FedMed, a privacy-preserving, personalized, and safe medication recommender based on federated learning. |
Anchen Li; Elena Casiraghi; Juho Rousu; |
| 114 | Efficient and Scalable Neural-Symbolic Search for Complex Query Answering Over Incomplete Knowledge Graphs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Consequently, these approaches struggle to scale effectively to large knowledge graphs and complex queries. To address these limitations, we propose an efficient and scalable symbolic search method comprising two key components: (1) constraint strategies that drastically reduce the variable search domain, lowering data complexity; and (2) a local search algorithm that approximately solves NP-hard cyclic queries. |
Weizhi Fei; Zihao Wang; Hang Yin; Shukai Zhao; Wei Zhang; Yangqiu Song; |
| 115 | Neural Scalable Symbolic Search Framework for Complex Logical Queries with Multiple Free Variables Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Building on neural symbolic search for EFO1 queries, we propose Neural Scalable Symbolic Search (NS3), a budgeted framework that approximates joint ranking without enumerating Ek . |
Weizhi Fei; Hang Yin; Zihao Wang; Shukai Zhao; Wei Zhang; Yangqiu Song; |
| 116 | FineFT: Efficient and Risk-Aware Ensemble Reinforcement Learning for Futures Trading Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Second, prior works lacked self-awareness of capability boundaries, exposing them to the risk of significant capital loss when encountering previously unseen market state representations (e.g., during a black swan event like COVID-19). To tackle these challenges, we propose the eFficient and rIsk-aware eNsemble rEinforcement learning for Futures Trading (FineFT), a novel three-stage ensemble RL framework with stable training and proper risk management. |
Molei Qin; Xinyu Cai; Yewen Li; Haochong Xia; Chuqiao Zong; Shuo Sun; Xinrun Wang; Bo An; |
| 117 | Bayesian Robust Financial Trading with Adversarial Synthetic Market Data Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We identify two core challenges that perpetuate this mismatch: (1) insufficient robustness in existing policy against uncertainties in high-level market fluctuations, and (2) the absence of a realistic and diverse simulation environment for training, leading to policy overfitting. To address these issues, we propose a Bayesian Robust Framework that systematically integrates a macro-conditioned generative model with robust policy learning. |
Haochong Xia; Simin Li; Ruixiao Xu; Zhixia Zhang; Hongxiang Wang; Zhiqian Liu; Teng Yao Long; Molei Qin; Chuqiao Zong; Bo An; |
| 118 | BacktestBench: Benchmarking Large Language Models for Automated Quantitative Strategy Backtesting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While Large Language Models (LLMs) offer a transformative path to automate this complex, interdisciplinary workflow through advanced code generation, tool usage, and agentic planning, the practical realization is significantly challenged by the current lack of a large-scale benchmark dedicated to automated quantitative backtesting, which hinders progress in this field. To bridge this critical gap, we introduce BacktestBench, the first large-scale benchmark for automated quantitative backtesting. |
Zhensheng Wang; Wenmian Yang; Qingtai Wu; Lequan Ma; Yiquan Zhang; Weijia Jia; |
| 119 | RePatch: Learning Entropy-Guided Patch Structures with Quantized Representations for Time Series Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose RePatch, a two-stage framework that learns adaptive and reusable temporal representations for time series forecasting. |
Hanbin Xiao; Xun Zhou; Rui Huang; Xiucheng Li; Weili Guan; Liqiang Nie; |
| 120 | CSSG: A Continuous Spatio-temporal Graph Learning Framework with Scalable Spatial Granularity Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we propose a Continuous spatio-temporal graph learning framework with Scalable Spatial Granularity (CSSG). |
Kaiwen Xia; Li Lin; Qi Zhang; Xinrui Zhang; Shuai Wang; Xuming Hu; Philip S. Yu; |
| 121 | Align-for-Fusion: Harmonizing Triple Preferences Via Dual-oriented Diffusion for Cross-domain Sequential Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Inspired by the advancements of diffusion models (DMs) in distribution matching, we propose an align-for-fusion framework for CDSR to Harmonize triple preferences utilizing Dual-oriented DMs (HorizonRec). |
Yongfu Zha; Xinxin Dong; Haokai Ma; Yonghui Yang; Xiaodong Wang; |
| 122 | Single-Cell Spatial Proteomics Clustering By Decoupling Spatiality and Expression Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: ii) Cellular identity is influenced by both intrinsic protein expression and the external spatial microenvironment; however, the heterogeneity and potential conflicts between these two information sources make it difficult to effectively identify subtle yet biologically significant cellular states. To overcome these issues, we propose a deep clustering framework named spClust. |
Benyu Wu; Shan Zhang; Yuequn Wang; Liangrui Ren; Wei Du; Jun Wang; Carlotta Domeniconi; Guoxian Yu; |
| 123 | FuXi-Linear: Unleashing The Power of Linear Attention in Long-term Time-aware Sequential Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While linear attention is a promising alternative, existing research faces three critical challenges: (1) temporal signals are often overlooked or integrated via naive coupling that causes mutual interference between temporal and semantic signals while neglecting behavioral periodicity; (2) insufficient positional information provided by existing linear frameworks; and (3) a primary focus on short sequences and shallow architectures. To address these issues, we propose FuXi-Linear, a linear-complexity model designed for efficient long-sequence recommendation. |
Yufei Ye; Wei Guo; Hao Wang; Luankang Zhang; Heng Chang; Hong Zhu; Yuyang Ye; Yong Liu; Defu Lian; Enhong Chen; |
| 124 | NumCache: KV Cache Compression and Retrieval for Financial Document QA Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Cache-Augmented Generation (CAG) projects attention states into compact KV representations and treats precomputed caches as reusable internal memory, but typically assumes caches are already well-formed and query-relevant, leaving open how to build and select number-faithful caches. To address this gap, we propose NumCache, which compresses SEC filings into KV caches initialized from numerically dense regions and trained directly on financial QAs. |
Eftychia Makri; Peiwen Li; Yidong Jiang; Junrong Chen; Jialin Chen; Ali Maatouk; Leandros Tassiulas; Eliot Brenner; Bing Xiang; Rex Ying; |
| 125 | Fin-RATE: A Real-world Financial Analytics and Tracking Evaluation Benchmark for LLMs on SEC Filings Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Furthermore, these benchmarks do not disentangle whether errors arise from retrieval failures, generation inaccuracies, domain-specific reasoning mistakes, or misinterpretation of the query or context, making it difficult to precisely diagnose performance bottlenecks. To bridge these gaps, we introduce Fin-RATE, a benchmark built on U.S. Securities and Exchange Commission (SEC) filings and mirroring financial analyst workflows through three pathways: detail-oriented reasoning within individual disclosures, cross-entity comparison under shared topics, and longitudinal tracking of the same firm across reporting periods. |
Yidong Jiang; Junrong Chen; Eftychia Makri; Jialin Chen; Peiwen Li; Ali Maatouk; Leandros Tassiulas; Eliot Brenner; Bing Xiang; Rex Ying; |
| 126 | MapAgent: An Industrial-Grade Agentic Framework for City-scale Lane-level Map Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose MapAgent, an industrial-grade agentic architecture that augments a vectorization backbone for specification-compliant lane-map production. |
Deguo Xia; Zihan Li; Haochen Zhao; Dong Xie; Yuyao Kong; Xiyan Liu; Jizhou Huang; Mengmeng Yang; Diange Yang; |
| 127 | The Hidden Fragility of GNNs: How Graph Structure Amplifies Numerical Errors Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Consequently, we propose Aggregation-Aware Representation Learning (AARL) to learn numerically stable and cancellation-resistant representations without sacrificing expressiveness. |
Jiawei Gu; Ziyue Qiao; |
| 128 | Permissive-Washing in The Open AI Supply Chain: A Large-Scale Audit of License Integrity Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We find that an astonishing 96.9\% of datasets and 96.4\% of models lack the required license text, only 2.1\% of datasets and 2.6\% of models satisfy both license text and copyright requirements, and even when upstream artifacts provide complete licensing evidence, attribution rarely propagates downstream: only 25.0\% of models preserve compliant dataset notices and only 5.4\% of applications preserve compliant model notices (with just 5.9\% preserving any linked upstream notice). |
James Jewitt; Gopi Krishnan Rajbahadur; Hao Li; Bram Adams; Ahmed E. Hassan; |
| 129 | Explicit Retrieval, Implicit Cognition: Towards Personalized Micro-video Popularity Prediction Via Dual Latent Memory Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Inspired by human memory theory, we propose CLAMP, a cognition-memory-aligned framework that synergizes a large multimodal model (LMM) with dual latent memory, comprising a short-term module for content-centric perceptual retention and a long-term module for user-centric semantic consolidation. |
Zhangtao Cheng; Bo Chen; Meihui Zhong; Ting Zhong; Bing Xia; Fan Zhou; |
| 130 | CA-DEL: An Open Multi-Target, Multi-Modal Benchmark for Learning from DNA-Encoded Library Screens Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: DNA-Encoded Library (DEL) technology can generate large-scale screening data, but its primary signal – high-throughput sequencing read counts – is an indirect and noisy proxy for molecular binding affinity. To support rigorous model development under this noisy supervision setting, we introduce CA-DEL, an open, multi-target, multi-modal benchmark focused on the homologous subtype selectivity challenge within the Carbonic Anhydrase (CA) family. |
Mutian He; Hanqun Cao; Cheng Tan; Zijun Gao; Xiaojun Yao; Chunbin Gu; Pheng-Ann Heng; |
| 131 | How Much Reasoning Do Retrieval-Augmented Models Add Beyond LLMs? A Benchmarking Framework for Multi-Hop Inference Over Hybrid Knowledge Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce HybridRAG-Bench, a contamination-aware benchmark construction framework to evaluate retrieval-intensive, multi-hop reasoning over hybrid knowledge. |
Junhong Lin; Bing Zhang; Song Wang; Ziyan Liu; Dan Gutfreund; Julian Shun; Yada Zhu; |
| 132 | MigrationBench: Repository-Level Code Migration Benchmark from Java 8 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In contrast, we introduce a new coding benchmark MigrationBench with a distinct focus: code migration. |
Linbo Liu; Xinle Liu; Qiang Zhou; Lin Chen; Yihan Liu; Hoan Nguyen; Behrooz Omidvar Tehrani; Xi Shen; Jun Huan; Omer Tripp; Anoop Deoras; |
| 133 | From Shallow Humor to Metaphor: Towards Label-Free Harmful Meme Detection Via LMM Agent Self-Improvement Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To address these challenges, we present ALARM, the first lAbeL-free hARmful Meme detection framework powered by Large Multimodal Model (LMM) agent self-improvement. |
Jian Lang; Rongpei Hong; Ting Zhong; Leiting Chen; Qiang Gao; Fan Zhou; |
| 134 | Nip Rumors in The Bud: Retrieval-Guided Topic-Level Adaptation for Test-Time Fake News Video Detection Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To bridge this gap, we introduce RADAR, the first framework that enables test-time adaptation to unseen news videos. |
Jian Lang; Rongpei Hong; Ting Zhong; Yong Wang; Fan Zhou; |
| 135 | Neural Predictive Control to Coordinate Discrete- and Continuous-Time Models for Time-Series Analysis with Control-Theoretical Improvements Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we recast time-series problems as the continuous ODE-based optimal control problem. |
Haoran Li; Muhao Guo; Yang Weng; Hanghang Tong; |
| 136 | Exploring Recommender System Evaluation: A Multi-Modal LLM Agent Framework for A/B Testing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Nonetheless, current agents fail to simulate the perception process and interaction patterns, due to the lack of real environments and visual perception capability. To address these challenges, we introduce a multi-modal user agent for A/B testing (A/B Agent). |
Wenlin Zhang; Xiangyang Li; Qiyuan Ge; Kuicai Dong; Pengyue Jia; Xiaopeng Li; Zijian Zhang; Maolin Wang; Yichao Wang; Huifeng Guo; Ruiming Tang; Xiangyu Zhao; |
| 137 | From Agnostic to Specific: Latent Preference Diffusion for Multi-Behavior Sequential Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Meanwhile, due to the asymmetric deterministic between items and behaviors, discriminative paradigm based on preference scoring is unsuitable to capture the uncertainty from low-entropy behaviors to high-entropy items, failing to provide efficient and diverse recommendation. To address these challenges, we propose FatsMB, a framework based diffusion model that guides preference generation From Behavior-Agnostic To Behavior-Specific in latent spaces, enabling diverse and accurate Multi-Behavior Sequential Recommendation. |
Ruochen Yang; Xiaodong Li; Jiawei Sheng; Jiangxia Cao; Xinkui Lin; Shen Wang; Shuang Yang; Zhaojie Liu; Tingwen Liu; |
| 138 | Test-Time Deep Thinking to Explore Implicit Rules Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This causes agents to fall into repetitive trial-and-error loops, ultimately leading to task failure. To address this challenge, we propose Test-Time Exploration (TTExplore), a framework where a thinker component analyzes interaction history to infer these implicit rules and guide an actor. |
Wentong Chen; Xin Cong; Zhong Zhang; Yaxi Lu; Siyuan Zhao; Yesai Wu; Qinyu Luo; Haotian Chen; Yankai Lin; Zhiyuan Liu; Maosong Sun; |
| 139 | EHRBench: An Automated and Reliable EHR-based Benchmark for Clinical Decision Making with LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To fill the gaps, we introduce EHRBench, an automated and reliable EHR-grounded benchmark for evaluating LLM-based clinical decision-making at scale. |
Yuzhang Xie; Keqi Han; Yunpeng Xiao; Hejie Cui; Guanchen Wu; Ziyang Zhang; Kai Shu; Jiaying Lu; Xiao Hu; Carl Yang; |
| 140 | HyFunc: Accelerating LLM-based Function Calls for Agentic AI Through Hybrid-Model Cascade and Dynamic Templating Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper identifies and addresses three key redundancies: (1) the redundant processing of a large library of function descriptions for every request; (2) the redundant use of a large, slow model to generate an entire, often predictable, token sequence; and (3) the redundant generation of fixed, boilerplate parameter syntax. We introduce HyFunc, a novel framework that systematically eliminates these inefficiencies. |
Weibin Liao; Jian-Guang Lou; Haoyi Xiong; |
| 141 | Natural Language-Powered Functional Protein Sequence and Structure Co-Design with Multi-Modal Knowledge Fusion Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, they face two major challenges in limited integration of diverse biological knowledge and insufficient understanding of ‘sequence-structure-function’ relations, hindering the discovery of functional and diverse proteins in de novo design. To address these challenges, we propose a Protein sequence–structure–function Consistency Design model empowered by Natural Language function description, dubbed ProtcdNl, which expands the protein design space and ensures alignment with function-aware framework. |
Ming Yang; Xin Zheng; Yi Li; Yizhen Zheng; Huan Yee Koh; Yanqing Guo; Jian Gao; Feng Xia; Shirui Pan; |
| 142 | Are Rationales Necessary and Sufficient? Tuning LLMs for Explainable Misinformation Detection Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose a pipeline to fine-tune a dedicated LLM specifically for explainable MD. |
Bing Wang; Rui Miao; Ximing Li; Chen Shen; Shaotian Yan; Changchun Li; Kaiyuan Liu; Xiaosong Yuan; Jieping Ye; |
| 143 | Riemannian Geometry Speaks Louder Than Words: From Graph Foundation Model to Next-Generation Graph Intelligence Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we argue that, for graphs, Riemannian geometry speaks louder than words, laying out the foundational principles for GFM. |
Philip S. Yu; Li Sun; |
| 144 | Local Clustering on Complex Graphs and Complex Hypergraphs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While most existing studies on graph clustering assume a discrete graph setting (i.e., unweighted, undirected graphs without self-loops), real-world graphs can be more complex. In this paper, we extend the classic non-approximating Andersen-Chung-Lang (ACL) clustering algorithm beyond discrete graphs and generalize its quadratic optimality to a wider range of complex graphs, including weighted, directed, and self-looped graphs and hypergraphs with edge-dependent vertex weights. |
Zihao Li; Dongqi Fu; Hengyu Liu; Jingrui He; |
| 145 | AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing process-level benchmarks are predominantly confined to closed-world mathematical domains, failing to capture the dynamic and open-ended nature of tool execution. To bridge this gap, we introduce AgentProcessBench, the first benchmark dedicated to evaluating step-level effectiveness in realistic, tool-augmented trajectories. |
Shengda Fan; Xuyan Ye; Yupeng Huo; Zhi-Yuan Chen; Yiju Guo; Shenzhi Yang; Wenkai Yang; Shuqi Ye; Jingwen Chen; Haotian Chen; Xin Cong; Yankai Lin; |
| 146 | PowerGrow: Feasible Co-Growth of Structures and Dynamics for Power Grid Synthesis Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present PowerGrow, a co-generative framework that significantly reduces computational overhead while maintaining operational validity. |
Xinyu He; Chenhan Xiao; Haoran Li; Ruizhong Qiu; Zhe Xu; Yang Weng; Jingrui He; Hanghang Tong; |
| 147 | PinRec: Unified Generative Retrieval Model for Pinterest Recommender Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To our knowledge, this paper presents the first rigorous study of a unified generative retrieval model built and deployed at Pinterest scale, marking a significant milestone in the field. |
Edoardo Botta; Jaewon Yang; Yi-Ping Hsu; Laksh Bhasin; Yilin Chen; Prabhat Agarwal; Anirudhan Badrinath; Jiajing Xu; Charles Rosenberg; |
| 148 | Designing A Scalable LLM Agent Framework for Large-scale Urban Segregation Simulation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, urban dynamics often require extensive agent interactions to emerge, and scaling up LLM agent simulations is limited by high-latency remote LLM inference and high costs. To address this, we propose the OpenCity framework for large-scale LLM agent simulation. |
Qingbin Zeng; Yuwei Yan; Zhiheng Zheng; Jingzhe Yuan; Jun Zhang; Jie Feng; Fengli Xu; James Evans; Yong Li; |
| 149 | DeepTravel: An End-to-End Agentic Reinforcement Learning Framework for Autonomous Travel Planning Agents Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper proposes DeepTravel, an end-to-end agentic reinforcement learning framework for building an autonomous travel planning agent, capable of autonomously planning, executing tools, and reflecting on tool responses to explore, verify, and refine intermediate actions in multi-step reasoning. |
Yansong Ning; Rui Liu; Jun Wang; Kai Chen; Wei Li; Jun Fang; Kan Zheng; Naiqiang Tan; Hao Liu; |
| 150 | KBest: Efficient Vector Search on Kunpeng CPU Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present KBest as a vector search library tailored for the latest Kunpeng 920 CPUs. |
Kaihao Ma; Meiling Wang; Senkevich Oleg; Zijian Li; Daihao Xue; Dmitriy Malyshev; Yangming Lv; Shihai Xiao; Xiao Yan; Radionov Alexander; Weidi Zeng; Yuanzhan Gao; Zhiyu Zou; Xin Yao; Lin Liu; Junhao Wu; Yiding Liu; Yaoyao Fu; Gongyi Wang; Gong Zhang; Fei Yi; Yingfan Liu; |
| 151 | Let’s Verify Math Questions Step By Step Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this work, we present ValiMath, a benchmark consisting of 2147 human-verified mathematical questions covering a wide range of domains such as arithmetic, algebra, and geometry, which are synthesized and curated from the NuminaMath dataset. |
Chengyu Shen; Zhen Hao Wong; Runming He; Hao Liang; Meiyi Qiang; Zimo Meng; Zhengyang Zhao; Bohan Zeng; Zhengzhou Zhu; Bin Cui; Wentao Zhang; |
| 152 | Toward A Science of AI Agent Societies Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To formalize this perspective, we propose four core properties that a valid AI agent society should satisfy: individualized objectives, rules and governance, autonomy, and scale and complexity. |
Geon Lee; Fanchen Bu; Soo Yong Lee; Sunwoo Kim; Kijung Shin; |
| 153 | Retain to Refine: Adaptive Online Question Answering Via Query Routing and Long-Short Memory Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: These include: (1) handling both simple and complex queries with appropriate levels of reasoning, (2) minimizing latency without compromising answer quality, and (3) maintaining answer consistency under evolving and noisy retrieval contexts. To address these challenges, we propose Retain-to-Refine (ℜ2ℜ), an adaptive agent-based QA framework designed for practical deployment. |
Yuchen Li; Jiamin Chen; Xinran Chen; Zhiyu Li; Haojie Zhang; Rui Kong; Jiayi Li; Xinyu Ma; Hengyi Cai; Lixin Su; Shuaiqiang Wang; Jiashu Zhao; Yongqi Zhang; Haoyi Xiong; Linghe Kong; Lei Chen; Dawei Yin; |
| 154 | Differential-Aware Synergy of Quantity and Topology for Hyper-Relational Knowledge Graphs with Numeric Entities Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this predicament, standard attention mechanisms—limited by the inherent nature of positive-only accumulation (i.e., non-negative weights)-fail to peel away quantitative noise, forcing models into a compromised balance. To address these challenges, we propose NumDAE—a novel differential-aware decouple-then-synergize embedding framework for HNKGs. |
Ming Yin; Neng Gao; |
| 155 | FedPRE: Robust Federated Graph Learning Against Topological Corruption Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing methods with poor robustness are inevitably constrained due to the absence of targeted strategies for addressing the issues of global contaminated collaboration and local vulnerability. To tackle this challenge, we conduct the first comprehensive investigation of robust FGL against topological corruption and propose FedPRE. |
Zihan Tan; Guancheng Wan; Wenke Huang; Bin Yang; Mang Ye; |
| 156 | Bradley-Terry Rankings for Recommender Systems Across Dataset Taxonomies Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Naive aggregation of performance metrics (e.g., averaging NDCG over benchmarks) can yield misleading rankings, undermining practical selection. To address this problem, we introduce a novel, data-driven ranking methodology based on Bradley-Terry (BT) model. |
Ekaterina Grishina; Stepan Kuznetsov; Askar Tsyganov; Ilya Ivanov; Daria Korovaitceva; Margarita Rusanova; Uliana Parkina; Alexander Derevyagin; Evgeny Frolov; Sergey Samsonov; Anton Lysenko; |
| 157 | Mixture-of-Experts Knowledge Graph Retrieval-Augmented Generation for Multi-Agent LLM-based Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Moreover, the selection of retrieval granularity lacks direct supervision and must be inferred from the final recommendation after alignment and downstream utilization, making query-aware retrieval hard to learn end-to-end. To address these issues, we propose MixRAGRec, a cooperative multi-agent framework for KG-RAG recommendations. |
Shijie Wang; Chengyi Liu; Yujuan Ding; Shanru Lin; See-Kiong Ng; Xu Xin; Wenqi Fan; |
| 158 | DuET: Dual-View Tensor-to-Topology Spectral Adapter for Enhancing Sparse Tensor Factorization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose DuET, a model-agnostic refinement framework that stabilizes TF embeddings by separating structural denoising from tensor factorization. |
Jun-Gi Jang; Jingrui He; Andrew J. Margenot; Hanghang Tong; |
| 159 | GPR: Towards A Generative Pre-trained One-Model Paradigm for Large-Scale Advertising Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Conversely, emerging generative models often struggle with the strict latency and revenue alignment requirements of industrial applications. To address these issues, we propose GPR (Generative Pre-trained Recommender). |
Jie Jiang; Jun Zhang; Yi Li; Yue Liu; Changping Wang; Yuan Wang; Yuling Xiong; Xun Liu; Haiyang Wu; Qian Li; Enming Zhang; Jiawei Sun; Xin Xu; Zishuai Zhang; Ruoran Liu; Suyuan Huang; Zhaoxin Zhang; Zhengkai Guo; Shuojin Yang; Meng-Hao Guo; Huan Yu; Shi-Min Hu; |
| 160 | Bridging Front-Door Adjustment and Information Bottleneck for Identifiable Causal Representations Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: The classic front-door adjustment provides theoretical criteria for identifying such causal mediators, but it relies on known or preset mediator variables and is difficult to learn directly from data. Therefore, this paper proposes FDA-IB, a unified framework that embeds the causal identification conditions of the front-door adjustment into the IB optimization process. |
Jue Li; Yuhua Qian; Jieting Wang; Saixiong Liu; Honghong Cheng; |
| 161 | Investigating Reasoning in Large Language Models with Counterfactual Knowledge Graphs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a novel diagnostic benchmark to decouple knowledge memorization from logical reasoning. |
Fangfei Yan; Jianbo Yao; Michael K. Chen; Yizhou Sun; Qixin Zhang; Xikun Zhang; Renqiang Luo; Dacheng Tao; |
| 162 | Geometry-aware Test-Time Adaptation on Graphs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we explore Riemannian geometry as a principled foundation to mitigate the geometric distortion issue in test-time adaptation on graphs. |
Lingwei Wei; Dou Hu; Li Sun; Chengze Li; Wei Zhou; Songlin Hu; Philip S. Yu; |
| 163 | Disentangling Multi-View Scanning in Mamba for Network Traffic Anomaly Detection Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Specifically, distinct scanning branches capture substantial view-invariant information, which is repeatedly amplified during multi-view fusion; conversely, view-specific information is diluted or even suppressed, leading to representation homogenization and multi-view degradation. To address this problem, we propose DisenMamba, a novel disentangled multi-view Mamba framework. |
Xinglin Lian; Chengtai Cao; Ting Zhong; Fan Zhou; |
| 164 | One Model, Multiple Goals: Adaptive Multi-Objective Learning for E-commerce Dialogue Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose MORE, an adaptive Multi-Objective REinforcement learning framework that jointly optimizes reasoning accuracy and linguistic naturalness. |
Mingzhe Li; Jing Xiang; Enguo Zhou; Lang Gao; Tai Li; Qishen Zhang; Xiangliang Zhang; Xiuying Chen; |
| 165 | Rethinking Federated Unlearning Via The Lens of Memorization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we revisit federated unlearning through the lens of memorization. |
Jiaheng Wei; Yanjun Zhang; He Zhang; Leo Yu Zhang; Chao Chen; Kok-Leong Ong; Jun Zhang; Yang Xiang; |
| 166 | Can LLM-based Financial Investing Strategies Outperform The Market in Long Run? Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We critically assess their generalizability and robustness by proposing FINSABER, a backtesting framework evaluating timing-based strategies across longer periods and a larger universe of symbols. |
Weixian Waylon Li; Hyeonjun Kim; Mihai Cucuringu; Tiejun Ma; |
| 167 | HiParse: A Hierarchical Framework for Optimizing Web Content Extraction to Enhance LLM Pre-training Data Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: As a result, existing solutions deployed at scale often lead to significant data quality degradation and corpus loss. To address this challenge, which we faced directly at Ant Group, this paper introduces HiParse, a hierarchical adaptive web parsing framework deployed in production. |
Yuzhuo Fu; Zhuyan Zhou; Chao Huang; Jiayi Wang; Binwei Zeng; Dongke Hu; XiangChun Wang; Wang Hong; Jin Fan; |
| 168 | DEGR: Dual Exploration-Driven Generative Re-Ranking for Adaptive Cross-Request Context Bridging Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To overcome this, re-ranking can actively balance immediate and exploratory value, for instance, by prioritizing exploratory exposure under low-quality supply to preserve browsing potential and facilitate serendipitous conversions. Therefore, we propose a Dual Exploration-Driven Generative Re-Ranking (DEGR) method. |
Binglei Zhao; Xuanhua Yang; Xiwei Zhao; Sulong Xu; |
| 169 | Graph Diffusion History Reconstruction Via Feasibility-Aware Markov Chain Monte Carlo Estimation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Diffusion history reconstruction is challenging due to explosive search space, complex combinatorial constraints, and scarcity of training data. To address these challenges, we propose a new method called HERMES. |
Yijing Zuo; Ruizhong Qiu; Lingjie Chen; Hanghang Tong; |
| 170 | Ready to Sim? Inverse Parametric Building Modeling Via Universal Anchor Representation for Urban Simulation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose Universal Anchor Representation (UAR), a normalized hierarchical parameterization that constrains inference to bounded coordinates (t,s) in [0,1]2 while guaranteeing structural connectivity by construction. |
Jaeyeon Kim; Po-Yen Lai; Jian Cheng Wong; Chin Chun Ooi; Yew-Soon Ong; Ivor Tsang; |
| 171 | Each Rank Could Be An Expert: Single-Ranked Mixture of Experts LoRA for Multi-task Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While effective, these methods often isolate knowledge within individual tasks, failing to fully exploit the shared knowledge across related tasks. In this paper, we establish a connection between single LoRA and multi-LoRA MoE, integrating them into a unified framework. |
Ziyu Zhao; Yixiao Zhou; Xin Yu; Zhi Zhang; Didi Zhu; Tao Shen; Zexi Li; Jinluan Yang; Xuwu Wang; Jing Su; Kun Kuang; Zhongyu Wei; Fei Wu; Yu Cheng; |
| 172 | SafeImpute: Reliable Clinical Data Imputation Via Conformal Selection Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we study reliable clinical imputation, aiming to produce accurate imputations while selectively releasing the reliable results, with statistical control over clinically unacceptable errors. To achieve this goal, we propose SafeImpute, a reliable imputation framework for irregular and sparse clinical longitudinal records. |
Xinrui He; Mengting Ai; Junting Wang; Curtiss B. Cook; Jingrui He; |
| 173 | Generative Auto-Bidding in Large-Scale Auctions Via Diffusion Completer-Aligner Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To address it, we propose a Causal auto-Bidding method based on a Diffusion completer-aligner framework, termed CBD. |
Yewen Li; Jingtong Gao; Peng Jiang; Ruyi An; Xiangyu Zhao; Bo An; Fei Pan; Qingpeng Cai; Peng Jiang; Kun Gai; |
| 174 | In A Streaming World, Should You Stand Still- A Comprehensive Benchmark of Anomaly Detection in Streams Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we carry out the first large-scale experimental study comparing streaming and static TSAD methods under a unified streaming evaluation benchmark. |
Magali Parrino; Antoine Ajenjo; Emmanuel Remy; Pierre Stephan; Pierre Senellart; Paul Boniol; |
| 175 | Text-Guided Visual Representation Learning for Robust Multimodal E-Commerce Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose Text-Guided Q-Former (TGQ-Former), a text-guided visual representation learning framework that leverages structured metadata as semantic guidance for visual token extraction while preserving complementary visual evidence. |
Yufei Guo; Jing Ma; Yixuan Dong; Tianlu Zhang; Shijie Yang; Yanlong Zang; Weijie Ding; Pinghua Gong; Jungong Han; |
| 176 | Certified Defense on The Fairness of Graph Neural Networks Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we take crucial steps to study a novel problem of certifiable defense on the fairness level of GNNs. |
Yushun Dong; Binchi Zhang; Hanghang Tong; Jundong Li; |
| 177 | Beyond Static Priors: Dynamic Neural Guidance for Large-Scale Ant Colony Optimization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present DyNACO, a novel framework that achieves dynamic neural guidance by periodically observing the pheromone distribution and the incumbent solution. |
Dat Thanh Tran; Van Khu Vu; Yining Ma; |
| 178 | TemporalBench: A Benchmark for Evaluating LLM-Based Agents on Contextual and Event-Informed Time Series Tasks Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce TemporalBench, a multi-domain benchmark designed to evaluate temporal reasoning behavior under progressively richer informational settings. |
Muyan Weng; Defu Cao; Wei Yang; Yashaswi Sharma; Yan Liu; |
| 179 | HDMoE: A Hierarchical Decoupling-Fusion Mixture-of-Experts Framework for Multimodal Cancer Survival Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, these methods have the following shortcomings: (1) fail to reduce the redundant information of modality features before decoupling, which negatively affects the feature decoupling and fusion effect; (2) lack the ability to model the fine-grained relationships of the features and capture the local information interactions between intra- and inter-modality features. To address these issues, we propose a Hierarchical Decoupling-Fusion Mixture-of-Experts (HDMoE) framework with two levels of MoE and Random Feature Reorganization (RFR) modules. |
Huayi Wang; Haochao Ying; Yuyang Xu; Qiyao Zheng; Jun Wang; Cheng Zhang; Ying Sun; Jian Wu; |
| 180 | LitBench: A Graph-Centric Large Language Model Benchmarking Tool For Literature Tasks Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To that end, we introduce LitBench, a benchmarking tool designed to enable the development and evaluation of domain-specific LLMs tailored to literature-related tasks. |
Andreas Varvarigos; Ali Maatouk; Jiasheng Zhang; Ngoc Bui; Jialin Chen; Leandros Tassiulas; Rex Ying; |
| 181 | Self-Enhanced Density Clustering for High Dimension and Low Sample Size Data Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This creates a dilemma: spectral methods fail as distance metrics degrade, while deep clustering tends to over-fit scarce data. To break this dilemma, a Self-Enhanced Density Clustering (SEDC) framework that integrates the cluster structure discovery and embedding representation learning into an iterative enhancement process is proposed in this paper. |
Bingbing Jiang; Zhongli Wang; Jie Yang; Guang-Kui Xu; Wei Chen; Chenglong Zhang; Xinyan Liang; Peng Zhou; Weiguo Sheng; Weiping Ding; |
| 182 | RARE: Retrieval-Augmented Reasoning Modeling Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: For the efficient discovery and modeling of reasoning patterns, we propose Retrieval-Augmented Reasoning Modeling (RARE), a novel paradigm to extract and model reasoning patterns from data, represented as salient and learnable tokens. |
Zhengren Wang; Jiayang Yu; Dongsheng Ma; Zhe Chen; Yu Wang; Zhiyu Li; Feiyu Xiong; Yanfeng Wang; Weinan E; Linpeng Tang; Wentao Zhang; |
| 183 | Passing The Turing Test on Screen: A Benchmark for Mobile GUI Agent Humanization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce the ”Turing Test on Screen,” formally modeling the interaction as a MinMax optimization problem between a detector and an agent aiming to minimize behavioral divergence. |
Jiachen Zhu; Lingyu Yang; Rong Shan; Congmin Zheng; Zeyu Zheng; Weiwen Liu; Yong Yu; Weinan Zhang; Jianghao Lin; |
| 184 | LingxiDiagBench: A Multi-Agent Framework for Benchmarking LLMs in Chinese Psychiatric Consultation and Diagnosis Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present LingxiDiagBench, a large-scale multi-agent benchmark that evaluates LLMs on both static diagnostic inference and dynamic multi-turn psychiatric consultation in Chinese. |
Shihao Xu; Tiancheng Zhou; Jiatong Ma; Ming Xiao; Yanli Ding; Yiming Yan; Haiyang Geng; Guoyi Li; Yunyun Han; Jianhua Chen; Yafeng Deng; |
| 185 | Ocean-E2E: Hybrid Physics-Based and Data-Driven Global Forecasting of Marine Heatwaves with End-to-End Neural Assimilation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing methods still have certain limitations in forecasting general patterns and extreme events. In this study, to address these issues, based on the physical nature of MHWs, we created a novel hybrid data-driven and numerical MHWs forecast framework Ocean-E2E, which is capable of 40-day accurate MHW forecasting with end-to-end data assimilation. |
Ruiqi Shu; Ruijian Gou; Yanfei Xiang; Xiaomeng Huang; |
| 186 | Expanding Knowledge Boundaries Via LLM-Grounded Alignment for Drug Combination Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing methods rely primarily on observed drug–cell responses and learn representations within a limited experimental knowledge regime, resulting in poor generalization in cold-start and long-tail settings. To address this limitation, we propose L2aCo, a model-agnostic knowledge alignment framework that leverages large language models as external biomedical knowledge sources to expand the effective knowledge boundary for drug combinations. |
Tengfei Ma; Yuqin He; Zhonghao Ren; Bosheng Song; Qian Li; Xiangxiang Zeng; |
| 187 | ClinicalAgents: Multi-Agent Orchestration for Clinical Decision Making with Dual-Memory Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing methods typically rely on static, linear mappings from symptoms to diagnoses, failing to capture the iterative, hypothesis-driven reasoning inherent in human clinicians. To bridge this gap, we introduce ClinicalAgents, a novel multi-agent framework designed to simulate the cognitive workflow of expert clinicians. |
Zhuohan Ge; Haoyang Li; Yubo Wang; Nicole Hu; Chen Jason Zhang; Qing Li; |
| 188 | Rethinking Weak Supervision in Anomaly Detection: A Comprehensive Benchmark Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper introduces WSADBench, the first benchmark that unifies evaluation across distinct weakly supervised scenarios, benchmarking diverse approaches from specialized WSAD methods to advanced tabular foundation models. |
Xu Yao; Siyuan Zhou; Zhenbo Wu; Chaochuan Hou; Shuang Liang; Shiping Wang; Hailiang Huang; Songqiao Han; Minqi Jiang; |
| 189 | Towards Robust EEG Decoding Based on Riemannian Self-Attention Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In contrast, the Bures-Wasserstein Metric (BWM) exhibits linear dependence on SPD matrices and demonstrates superior performance for ill conditioning. To overcome these challenges, we propose a Riemannian self-attention network based on the BWM. |
Shaocheng Jin; Tao Zhou; Rui Wang; Ziheng Chen; Xiaoqing Luo; Xiao-Jun Wu; Josef Kittler; |
| 190 | MLaGA: Multimodal Large Language and Graph Assistant Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Effectively modeling MMGs presents two key challenges: (i) capturing fine-grained cross-modal interactions—e.g., between visual patches and word tokens—while preserving structural dependencies, and (ii) achieving unified generalization across diverse tasks and domains within a single model. To address these challenges, we propose MLaGA, a novel Multimodal Large Language and Graph Assistant that serves as the LLM-based foundation model for multimodal graphs. |
Dongzhe Fan; Jiajin Liu; Yi Fang; Djellel Difallah; Qiaoyu Tan; |
| 191 | Breaking Bad Molecules: Are MLLMs Ready for Structure-Level Molecular Detoxification? Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In parallel, we propose an automated evaluation framework, ToxiEval, which integrates toxicity endpoint prediction, synthetic accessibility, drug-likeness, and structural similarity into a high-throughput evaluation chain for repair success. |
Fei Lin; Ziyang Gong; Cong Wang; Tengchao Zhang; Yonglin Tian; Yining Jiang; Ji Dai; Chao Guo; Xiaotong Yu; Xue Yang; Gen Luo; Fei-Yue Wang; |
| 192 | Efficient Approximation Algorithms for Adaptive Minimum Cost Seed Selection Via MRR-set Updates Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we propose the EMASS framework which achieves an approximation ratio of (ln η+1)2/[(1-1/e)2-ε], where ε is the estimation error of mRR-sets. |
Chen Feng; Gongyao Guo; Yiran Li; Jieming Shi; Sibo Wang; |
| 193 | DynaTree: Dynamic Agentic Retrieval Tree for Time-Sensitive News Retrieval Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose DynaTree (Dynamic Agentic Retrieval Tree), a two-stage framework in which agentic RAG is used for offline semantic exploration, while online retrieval is performed without agentic inference. |
Siyuan Qi; Xinyuan Wang; Yingxuan Yang; Haochuan Guo; Jianghao Lin; Weiwen Liu; Yong Yu; Weinan Zhang; |
| 194 | FDABench: A Benchmark for Data Agents on Analytical Queries Over Heterogeneous Data Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our contributions are threefold: (1) A comprehensive benchmark of 2,007 tasks spanning six data modalities with a unified, multi-granularity evaluation framework. |
Ziting Wang; Shize Zhang; Haitao Yuan; Jinwei Zhu; Wei Dong; Gao Cong; |
| 195 | PRIME: A Pretrained Representation-Induced Model for 3D Molecules in De Novo Binder Design Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In current generative models, the effective search space for structurally feasible binders is severely constrained, as the complexity of biochemical interactions is not explicitly encoded into a semantically grounded representation of viable molecular manifolds. To address this challenge, we propose Pretrained Representation Induced Molecular gEneration (PRIME), a unified generative framework for three-dimensional binder design across peptides and antibodies. |
Zhihua Tian; Jiale Zhou; Rubo Wang; Yidong Song; Zhenchao Tang; Tianxu Lv; Zhijian Wu; Yefeng Zheng; |
| 196 | HiLLM-CD: LLM-Enhanced Hierarchical Cognitive Diagnosis Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose LLM-Enhanced Hierarchical Cognitive Diagnosis (HiLLM-CD), a tree-structured encoder-decoder framework that uses the concept tree as an interpretable proficiency representation. |
Yuquan Xie; Wanqi Yang; Bo Zhang; Zekun Li; Lei Wang; Ming Yang; Yang Gao; |
| 197 | Sci-PRM: A Tool Aware Process Reward Model for Scientific Reasoning Verification Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we first construct SCIPRM70K, a large-scale dataset featuring ”Chain-of-Tool” trajectories that explicitly interleave reasoning with the execution of scientific tools. Building upon this, we train an efficient reward model called Sci-PRM to provide fine-grained supervision on tool selection, execution accuracy, and result interpretation at each step in one inference. |
Xiangyu Zhao; Henry Hengyuan Zhao; Yiheng Wang; Wanghan Xu; Yuhao Zhou; Qinglong Cao; Zhiwang Zhou; Lei Bai; Wenlong Zhang; Xiao-Ming Wu; |
| 198 | Privacy-Aware Decoding: Mitigating Privacy Leakage of Large Language Models in Retrieval-Augmented Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose Privacy-Aware Decoding (PAD), a lightweight, inference-time defense that adaptively injects calibrated Gaussian noise into token logits during generation. |
Haoran Wang; Xiongxiao Xu; Baixiang Huang; Kai Shu; |
| 199 | ReLU: Refined Chunk Embeddings Learning for Ultra-long SNP Genomic Prediction in Crop Breeding Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: A straightforward solution is to chunk SNP sequences and pool the embeddings, but pooled chunk embeddings often lose local SNP information within the sample and hinder modeling global dependencies across samples. To address this, we present ReLU, Refined Chunk Embeddings Learning for Ultra-long SNP modeling, a scalable framework that refines chunk embeddings progressively for genomic prediction in crop breeding. |
Huachi Zhou; Jiahe Du; Yujing Zhang; Luyao Zhuang; Chang Yang; Zijin Hong; Jiaqi Bai; Qinggang Zhang; Kaixiong Zhou; Xiao Huang; |
| 200 | Net-Ev2: A Generative Simulator for Network Event Evolution Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Reducing real-world trial and error has long been a central goal of decision making, and generative simulators advance this goal by modeling the evolution of future states. |
Guangyu Wang; Zhaonan Wang; |
| 201 | Low-Rank Prior-Induced Consistency Flow Matching for Efficient Traffic Imputation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Furthermore, learning the transformation from non-informative priors introduces redundant computational overhead. To address these issues, we propose Low-Rank Prior-Induced Consistency Flow Matching (LOFT) for efficient and effective distribution modeling under highly sparse data. |
Xiaowei Mao; Tingrui Wu; Yawen Yang; Shengnan Guo; Yan Lin; Shilong Zhao; Haochen Lv; Youfang Lin; Huaiyu Wan; |
| 202 | Revisiting Graph Autoencoders As Implicit Contrastive Learners Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we revisit GAEs through the lens of contrastive learning and show that both structure-based and feature-based GAEs can be conceptualized as implicitly graph contrastive learners. |
Jintang Li; Ruofan Wu; Yuchang Zhu; Huizhe Zhang; Zulun Zhu; Liang Chen; |
| 203 | Optimizing Generative Ranking Relevance Via Reinforcement Learning in Xiaohongshu Search Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we formulate relevance modeling in Xiaohongshu search as a reasoning task and introduce a Reinforcement Learning (RL)-based training framework to enhance the grounded reasoning capabilities of GRMs. |
Ziyang Zeng; Heming Jing; Jindong Chen; Xiangli Li; Hongyu Liu; Yixuan He; Zhengyu Li; Yige Sun; Zheyong Xie; Yuqing Yang; Shaosheng Cao; Jun Fan; Yi Wu; Yao Hu; |
| 204 | ClinicalBench: Can LLMs Beat Traditional ML Models in Clinical Prediction? Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: An emerging question is: Can LLMs beat traditional ML models in clinical prediction? Thus, we build a new benchmark ClinicalBench to comprehensively study the clinical predictive modeling capacities of both general-purpose and medical LLMs, and compare them with traditional ML models. |
Canyu Chen; Jian Yu; Shan Chen; Che Liu; Zhongwei Wan; Shuang Zhou; Yuan Luo; Rui Zhang; Danielle Bitterman; Fei Wang; Kai Shu; |
| 205 | Unity: Fully Self-Supervised Pretraining with Transformers for Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present Unity, a fully self-supervised learning framework for recommendation. |
Shuang Yang; Yang Yang; Tao Liu; Feng Qi; Kaushik Rangadurai; Luke Simon; Sandeep Pandey; |
| 206 | SGS-GNN: A Supervised Graph Sparsifier for Graph Neural Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose SGS-GNN, a supervised graph sparsifier for Graph Neural Networks (GNNs) to improve predictive performance and reduce the cost of message passing by removing task-irrelevant edges. |
Siddhartha Shankar Das; Naheed Anjum Arafat; Muftiqur Rahman; S M Ferdous; Alex Pothen; Mahantesh Halappanavar; Danda B. Rawat; |
| 207 | Benchmarking Multimodal LLMs on Recognition and Understanding Over Chemical Tables Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Chemical tables are particularly representative: they intertwine structured variables such as reagents, conditions, and yields with visual symbols like molecular structures and chemical formulas, posing significant challenges to models in cross-modal alignment and semantic parsing. To address this, we propose ChemTable—a benchmark of chemical tables constructed from real-world literature, containing expert-annotated cell layouts, logical structures, and domain-specific labels. |
Yitong Zhou; Mingyue Cheng; Qingyang Mao; Yucong Luo; Qi Liu; Yupeng Li; Xiaohan Zhang; Deguang Liu; Xin Li; Enhong Chen; |
| 208 | PilotANN: Memory-Bounded GPU Acceleration for Vector Search Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: As a solution, we propose PilotANN, a hybrid CPU-GPU system for graph-based ANNS that utilizes both CPU’s abundant RAM and GPU’s parallel processing capabilities. |
Yuntao Gui; Peiqi Yin; Xiao Yan; Chaorui Zhang; Weixi Zhang; James Cheng; |
| 209 | Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP Vs Rule Extraction Vs RuleSHAP Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We find that RuleFit often misses non-univariate triggers, while global SHAP better ranks conjunctive trigger features but yields no symbolic rules. To bridge this gap, we propose RuleSHAP, a rule-extraction algorithm that couples global SHAP aggregates with rule induction to better capture non-univariate triggers, improving MRR@1 over RuleFit by +82\% on average. |
Francesco Sovrano; |
| 210 | Self-Regulating Prompt Expansion for Continual Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, this design limits knowledge reuse and imposes a fixed prompt capacity, leading to linear prompt growth and suboptimal performance across diverse task distributions. To solve these limitations, we propose Self-regulating COntinual Prompt Expansion (SCOPE), a framework that dynamically allocates prompt capacity on demand. |
Yiwen Wang; Diana Benavides-Prado; Yun Sing Koh; |
| 211 | RAViG-Bench: A Benchmark for Retrieval-Augmented Visually-Rich Generation with Multi-Modal Automated Evaluation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Besides, we introduce a novel multi-modal automated evaluation framework that holistically assesses the quality of RAViG outputs. |
Qirui Hu; Shunlei Ning; Chong Bao; Guanyu Chen; Jiaotuan Wang; Wei Yang; Hao Chen; Xuepeng Jia; Wei Zhou; Guofeng Zhang; |
| 212 | Unleashing The Potential of Neighbors: Diffusion-based Latent Neighbor Generation for Session-based Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing methods typically rely on explicitly observed session data, neglecting latent neighbors – not directly observed but potentially relevant within the interest space – thereby failing to fully exploit the potential of neighbor sessions in recommendation. To address the above limitation, we propose a novel model of diffusion-based latent neighbor generation for session-based recommendation, named DiffSBR. |
Yuhan Yang; Jie Zou; Guojia An; Jiwei Wei; Yang Yang; Heng Tao Shen; |
| 213 | OOD-GraphLLM: Graph Large Language Model for Out-of-Distribution Generalized Drug Synergy Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Nevertheless, O.O.D. generalized DSP is highly non-trivial, posing several challenges: i) how to discover structurally relevant and irrelevant molecular representations with respect to cell targets; ii) how to find the optimal graph neural architectures that accurately calculate molecular representations; and iii) how to jointly leverage molecular structural and semantic information in LLMs. To address these challenges, we propose OOD-GraphLLM, a novel graphLLM framework which is able to accurately predict drug synergy under O.O.D. settings via jointly optimizing molecular graph representation and biomedical semantic language representations in a unified manner. |
Xin Wang; Linxin Xiao; Yang Yao; Wenwu Zhu; |
| 214 | Towards Resilient Transportation: A Conditional Transformer for Accident-Informed Traffic Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To address these limitations, we present two enriched traffic datasets from Tokyo and California, incorporating traffic accident and regulation data. Leveraging these datasets, we propose ConFormer (Conditional Transformer), a novel framework that integrates graph propagation with guided normalization layer. |
Hongjun Wang; Jiawei Yong; Jiawei Wang; Shintaro Fukushima; Renhe Jiang; |
| 215 | MoE-Pointer: Seq2Seq Reinforcement Learning for Dynamic Multi-Echelon Pickup-and-Delivery with Courier-Drone Relay Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Moreover, existing reinforcement learning methods are typically tailored for single-echelon problems; this not only mandates stage decoupling that prevents joint optimization, but also fails to address the differentiation across stages. To address these issues, we propose MoE-Pointer, a unified reinforcement learning framework that reformulates DM-PDP into a sequence-to-sequence generation task. |
Rui Bai; Jingyuan Wang; Lu Zhen; |
| 216 | AutoDavis: Automatic and Dynamic Evaluation Protocol of Large Vision-Language Models on Visual Question-Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In comparison, automatic evaluation has shown promise in the textual domain, but the visual modality remains far less explored. To advance this frontier, in this work, we introduce AutoDavis, a first-of-its-kind automatic and dynamic evaluation protocol that enables on-demand benchmarking of LVLMs across specific capability dimensions. |
Han Bao; Yue Huang; Yanbo Wang; Jiayi Ye; Xiangqi Wang; Xiuying Chen; Yue Zhao; Tianyi Zhou; Mohamed Elhoseiny; Xiangliang Zhang; |
| 217 | TEUM: Team Effect-aware Uplift Modeling for Online Games Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Such team effects can heavily influence players’ responses to external treatments in team-based multiplayer games, e.g., in-game resources attained by a player can be shared with the teammates, thus affecting the teammates’ response and vice versa. To tackle this issue, we propose a Team Effect-aware Uplift Modeling framework (TEUM) that incorporates the awareness of causal team effects into the ITE modeling process. |
Ziming Wu; Peicheng Yao; Hanwen Zhong; Xiaohan Hou; Fuming Lai; Shaobing Lian; |
| 218 | From Surface to Depth: Diagnosing Ocean Vertical Velocity with 3D Frequency Operator Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, both existing traditional dynamic methods and classic machine learning algorithms struggle to provide accurate estimates due to their inability to capture the multi-scale spatiotemporal structures and intense vertical fluctuations. To address these challenges, combined with theoretical ocean dynamics, we propose TriSEFormer, a novel approach that leverages frequency-embedded attention mechanism from a tri-dimensional (3D) frequency perspective. |
Haonan Qi; Bin Lu; Yimian Hu; Ze Zhao; Meng Jin; Lixin Qu; Shuai Li; Shizhen Zhao; Lei Zhou; Xiaoying Gan; Xinbing Wang; Chenghu Zhou; |
| 219 | SCOPE: Cost-Efficient Model Selection for Compound AI Systems Under Quality Constraints Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Given a query dataset and a user-specified quality threshold, we aim to select an LLM for each module to minimize the system’s average cost while ensuring that overall quality meets the required threshold. To solve this problem, we propose SCOPE, a cost-efficient optimization algorithm. |
Yiqian Huang; Shiqi Zhang; Tianyuan Jin; Xiaokui Xiao; |
| 220 | CausalPOI: Spatio-Temporal Graph-Based Causal Modeling for Cold-Start POI Check-in Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While recent advancements in spatio-temporal graph learning have improved POI forecasting, most methods rely on proximity-based graphs and correlation-driven modeling, which overlook the functional dependencies between POIs and fail to capture the causal effects of urban interventions. In this paper, we introduce a novel research problem — cold-start POI check-in forecasting, which aims to predict the future check-in pattern of a newly introduced POI, by modeling its temporal evolution and functional interactions with nearby POIs in a structured urban spatial context. |
Zhaoqi Zhang; Miao Xie; Yi Li; Linyou Cai; Siqiang Luo; Gao Cong; |
| 221 | The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs As Unsafe in Multimodal Guardrails Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce Unsafe Induction Attacks, where adversaries distribute imperceptibly perturbed safe images that trigger guard models to reject legitimate user requests, causing a ”Boy Who Cried Wolf” effect that degrades service availability and erodes trust. |
Shuo Shi; Rui Yin; Naen Xu; Jiahao Chen; Chunyi Zhou; Tianyu Du; Zhihui Fu; Jun Wang; Zhaoxiang Wang; Shouling Ji; |
| 222 | Causality-Based Conformal Imputation Correction with Non-Random Missing Labels Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose a model-agnostic framework to assess the accuracy of imputed labels and to correct imputations with large bias based on conformal prediction. |
Chunyuan Zheng; Xiang Li; Hang Pan; Eric Wang; Haoxuan Li; Yang Zhang; See-Kiong Ng; Xiao-Hua Zhou; |
| 223 | LineLM: An Operational Language Model for Minimizing Expert Curation Effort in Large-Scale Geospatial Vector Lines Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present LineLM, an operational language-model-based refinement framework that transforms imperfect line extractions into analysis-ready geospatial vectors in production pipelines. |
Weiwei Duan; Yao-Yi Chiang; |
| 224 | HiBrain: Hierarchical Prototype Learning on Multimodal Brain Graphs for Stage-Aware Biomarker Discovery Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose HiBrain, a hierarchical prototype-based framework for multimodal brain network analysis. |
Jing Ren; Kefan Yang; Nguyen Linh Dan Le; Jingjing Zhou; Xikun Zhang; Ziqi Xu; Xiangjie Kong; Xiaodong Li; Feng Xia; |
| 225 | Generalized Range Filtering Approximate Nearest Neighbor Search: Containment and Overlap Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Hence, we introduce a new approach, labeled multi-segment tree graph. |
Yingfan Liu; Tong Wu; Jiadong Xie; Yang Zhao; Jeffrey Xu Yu; Jiangtao Cui; |
| 226 | BatteryMFormer: Multi-level Learning for Battery Degradation Trajectory Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing approaches often fail to explicitly model these characteristics. To bridge this gap, we propose BatteryMFormer, a multi-level Transformer for early BDTF. |
Ruifeng Tan; Jintao Dong; Weixiang Hong; Jia Li; Jiaqiang Huang; Tong-Yi Zhang; |
| 227 | Neural Gaussian Radio Fields for Channel Estimation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This work introduces neural Gaussian radio fields (nGRF), a physics-informed framework that reframes neural field design by replacing view-dependent rasterization with direct complex-valued aggregation in 3D space. |
Muhammad Umer; Muhammad Ahmed Mohsin; Ahsan Bilal; John M. Cioffi; |
| 228 | Epistemic-Aware Vision-Language Foundation Model for Fetal Ultrasound Interpretation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, most are adapted to structured adult imaging and underperform in fetal ultrasound, which poses challenges of multi-view image reasoning, numerous diseases, and image diversity. To bridge this gap, we introduce FetalMind, a medical AI system tailored to fetal ultrasound for both report generation and diagnosis. |
Xiao He; Huangxuan Zhao; Guojia Wan; Jiancheng Pan; Yanxing Liu; Xin Zou; Yong Luo; Yongchao Xu; Juhua Liu; Wei Zhou; Dacheng Tao; Bo Du; |
| 229 | Co4ICF: Co-evolving Physics-Informed Surrogate and RL-based Pulse Optimizer for Inertial Confinement Fusion Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Here we present Co4ICF, a co-evolving framework that couples a physics-informed surrogate with a PPO-based pulse optimizer. |
Jiatong Zhao; Tengyue Zhang; Yuhan Wang; Fuyuan Wu; Junchi Yan; |
| 230 | Uncertainty-aware Generative Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose Uncertainty-aware Generative Recommendation (UGR), a unified framework that leverages uncertainty as a critical signal for adaptive optimization. |
Chenxiao Fan; Chongming Gao; Yaxin Gong; Haoyan Liu; Fuli Feng; Xiangnan He; |
| 231 | Multi-Agent Collaborative Reasoning with Tool-Augmented Evidence for Urban Region Profiling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose UrbanAgent, an agentic framework that reframes urban region profiling as a reasoning-driven inference problem. |
Xixuan Hao; Yutian Jiang; Jiabo Liu; Yihang Yang; Guangyin Jin; Song Gao; Yuxuan Liang; |
| 232 | TAROT: Task-Adaptive Refinement of LLM-prior Graphs for Few-shot Tabular Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Semantic graph is essential for modeling meaningful feature interactions in few-shot scenarios. In this paper, we propose TAROT, a GNN-based framework that encodes the structural and semantic prior by constructing and refining a task-adaptive semantic graph from this prior, thereby improving predictive performance in few-shot tabular learning. |
Ruxue Shi; Yili Wang; Mengnan Du; Hangting Ye; Yi Chang; Xin Wang; |
| 233 | Text-guided Molecule Generation with Conditional Discrete Graph Diffusion Model Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a text-guided molecular graph generation framework that leverages the structural modeling power of graph diffusion models to achieve both strong alignment with textual descriptions and high-quality molecular structures. |
Yang Yao; Xin Wang; Yaofei Wu; Zeyang Zhang; Daixin Wang; Zhiqiang Zhang; Hong Mei; Wenwu Zhu; |
| 234 | TS-MTM: Temporal-Spectral Masked Time-Series Modeling for Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While Masked Time-series Modeling (MTM) has emerged as a powerful self-supervised paradigm, its conventional one-dimensional (1D) formulation often fails to resolve the underlying structural dependencies essential for long-term forecasting explicitly. To address this limitation, we propose TS-MTM, a Temporal-Spectral Masked Time-series Modeling framework that formalizes pretraining within a joint representation space. |
Pengcheng Zhang; Xiaocao Ouyang; Xin Li; Fan Yang; Wei Huang; Lingfei Ren; Ran Peng; Qiang Zhai; Huimin Fu; |
| 235 | Cross-Source Reasoning-based Correction for Author Name Disambiguation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose CrossND, a full-stack framework that integrates data refinement, cross?source reasoning, and test-time scaling. |
Fanjin Zhang; Yunhe Pang; Bo Chen; Zhiyu Shen; Yanghui Rao; Evgeny Kharlamov; Jie Tang; |
| 236 | AGDN: Learning to Solve Traveling Salesman Problem with Anisotropic Graph Diffusion Network Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present the Anisotropic Graph Diffusion Network (AGDN), a new Graph Neural Network framework designed to solve TSP. |
Bolin Shen; Ziwei Huang; Zhiguang Cao; Yushun Dong; |
| 237 | PACE: Unleashing The Power of Code Embeddings to Boost AutoML Agents Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose PACE (Pre-execution Admission via Code Embeddings), an online-adaptive admission control framework that improves budgeted sample efficiency by estimating candidate utility prior to execution from within-run execution history, without training a separate offline predictor. |
Gangyi Zhao; Hebin Liang; Hongyao Tang; Yi Ma; Jinyi Liu; Zhaocheng Du; Yan Zheng; Chenjun Xiao; Jianye Hao; |
| 238 | EviCare: Enhancing Diagnosis Prediction with Deep Model-Guided Evidence for In-Context Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing LLM-based approaches tend to overfit to historically observed diagnoses, often overlooking novel yet clinically important conditions that are critical for early intervention. To address this, we propose EviCare, an in-context reasoning framework that integrates deep model guidance into LLM-based diagnosis prediction. |
Hengyu Zhang; Xuyun Zhang; Pengxiang Zhan; Linhao Luo; Hang Lv; Yanchao Tan; Shirui Pan; Carl Yang; |
| 239 | NBQ: Next-Best-Question for Dynamic Profiling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To scale matching to real-world platforms with millions of concurrent users and continuously updated profiles, we introduce QuickMatch, an efficient retrieval layer that recasts reciprocal matching from quadratic pairwise scoring to approximate vector search. |
Yimin Shi; Clarice Wang; Haixun Wang; Xiaokui Xiao; |
| 240 | WARP: A Word-Level Backdoor Attack Targeting RAG Systems Via Retrieval Corpus Poisoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While enhancing large language models (LLMs) performance, RAG also introduces a new attack surface: adversaries can inject trigger-embedded malicious documents into the corpus database, potentially causing the LLM to produce attacker-controlled outputs. To expose this vulnerability, we propose the first word-level backdoor attack targeting RAG systems through retrieval corpus poisoning named WARP. |
Hui Liu; Yibo Zhou; Liguo Dong; Weidong Li; Shui Yu; |
| 241 | SmartGen: Synthesizing Context-Aware User Behavior Data for Adaptive Smart Home Intelligence Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose SmartGen, an LLM-based framework that synthesizes context-aware user behavior data to support continual adaptation of downstream smart home models. |
Zhiyao Xu; Dan Zhao; Qingsong Zou; Qing Li; Yong Jiang; Yuhang Wang; Jingyu Xiao; |
| 242 | DMFlow: Disordered Materials Generation By Flow Matching Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, most deep generative models focus exclusively on perfectly ordered crystals, neglecting the important class of disordered materials. To address this gap, we introduce DMFlow, a generative framework specifically designed for disordered crystals. |
Liming Wu; Rui Jiao; Qi Li; Mingze Li; Songyou Li; Shifeng Jin; Wenbing Huang; |
| 243 | CoFEH: LLM-driven Feature Engineering Empowered By Collaborative Bayesian Hyperparameter Optimization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present CoFEH, a collaborative framework that interleaves LLM-based FE and Bayesian HPO for robust end-to-end AutoML. |
Beicheng Xu; Keyao Ding; Wei Liu; Yupeng Lu; Bin Cui; |
| 244 | EnergyMamba: An Uncertainty-Aware Graph-Enhanced Selective State Space Model for Energy Consumption Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To advance existing research, we propose EnergyMamba, an uncertainty-aware spatiotemporal learning framework for accurate and reliable energy consumption prediction, which comprises two key components: (i) a novel Graph-Enhanced Selective State Space Model (GE-Mamba) that injects spatial context learned from the grid topology into the temporal dynamics, enabling coupled spatiotemporal modeling, and (ii) an Adaptive Sequential Conformalized Quantile Regression (AS-CQR) module, which includes locally adaptive normalization and an online feedback mechanism to dynamically calibrate prediction intervals under potential distribution shifts. |
Dahai Yu; Rongchao Xu; Lin Jiang; Guang Wang; |
| 245 | RAPO: Expanding Exploration for LLM Agents Via Retrieval-Augmented Policy Optimization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we revisit exploration in Agentic RL and propose Retrieval-Augmented Policy Optimization (RAPO), a novel RL framework that introduces retrieval to explicitly expand exploration during training. |
Siwei Zhang; Yun Xiong; Xi Chen; Zi’an Jia; Renhong Huang; Jiarong Xu; Jiawei Zhang; |
| 246 | Parameterized Fair Resource Allocation Under Diversity Constraints Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Resource allocation across multiple agent groups arises in many applications including e-commerce recommendation systems, housing assignment, and course allocation, and is commonly formulated as an optimization problem with diversity constraints to ensure group fairness. Existing approaches typically enforce these constraints as hard conditions, which overly restrict the feasible solution space and often lead to suboptimal allocations.In this paper, we propose PRA, a parameterized framework for fair resource allocation under diversity constraints. |
Keke Huang; Yik Yu Ng; Laks V.S. Lakshmanan; Xiaokui Xiao; |
| 247 | SensCluster: Sensitivity-Guided Client Clustering for Feature-Skewed Federated Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we reveal a key observation: under feature distribution skew, different network layers exhibit highly unequal sensitivity, with early layers encoding strongly client-specific feature patterns that dominate aggregation behavior. |
Jiaqi Wang; Tobias Schlagenhauf; Setareh Maghsudi; |
| 248 | UniExtreme: A Universal Foundation Model for Extreme Weather Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we identify two key characteristics of extreme events: (1) the spectral disparity against normal weather regimes, and (2) the hierarchical drivers and geographic blending of diverse extremes. |
Hang Ni; Weijia Zhang; Hao Liu; |
| 249 | MM-BRIGHT: A Multi-Task Multimodal Benchmark for Reasoning-Intensive Retrieval Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Many real-world queries contain multimodal elements, particularly, images such as diagrams, charts, and screenshots that require intensive reasoning to identify relevant documents. To address this gap, we introduce MM-BRIGHT, the first multimodal benchmark for reasoning-intensive retrieval. |
Abdelrahman Abdallah; Mohamed Darwish Mounis; Mahmoud Abdalla; Mahmoud SalahEldin Kasem; Mostafa Farouk Senussi; Mohamed Mahmoud; Mohammed Ali; Adam Jatowt; Hyun Soo Kang; |
| 250 | DiffoR: A Unified Continuous Generative Framework for Universal Ordinal Regression Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a novel paradigm where OR is formulated as a Continuous Generative Ordinal Regression task. |
Hongxu Ma; Lin Wang; Chenghou Jin; Han Zhou; Jie Zhang; Xiaoyu Yang; Chunjie Chen; Jihong Guan; Shuigeng Zhou; |
| 251 | FlowTime: Towards Continuous Generative Watch Time Prediction Via Flow-based Personalized Priors Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Watch time has emerged as a pivotal metric for optimizing deep user engagement in short-video recommender systems. However, current methods of watch time prediction (WTP) suffer … |
Hongxu Ma; Han Zhou; Chenghou Jin; Jie Zhang; Xiaoyu Yang; Chunjie Chen; Jihong Guan; Shuigeng Zhou; |
| 252 | FedTail-DT: A Dual-Teacher Framework for Long-Tailed Heterogeneous FL with CLIP Prototypes and Adaptive Aggregation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper proposes FedTail-DT, a novel approach for long-tailed heterogeneous federated learning, featuring three key innovations: (1) a dual-teacher–single-student architecture that integrates a pre-trained CLIP model as a semantic prior teacher and a globally aggregated model as an iterative optimization teacher to enhance tail-class perception; (2) CLIP text-prototype contrastive learning that uses text prototypes as semantic anchors to counteract feature bias caused by long-tailed distributions; (3) a multi-dimensional client scoring mechanism that dynamically calibrates aggregation weights based on data volume, category completeness, and update consistency. |
Zijie Guo; Jinghua Zhu; Gang Du; Kejia Zhang; |
| 253 | GEM-Bench: A Benchmark for Ad-Injected Response Generation Within Generative Engine Marketing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: GEM-Bench includes three curated datasets covering both chatbot and search scenarios, a metric ontology that captures multiple dimensions of user satisfaction and engagement, and several baseline solutions implemented within an extensible multi-agent framework. |
Silan Hu; Shiqi Zhang; Yimin Shi; Xiaokui Xiao; |
| 254 | ESTIM: Efficient and Scalable Tensorial Incomplete Multi-view Semi-supervised Classification Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, the computational complexity of these methods is cubically dependent on the scale of instances, which severely hampers the scalability to large-scale data. To address these issues, we propose an Efficient and Scalable Tensorial Incomplete Multi-view semi-supervised classification named ESTIM. |
Tingjin Luo; XiangYao Li; Zhangqi Jiang; Shuanghui Zhang; Dewen Hu; |
| 255 | AlphaEval: A Comprehensive and Efficient Evaluation Framework for Formula Alpha Mining Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Additionally, the closed-source nature of most existing alpha mining models hinders reproducibility and slows progress in this field. To address these issues, we propose AlphaEval, a unified, parallelizable, and backtest-free evaluation framework for automated alpha mining models. |
Hongjun Ding; Binqi Chen; Jinsheng Huang; Taian Guo; Zhengyang Mao; Guoyi Shao; Lutong Zou; Luchen Liu; Ming Zhang; |
| 256 | Recipes for Agents: Understanding Skills and Their Open Questions Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We then outline open questions in skill construction, composition, evaluation, portability, governance, and security, and conclude with a call for contribution. Our goal is not to present skills as a settled solution, but to clarify their promise, limits, and the questions that must be answered before they can become a principled foundation for future agent systems. |
Hanwen Xing; Haomin Zhuang; Xuandong Zhao; Yue Huang; Zhenheng Tang; Xiangliang Zhang; |
| 257 | FedFST: Mitigating Spectral Catastrophic Forgetting in Federated Graph Continual Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we propose FedFST, a spectral-aware framework that mitigates dual spectral forgetting. |
Hanyao Guo; Zihan Tan; Wenke Huang; Bin Yang; Mang Ye; |
| 258 | DualLane: Fast and Reliable LLM Agents for Interactive AIOps Via Dual-Path Planning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To enhance both operational efficiency and resolution accuracy, we propose DualLane, a novel parallel dual-path planning architecture designed for AI agents. |
Haoyu Wang; Wenxuan Ma; Bing Hu; Haozhe Li; Qingqian Si; Hongke Guo; Boyang Huang; Zhaoliang Zhu; You Zhang; Yu Zhou; Xudong Zheng; |
| 259 | AUDETER: A Large-scale Dataset for Deepfake Audio Detection in Open Worlds Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We further observe that most existing detectors default to binary supervised training, which can induce negative transfer across synthesis sources when the training data contains highly diverse deepfake patterns, impacting overall generalisation. As a complementary contribution, we propose an effective curriculum-learning-based approach to mitigate this effect. |
Qizhou Wang; Hanxun Huang; Guansong Pang; Sarah Erfani; Christopher Leckie; |
| 260 | HyRES: Measuring Node Influence Via Hyperspherical Representation Equilibrium Shift Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To bridge the gap between topological analysis and deep representation learning, we propose Hyperspherical Representation Equilibrium Shift (HyRES), a theoretically grounded, unsupervised framework that redefines node influence as a geometric displacement within the latent space. |
Yantuan Xian; Chunping Li; Hongbin Wang; Ran Song; Yan Xiang; Yuxin Huang; Zhengtao Yu; |
| 261 | Chem-R: Learning to Reason As A Chemist Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Despite the potential of Large Language Models (LLMs) in chemical discovery, current LLMs still lack fundamental chemical domain knowledge, produce incoherent reasoning trajectories, and exhibit suboptimal performance across diverse chemical tasks. To address these challenges, we propose Chem-R, a general Chemical Reasoning model designed to emulate the deliberative processes of chemists. |
Weida Wang; Benteng Chen; Di Zhang; Wanhao Liu; Ben Gao; Shuchen Pu; Shuzhou Sun; Jin Zeng; Tianshu Yu; Wanli Ouyang; Xiao-Yong Wei; Jiatong Li; Zifu Wang; Yuqiang Li; Shufei Zhang; |
| 262 | Structured Task Alignment for Multi-Objective Learning to Rank Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we reframe multi-objective ranking from a novel distribution-alignment perspective and propose a Structured Task Alignment Framework (STAF) to effectively model the user-satisfaction score. |
Qing Luo; Ge Chen; Huayi Shen; Weiqi Zhao; Ping Yang; Yao Hu; |
| 263 | Denoising Implicit Feedback for Cold-start Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To achieve denoising implicit feedback for cold-start recommendation, we propose a model-agnostic denoising method called DIF. |
Gaode Chen; Shicheng Wang; Shikun Li; Rui Huang; Xinghua Zhang; Yunze Luo; Shipeng Li; Shiming Ge; Ruina Sun; Yinjie Jiang; Jun Zhang; |
| 264 | Physics-Informed Generative World Models for Real-Time Bidding: Deriving Statistical Laws from First Principles Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: These approaches are statistically ill-posed for auction data, failing to capture the extreme heteroscedasticity where variance scales explosively with the mean, and neglecting the structural coupling between feedback variables. In this paper, we bridge this gap through a physics-informed statistical modeling framework derived from first principles. |
Chenyang Wu; Tianyu Wang; Shengjun Fang; Mingjun Cao; Pengfei Liu; Zongzhang Zhang; Yeshu Li; Zhilin Zhang; Chuan Yu; Jian Xu; Bo Zheng; |
| 265 | Approximate Machine Unlearning Through Manifold Representation Forgetting Guided By Self Mode Connectivity Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose ManiF-SMC (Manifold Forgetting with Self Mode Connectivity), motivated by the observation that a model retrained on the remaining data tends to classify erased samples by their semantic similarity to the retained data. |
Weiqi Wang; Zhiyi Tian; Chenhan Zhang; Luoyu Chen; Shui Yu; |
| 266 | HeimdaLLM: Efficient Cloud-assisted Federated Fine-tuning with Zeroth-Order Rectification for LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Federated Learning (FL) enables privacy-preserving distributed fine-tuning, yet conventional approaches, including full fine-tuning and parameter-efficient fine-tuning (PEFT), either rely on backpropagation, which is memory-intensive, or zeroth-order optimization (ZOO), which suffers from high variance and directional bias, leading to slow convergence and degrading accuracy. To address these limitations, we propose HeimdaLLM, a cloud-assisted federated fine-tuning framework that combines ZOO with Gradient Rectification (ZGR). |
He Sun; Jinrui Zhou; Li Li; Yebo Wu; Mingjun Xiao; |
| 267 | CityWeave: Weaving User Needs and World Constraints for Personalized and Reliable Mobility Planning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this study, we propose CityWeave, a VLM-based framework for urban D2D mobility planning that integrates the Who–When–Where–How (3W1H) reasoning paradigm with a two-stage training scheme. |
Ao Wang; Zhiwen Chen; Shen Wang; Qiang Xia; Yi Zhou; Jian Li; |
| 268 | MKG-RAG-Bench: Benchmarking Retrieval in Multimodal Knowledge Graph–Augmented Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In practice, retrieval is a critical bottleneck: multimodal knowledge is heterogeneous, difficult to align across modalities, and often poorly served by retrievers designed for unstructured corpora. To address this gap, we introduce MKG-RAG-Bench, a cross-domain benchmark explicitly designed to evaluate retrieval in MKG-RAG. |
Xiaochen Wang; Bao Hoang; Han Liu; Ting Wang; Fenglong Ma; |
| 269 | Decomposing Predictive Roles of Semantic and Collaborative Information for Sequential Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we revisit semantics-enhanced sequential recommendation by introducing an information-theoretic analysis, which decomposes next-item predictive information into three components: shared information, semantic-unique information, and collaborative-unique information. |
Jiangnan Xia; Yu Yang; Xiang Wang; Ninghao Liu; |
| 270 | Beyond Holistic Models: Systematic Component-level Benchmarking of Deep Multivariate Time-Series Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose TSCOMP, the first large-scale benchmark that systematically deconstructs deep forecasting methods into their core, fine-grained components—spanning series preprocessing, encoding strategies, network architectures including specific and large time-series models, and optimization methods. |
Shuang Liang; Chaochuan Hou; Xu Yao; Shiping Wang; Hailiang Huang; Songqiao Han; Minqi Jiang; |
| 271 | GenHAR: Generalizing Cross-domain Human Activity Recognition for Last-mile Delivery Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, a major challenge faced by HAR is the distribution shift across different sensor data domains, which often leads to decreased performance when deployed for real-world applications. To address this issue, this paper introduces GenHAR, a novel framework designed to mitigate the domain gap by learning domain-invariant sensor representations. |
Zhiqing Hong; Zelong Li; Xiubin Fan; Guang Yang; Baoshen Guo; Haotian Wang; Tian He; Desheng Zhang; |
| 272 | HIVE: Hierarchical Generation of Integrated and Varied Ensembles for Efficient Out-of-Distribution Generalization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose HIVE, a model-agnostic framework that reframes OOD generalization as the construction of a functionally diverse basis set. |
Qi Qin; Yuzhao Zhang; Jiaxing Han; Maolin Wang; Yu Su; Yifan Sun; Peng Zhang; |
| 273 | VIVID: Backbone Training-Free Text-to-Image Video Editing Via Variational Latent Anchors Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose VIVID (Variational Inference for Video editing with Image Diffusion), an uncertainty-aware variational latent anchoring module that dynamically selects informative frames and compresses cross-frame latents into a compact set of semantic anchors. |
Zhangkai Wu; Xuhui Fan; Zhongyuan Xie; Kaize Shi; Longbing Cao; |
| 274 | IMPACTNet: Unifying Auto-bidding in End-to-End Merged Auctions Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Nevertheless, existing works often fail to address this multi-stakeholder challenge in the modern auto-bidding era. To address these issues, we introduce IMPACTNet, an end-to-end framework based on automated mechanism design that learns a unified allocation and pricing mechanism. |
Yuhan Wang; Yuchao Ma; Liang Zhang; Ziyuan Wang; Zhiyuan Su; Qi Qi; Yafei Wang; Xu Li; Yuyao Liu; Pengjie Wang; Jian Xu; Bo Zheng; |
| 275 | Scalable Network-Aware Experiment Design for Two-Sided Marketplaces Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper introduces EgoCluster V3, an iterative clustering algorithm that reduces spillover by 3x compared to prior versions while preserving node coverage and doubling test power. |
Yi Su; Zhen Yan; |
| 276 | Rewarding The Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Specifically, they fail to detect silent errors, logical flaws that yield incorrect results without triggering interpreter exceptions, and erroneously penalize exploratory actions, mistaking necessary trial-and-error exploration for grounding failures. To bridge this gap, we introduce DataPRM, a novel environment-aware generative process reward model that (1) can serve as an active verifier, autonomously interacting with the environment to probe intermediate execution states and uncover silent errors, and (2) employs a reflection-aware ternary reward strategy that distinguishes between correctable grounding errors and irrecoverable mistakes. |
Zhisong Qiu; Shuofei Qiao; Kewei Xu; Yuqi Zhu; Lun Du; Ningyu Zhang; Huajun Chen; |
| 277 | ProfiliTable: Profiling-Driven Tabular Data Processing Via Agentic Workflows Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While recent LLM-based approaches show promise for automating such tasks, they often struggle in practice due to ambiguous instructions, complex task structures, and the lack of structured feedback, resulting in syntactically correct but semantically flawed code. To address these challenges, we propose ProfiliTable, an autonomous multi-agent framework centered on dynamic profiling, which constructs and iteratively refines a unified execution context through interactive exploration, knowledge-augmented synthesis, and feedback-driven refinement. |
Wei Liu; Yang Gu; Xi Yan; Zihan Nan; Beicheng Xu; Keyao Ding; Bin Cui; Wentao Zhang; |
| 278 | SafeBuild-Bench: A Temporal-Robust Construction Safety Benchmark with Graph-Enhanced Data Mining Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce SafeBuild-Bench, a metadata-driven benchmark for evaluating multimodal large language models on construction safety under realistic temporal and site variation. |
Yi Cui; Zilin Wang; Yijie Xu; Qianyi Cai; Huizai Yao; Shuai Jiang; Bingzhuo Zhong; Hui Xiong; |
| 279 | HD-Prot: A Protein Language Model for Joint Sequence-Structure Modeling with Continuous Structure Tokens Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Current methods often discretize protein structures to accommodate the language modeling framework, which inevitably results in the loss of fine-grained information and limits the performance potential of multimodal pLMs. In this paper, we argue that such concerns can be circumvented: a sequence-based pLM can be extended to incorporate the structure modality through continuous tokens, i.e., high-fidelity protein structure latents that avoid vector quantization. |
Yi Zhou; Haohao Qu; Yunqing Liu; Shanru Lin; Le Song; Wenqi Fan; |
| 280 | HURST: Heterogeneity-Adaptive Urban Foundation Models for Spatiotemporal Prediction Via Self-Partitional Mixture-of-Spatial-Experts Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing UFMs lack sufficient consideration of this important issue and thus have unsatisfactory performance in spatially heterogeneous urban settings. To address this limitation, this paper proposes HURST, a Heterogeneity-Adaptive URban Foundation Model for Spatio-Temporal Prediction, that is capable of capturing the spatial pattern of heterogeneity underlying the urban setting to enhance the UFM’s performance. |
Zirui Zhou; Xun Zhou; Kanyu Bao; Shengxin Liu; Kehai Chen; Min Zhang; |
| 281 | When Deepfake Detection Meets Graph Neural Network: A Unified and Lightweight Framework Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper introduces SSTGNN, a lightweight Spatial-Spectral-Temporal Graph Neural Network framework that represents videos as structured graphs, enabling joint reasoning over spatial inconsistencies, temporal artifacts, and spectral distortions. |
Haoyu Liu; Chaoyu Gong; Mengke He; Jiate Li; Kai Han; Siqiang Luo; |
| 282 | DuetDA: Decomposed and Dynamic Data Attribution with Model-State Gating for Accelerated Scientific Endeavors Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This phase-dependent behavior implies that a sample’s value is not fixed, but can change with the model’s state. To address this, we propose DuetDA, a decomposed and dynamic DA framework with model-state gating. |
Jianpeng Chen; Wangzhi Zhan; Haohui Wang; Dongqi Fu; Dawei Zhou; |
| 283 | SCOPE: Streaming Covariance-Orthogonal Post-Hoc Editing for Continual LLM Safety Governance Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose SCOPE, a streaming post-hoc editing framework for capability-invariant LLM safety governance. |
Yizhe Yang; Xuanming Jiang; Jisheng Dang; Aoying Wang; Baoyi An; Hao Wu; Bimei Wang; Hong Peng; Guoshuai Zhao; Bin Hu; Zhongyu Yang; |
| 284 | ErrorLLM: Modeling SQL Errors for Text-to-SQL Refinement Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose ErrorLLM, a framework that explicitly models text-to-SQL Errors within a dedicated LLM for text-to-SQL refinement. |
Zijin Hong; Hao Chen; Zheng Yuan; Qinggang Zhang; Luyao Zhuang; Qing Liao; Feiran Huang; Yangqiu Song; Xiao Huang; |
| 285 | Machine Unlearning on Trajectory Data: An Experimental Analysis Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we present the first systematic study of machine unlearning for trajectory data. |
Yuanjun Liu; Jiaxing Shen; Weiqi Wang; Jingwen Li; Jiajie Xu; Lei Zhao; Haoran Xie; An Liu; |
| 286 | Kairos: Time-Sensitive Scheduling for Ad-Oriented ML Workloads with Heterogeneous Time-Utility Functions Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing schedulers lack precise functions of such value decay and primarily optimize system-level metrics such as throughput or fairness, thereby failing to preserve the time-dependent business utility of these tasks. To bridge this gap, this paper identifies three distinct types of ad recommendation tasks (i.e.,, SLO, softSLO and BE tasks), each with characteristic value decay patterns, and develop empirically-grounded Time-Utility Functions (TUFs) using real-world datasets, which offer a robust abstraction that transforms noisy, non-stationary business data into tractable utility functions suitable for scheduling. |
Xun Hu; Luyao Luo; Yu-e Sun; He Huang; |
| 287 | Incorporating 3D Structural Information for Activity Cliff Analysis Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, the limited availability of activity cliff data for target-ligand 3D complexes constrains the predictive power of modern deep learning models. To bridge this gap, we introduce DockedAC, a new dataset incorporating the protein target and 3D complex structure information to enable geometric reasoning in activity cliff analysis. |
Zijing Liu; Xinni Zhang; Yankai Chen; Bin Feng; Mingjun Yang; Zenglin Xu; Yu Li; Philip S. Yu; Irwin King; |
| 288 | Cognitive Distillation for Information Forensics: Towards Improved Hateful Meme Detection Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, most existing methods rely solely on image-text semantic similarity for information forensics, ignoring the key characteristic of meme that their meanings are shaped by the collective cognition of diverse users. To address this issue, we propose a Cognition-driven Information Forensics (CIF) framework for hateful meme detection, which integrates the collective cognition of diverse users into the entire process of information forensics and hateful content detection. |
Xiuxian Wang; Yuting Su; Wenhui Li; Ruidong Chen; Zhuojun Li; Anan Liu; |
| 289 | Perturbed Public Voices (P2V): A Dataset for Robust Audio Deepfake Detection Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce Perturbed Public Voices (P2V), an IRB-approved dataset capturing three critical aspects of malicious deepfakes: (1) identity-consistent transcripts via LLMs, (2) environmental and adversarial noise, and (3) state-of-the-art voice cloning (2020–2025). |
Chongyang Gao; Marco Postiglione; Isabel Gortner; Sarit Kraus; VS Subrahmanian; |
| 290 | From Noisy STEM to Crystal Structure: Evidence-Structure CoDiffusion Under Composition Constraints Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We cast this task as a coupled inference problem that separates evidence recovery from structure inference under a minimal forward model. We introduce STEM2Crystal CoDiffusion (SCCD), a dual-diffusion framework that explicitly separates evidence recovery from structure inference and couples them via bidirectional feature exchange. |
Guangyao Chen; Fengqi You; |
| 291 | TGD-CSP: Reliable Crystal Structure Prediction with Template-Guided Diffusion and Energy-Based Optimization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While recent diffusion-based generative models achieve impressive results by conditioning on space-group symmetry information, this paradigm exposes three fundamental challenges: (1) unreliable symmetry inference from composition, (2) reliance on symmetry-only priors without comprehensive structural geometric guidance, and (3) prior-induced distribution shift caused by inaccurate or overly strong constraints. To address these challenges, we propose TGD-CSP, a three-stage generative framework that: (1) learns a cross-modal embedding space to retrieve structurally relevant templates directly from composition, thereby providing reliable symmetry priors; (2) guides diffusion-based generation via score-based conditioning that explicitly incorporates comprehensive geometric information from retrieved templates; and (3) fine-tunes the generative policy via reinforcement learning with an energy-based reward to alleviate prior-induced distribution shift and mitigate biased generation. |
Lu Yang; Tiantian Xu; Xiufeng Liu; Xu Cheng; Fan Shi; Shengyong Chen; |
| 292 | LC-ERD: Mining Latent Logic for Self-Evolving Reasoning Via Consistency-Regulated Reward Decomposition Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To address these, we introduce LC-ERD (Logic-Consistent Endogenous Reward Decomposition), a framework framing self-alignment as latent structure mining. |
Yanyu Chen; Jiyue Jiang; Dianzhi Yu; Zheng Wu; Jiahong Liu; Jiaming Han; Xiao Guo; Jinhu Qi; Yu Li; Yifei Zhang; Irwin King; |
| 293 | USBD: Universal Structural Basis Distillation for Source-Free Graph Domain Adaptation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This dependency is critical under significant topological shifts, where the source model misinterprets distinct topological patterns unseen in the source domain as noise, rendering pseudo-label-based adaptation unreliable. To overcome this limitation, we propose the Universal Structural Basis Distillation (USBD), a framework that shifts the paradigm from adapting a biased model to learning a universal structural basis for SF-GDA. |
Yingxu Wang; Kunyu Zhang; Mengzhu Wang; Siyang Gao; Nan Yin; |
| 294 | An Exterior-Embedding Neural Operator Framework for Preserving Conservation Laws Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This finding underscores the inherent limitations of specialized models in generalizing across diverse problem domains. To address these limitations, we propose Exterior-Embedded Conservation Framework (ECF), a universal conserving framework that can be integrated with various data-driven neural operators to enforce conservation laws strictly in predictions. |
Huanshuo Dong; Hong Wang; Hao Wu; Zhiwei Zhuang; Xuanze Yang; Ruiqi Shu; Yuan Gao; Xiaomeng Huang; |
| 295 | Federated Nonlinear Causal Discovery Via Divide-and-Conquer Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose DC-FNCD (Divide-and-Conquer based Federated Nonlinear Causal Discovery), which decomposes the global problem into independent per-variable neighborhood learning tasks. |
Xianjie Guo; Shuai Yang; Lin Ma; Xi Cheng; Jie Fu; Han Yu; |
| 296 | APCyc: Property-Informed Design of Cyclic Peptides Via Automated Cyclization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To address the limitation, we introduce APCyc, a target-aware de novo cyclic peptide generation framework that explicitly models cyclization and jointly optimizes multiple essential physicochemical properties. |
Yifan Zhao; Lang Qin; Jintai Chen; |
| 297 | The Pitfall of Scaling Up: Uncovering and Mitigating Popularity Bias Amplification in Scaling Transformer-based Recommenders Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our findings reveal that as model depth increases, the two core components of the transformer architecture, i.e., attention aggregation and feed-forward projections, synergistically induce severe spectral collapse in model predictions, which directly translates to the amplification of popularity bias. To address this challenge, we propose SPRINT (Scalable Popularity Regularization IN Transformers), which mitigates spectral collapse during scaling by constraining (i) the maximum columnsums of the attention score matrices and (ii) the spectral norms of the feed-forward parameters. |
Weiqin Yang; Yue Pan; Chongming Gao; Sheng Zhou; Xiang Wang; Can Wang; Jiawei Chen; |
| 298 | UrbanFM: Scaling Urban Spatio-Temporal Foundation Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To enable computation scaling for modeling correlations, we introduce the MiniST unit, a novel split mechanism that discretizes continuous spatio-temporal fields into learnable computational units to unify representations of grid-based and sensor-based observations. |
Wei Chen; Yuqian Wu; Junle Chen; Xiaofang Zhou; Yuxuan Liang; |
| 299 | Medusa: Cross-Modal Transferable Adversarial Attacks on Multimodal Medical Retrieval-Augmented Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose Medusa, a novel framework for crafting cross-modal transferable adversarial attacks on MMed-RAG systems under a black-box setting. |
Yingjia Shang; Yi Liu; Huimin Wang; Furong Li; Wenfang Sun; Chengyu Wu; Yefeng Zheng; |
| 300 | GUI-Robust: A Comprehensive Dataset for Testing GUI Agent Robustness in Real-World Anomalies Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Despite their importance, existing datasets are often constructed under idealized conditions, overlooking the diverse anomalies frequently encountered in real-world deployments. To address this limitation, we introduce GUI-Robust, a novel dataset designed for comprehensive GUI agent evaluation, explicitly incorporating seven common types of anomalies observed in everyday GUI interactions. |
Jingqi Yang; Zhilong Song; Jiawei Chen; Mingli Song; Sheng Zhou; Linjun Sun; Xiaogang Ouyang; Chun Chen; Can Wang; |
| 301 | SpaCellAgent: A Self-Evolving LLM-Based Multi-Agent Framework for Trajectory Analysis Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing methods require extensive manual intervention and proficiency in heterogeneous tools, posing a significant barrier to efficient TI analysis. To bridge this gap, we propose SpaCellAgent, an autonomous large language model (LLM) multi-agent framework that automates end-to-end spatiotemporal analysis and narrative generation. |
Songhan Wang; Haoang Chi; He Li; Zhiheng Zhang; Jiayan Yuan; Cheems Wang; Hao Peng; Xinwang Liu; Wenjing Yang; |
| 302 | VALUE: Value-Aware Large Language Model for Query Rewriting Via Weighted Trie in Sponsored Search Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In addition, bidword value changes rapidly, while existing generative methods do not respond to these fluctuations. To address this shortcoming, we introduce VALUE (Value-Aware Large language model for qUery rewriting via wEighted trie), a framework that integrates value awareness directly into generation and enhances value alignment during training. |
Xiao Zhang; Guanyu Chen; Boyang Zuo; Feng Li; Pengjie Wang; Jian Xu; Bo Zheng; |
| 303 | Step-TP: A Grounded, Step-Level Dataset with Chain-of-Thought Reasoning for LLM-Guided Tensor Program Optimization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce Step-TP, a post-training dataset for tensor program optimization that provides grounded, atomic, step-level supervision with structured chain-of-thought (CoT) reasoning. |
Mengfan Liu; Da Zheng; Junwei Su; Chuan Wu; |
| 304 | Cross-Domain Molecular Relational Learning: Leveraging Chemical Structure-Activity Analysis Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Benefiting from structure-activity analysis, we propose the Domain Adversarial Training Network with Structural-Semantic Transfer Discrepancy (DisTrans) to optimize cross-domain adaptive representation for molecular structures and visual images. |
Peiliang Zhang; Jingling Yuan; Shiqing Wu; Mengqing Hu; Chao Che; Yongjun Zhu; Lin Li; |
| 305 | Representational Alignment with Chemical Induced Fit for Molecular Relational Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: With theoretical justification, we propose the Representational Alignment with Chemical Induced Fit (ReAlignFit) to enhance the stability of MRL. |
Peiliang Zhang; Jingling Yuan; Qing Xie; Yongjun Zhu; Chao Che; Lin Li; |
| 306 | Lifting The Veil of Non-Stationarity in Financial Market Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing methods often assume that the market is stationary, which limits their applicability. To address this, we propose the Market-State Jump Diffusion Framework (MSJD), which models non-stationarity through two key components: an Explicit Market-State Jump Diffusion Process (EMJD) and an Implicit Market-State Jump Diffusion Process (IMJD). |
Vincent Fu; Xinxin Xu; Xuanmeng Zhang; Weichen Xu; Ruilong Ren; Bowen Deng; Xinyu Zhao; Jian Cao; Xixin Cao; |
| 307 | Large Language Model (LLM) As An Excellent Reinforcement Learning Researcher in Both Single-Agent and Multi-Agent Scenarios Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To address these, we propose a Self-Evolutional single-agent/multi-agent Reinforcement Learning (SE-RL) framework. |
Vincent Fu; Xinxin Xu; Weichen Xu; Ruilong Ren; Bowen Deng; Jue Chen; Xinyu Zhao; Jian Cao; Xixin Cao; |
| 308 | Rank Matters: Understanding and Defending Model Inversion Attacks Via Low-Rank Feature Filtering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose the ideal inversion error to measure the privacy leakage, and our theoretical and empirical investigations reveals that higher-rank features are inherently more prone to privacy leakage. |
Hongyao Yu; Yixiang Qiu; Hao Fang; Tianqu Zhuang; Bin Chen; Sijin Yu; Bin Wang; Shu-Tao Xia; Ke Xu; |
| 309 | Vertical Federated K-Means for Multi-View Data Guided By A K-Means Cost Bound After Projection Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To address the first challenge, we provide a theoretical analysis of the upper bound of the loss of k-means for transformation matrix mapping, revealing the relationship between the k-means loss of the transformed data and the original data. |
Feijiang Li; Jinhao Jiang; Jieting Wang; Liang Du; Yuhua Qian; |
| 310 | OmniPhys: Knowledge-Graph-Driven Benchmarking and Collective Optimization for Physical Commonsense in Text-to-Image Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Moreover, the high stochasticity of generative processes causes current prompt optimization methods to suffer from gradient hallucinations, where optimizers are misled by transient visual artifacts rather than systemic flaws. To address these challenges, we introduce OmniPhys, a rigorous benchmark of 1,551 samples grounded in a Physical Knowledge Graph. |
Yajing Xu; Yarong Lan; Jiaoyan Chen; Yichi Zhang; Jeff Z. Pan; Mingchen Tu; Zhizhen Liu; Wen Zhang; Huajun Chen; |
| 311 | Simple Yet Effective Diffusion-based Graph Data Augmentation Via Complementary Diffusion Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing diffusion-based GDA approaches predominantly rely on hard masking or truncation operations, which may inadvertently discard valuable propagated information, thereby limiting performance. To address this dilemma, we propose CoDiT (Complementary Diffusion Transfer), a novel approach that constructs two complementary diffusion views and compensates for missing diffusion signals through cross-view transfer. |
Longlong Lin; Youan Zhang; Zeli Wang; Xin Luo; |
| 312 | AbFlow: End-to-end Paratope-Centric Antibody Design By Interaction Enhanced Flow Matching Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Although recent progress has advanced antibody design, current methods lack a generative framework for end-to-end modeling of full-atom antibody structures and struggle to fully exploit antigen-specific geometric information for optimizing local binding interfaces and global structures. To overcome these limitations, we introduce AbFlow, a flow-matching framework that leverages optimal transport to design full-atom antibodies end-to-end. |
Wenda Wang; Yang Zhang; Zhewei Wei; Wenbing Huang; |
| 313 | See to Solve: A Geometry-Aware Vision-Language Agent for Real-World Routing Problem Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Conversely, neural-network-based methods frequently struggle with distribution shifts across diverse urban environments, leading to poor generalization in real-world deployments. To address these dual limitations, we introduce See to Solve (STS), a novel framework that employs a Vision-Language Model (VLM) as an autonomous agent to construct solutions for complex routing problems in an autoregressive manner. |
Wentao Zhang; Jingyuan Wang; Zetong Zhou; Jiahao Ji; Junjie Wu; |
| 314 | Efficient and Differentially Private Federated LLM Fine-Tuning on Heterogeneous Clients Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose iP-FedLoRA, a privacy-preserving federated fine-tuning framework for heterogeneous clients that strikes a good privacy-utility balance. |
Nan Yan; Yuqing Li; Xiong Wang; Jing Chen; Wei Wang; Kun He; Ruiying Du; Shuhua Li; |
| 315 | Scalable Graph Condensation with Evolving Capabilities Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This work introduces a novel framework for continual graph condensation, enabling efficient updates to the distilled graph that handle data streams without requiring costly retraining. |
Shengbo Gong; Mohammad Hashemi; Juntong Ni; Carl Yang; Wei Jin; |
| 316 | BiVCoder: A Multi-Agent Framework for Code Generation Via Bidirectional Code-Test Diagnosis Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing test-driven code generation and refinement frameworks are often hindered by the tests’ quality: they typically treat self-generated tests as ground truth, leading to ineffective debugging loops where code is modified to satisfy erroneous tests. To address this, we propose BiVCoder, a diagnosis-driven multi-agent framework featuring a novel bidirectional code-test diagnosis mechanism. |
Xiaoyang Li; Jinhao Dong; Wenhang Shi; Wei Lu; Xiaoyong Du; |
| 317 | A Practical Upper Bound on Selection Bias Effects in Medical Prediction Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing methods for predicting model performance rely on unrealistic access to the target distribution or knowledge of the selection mechanism causing bias. To address these limitations, we propose a novel upper bound on the worst-case model performance on the target population under the realistic setting where the selection mechanism and the target population data are only partially observed. |
Kara Liu; Maggie Wang; Russ B. Altman; |
| 318 | Force-Recovered Neural Operators for Coupled Structures with Test-Time Closure Calibration Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a deformation-first neural operator for coupled structural systems. |
Qiwei Wan; Changjie Xu; |
| 319 | SaVe-TAG: LLM-based Interpolation for Long-Tailed Text-Attributed Graphs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose our method, SaVe-TAG (Semantic-aware Vicinal Risk Minimization for Long-Tailed Text-Attributed Graphs), a novel VRM framework that leverages Large Language Models (LLMs) to perform text-level interpolation, generating on-manifold, boundary-enriching synthetic samples for minority classes. |
Leyao Wang; Yu Wang; Bo Ni; Yuying Zhao; Hanyu Wang; Yao Ma; Tyler Derr; |
| 320 | R-Select: A Robust Multi-Metric Data Selection Approach for Fine-Tuning Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, effective data selection remains a persistent bottleneck: simple heuristic filters often fail to capture multifaceted data features (e.g., reasoning depth and diversity), while advanced model-based scoring methods typically prioritize isolated quality dimensions, failing to provide a holistic assessment. To address these challenges, we propose R-Select, a robust and scalable framework that optimizes data selection with 30 distinct quality metrics. |
Xin Gao; Xiaoyang Wang; Yun Zhu; Zheng Liu; Conghui He; Lijun Wu; |
| 321 | SGA: Self-boosting Attributed Graph Alignment Via Neighborhood Consistency-based Edge Enhancement Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper presents SGA (Self-boosting Graph Alignment), a novel framework that introduces a self-supervised objective and an iterative refinement scheme for robustly aligning attributed graphs. |
Chenxu Wang; Wencong Lin; Pinghui Wang; Tao Qin; Wei Wang; Xiaohong Guan; |
| 322 | Hitcher: Efficient GPU-based Vector Search Via Cluster-Centric Kernel and Hitch-Ride Ordering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While their batch-based task reordering rearranges computation for queries in a batch to reduce CPU-GPU data transfer, but latency is prolonged since each query needs to wait for its slowest task. To tackle these problems, we propose Hitcher. |
Qihui Zhou; Changji Li; Guanxian Jiang; Chenhao Ma; Xiao Yan; Yu Mao; Ming-Chang Yang; James Cheng; |
| 323 | Regime-Adaptive Continual Learning for Portfolio Management Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose Regime-aware Continual Adaptive Portfolio management (ReCAP), a novel framework that integrates CL into PM to address the challenges of dynamic financial environments. |
Chaofan Pan; Lingfei Ren; Linbo Xiong; Yonghao Li; Wei Wei; Xin Yang; |
| 324 | ANCHOR: Taming Entropy Dynamics for Stable and Efficient Reasoning of Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our results indicate that entropy evolution depends on the interaction between advantage signals and the log-probability residual relative to its expectation, offering a unified perspective on existing interventions. Based on these findings, we propose ANCHOR, an algorithm designed to resolve deadlocks and maintain stability. |
Cong Qin; Jiaye Lin; Xiaoliang Fu; Yangyi Fang; Chaowen Hu; Huanyao Zhang; Yifu Guo; Zheyuan Gu; Kaitong Qin; Jiawen Kang; Deyang Ding; Peilin Zhao; |
| 325 | Compress The Easy, Explore The Hard: Difficulty-Aware Entropy Regularization for Efficient LLM Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We identify a critical failure mode in these approaches: explicitly optimizing for shorter trajectories triggers rapid entropy collapse, which prematurely shrinks the exploration space and stifles the discovery of valid reasoning paths, particularly for challenging questions requiring extensive deduction. To address this issue, we propose Compress responses for Easy questions and Explore Hard ones (CEEH), a difficulty-aware approach to RL-based efficient reasoning. |
Qin-Wen Luo; Sheng Ren; Xiang Chen; Rui Liu; Jun Fang; Naiqiang Tan; Sheng-Jun Huang; |
| 326 | Bounded Multiscale Forecasting with Hierarchical and Sequential Mesh Refinement of Graph Neural Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce HiFlowCast, a lightweight HGNN that generates boundary conditions by predicting output fields at coarser scales during iterative mesh refinement. |
Thomas Bailie; S. Karthik Mukkavilli; Varvara Vetrova; Yun Sing Koh; |
| 327 | Towards Sustainable Growth: A Multi-Value-Aware Retrieval Framework for E-Commerce Search Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a Multi-Value-Aware retrieval framework tailored for e-commerce search, designed to better align with the cascaded online values across different stages of the search system while balancing immediate conversion and long-term item growth. |
Yifan Wang; Yixuan Wang; Yidan Liang; Qiang Liu; Fei Xiao; |
| 328 | KFTD: Koopman-Fourier Time-Differentiable Network for Continuous Ocean Spatiotemporal Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present Koopman–Fourier Time-Differentiable (KFTD) Network, a time-continuous two-stage paradigm that decouples interpolation from prediction to achieve efficient and scalable spatiotemporal modeling. |
Qinghui Chen; Zekai Zhang; Hailong Liu; Jinglin Zhang; Cong Bai; |
| 329 | CausalFlip: A Benchmark for LLM Causal Judgment Beyond Semantic Matching Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, strong performance on traditional reasoning benchmarks does not guarantee true causal reasoning ability of LLMs, as high accuracy may still arise from memorizing semantic patterns instead of analyzing the underlying true causal structures. To bridge this critical gap, we propose a new causal reasoning benchmark, CausalFlip, designed to encourage the development of new LLM paradigms or training algorithms that ground LLM reasoning in causality rather than semantic correlation. |
Yuzhe Wang; Yaochen Zhu; Jundong Li; |
| 330 | ECGFlowCMR: Pretraining with ECG-Generated Cine CMR Helps Cardiac Disease Classification and Phenotype Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we propose ECGFlowCMR, a novel ECG-to-CMR generative framework that integrates a Phase-Aware Masked Autoencoder (PA-MAE) and an Anatomy-Motion Disentangled Flow (AMDF) to address two fundamental challenges: (1) the cross-modal temporal mismatch between multi-beat ECG recordings and single-cycle CMR sequences, and (2) the anatomical observability gap due to the limited structural information inherent in ECGs. |
Xiaocheng Fang; Zhengyao Ding; Guangkun Nie; Jieyi Cai; Yujie Xiao; Bo Liu; Jiarui Jin; Haoyu Wang; Shun Huang; Ting Chen; Hongyan Li; Shenda Hong; |
| 331 | Over-squashing As Transport Congestion: A Sandpile Dynamics Perspective Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: The theory identifies the relevant design factors, namely capacity and cut size. Guided by these insights, we propose a differentiable Sandpile Stabilization Layer (SSL) and congestion-aware objectives designed to redistribute excess load and manage stabilization costs. |
Yang Shi; Lixian Chen; Jingchao Wang; Minzhe Guo; Mingxuan Huang; Yanhui Chen; Yifeng Xie; Xuhang Chen; Liangsi Lu; |
| 332 | CNText2Sign and CNSign: Unified Chinese Sign Language Datasets for Bidirectional Accessibility Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To create this crucial environment and overcome these challenges, we introduce CNText2Sign and CNSign, which together constitute the first unified dataset aimed at supporting bidirectional accessibility systems for Chinese sign language; CNText2Sign provides 15,000 natural language-to-sign mappings and standardized skeletal keypoints for 8,643 vocabulary items supporting pose assessment. Building upon this foundation, we propose the AuraLLM model, which leverages a decoupled architecture with CNText2Sign’s pose data for novel direct gesture accuracy assessment. |
Yulong Li; Yuxuan Zhang; Feilong Tang; Ming Hu; Zhixiang Lu; Haochen Xue; Jianghao Wu; Rui Chen; Mian Zhou; Kang Dang; Chong Li; Yifang Wang; Imran Razzak; Jionglong Su; |
| 333 | Collaborative Memory Augmentation for Generative Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Despite the success of GR, existing frameworks primarily focus on modeling individual user sequences within a constrained internal parametric space, failing to explicitly leverage cross-user collaborative signals. To address this issue, we propose OMEGA, a cOllaborative MEmory augmentation framework for Generative recommendAtion. |
Enze Liu; Zhen Tian; Wayne Xin Zhao; |
| 334 | AlphaOPT: Formulating Optimization Programs with Self-Improving LLM Experience Library Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present AlphaOPT, a self-improving experience library that enables LLMs to learn optimization modeling knowledge from limited supervision, including answer-only feedback without gold-standard programs, annotated reasoning traces, or parameter updates. |
Minwei Kong; Ao Qu; Xiaotong Guo; Wenbin Ouyang; Chonghe Jiang; Han Zheng; Yining Ma; Dingyi Zhuang; Yuhan Tang; Junyi Li; Shenhao Wang; Haris Koutsopoulos; Hai Wang; Cathy Wu; Jinhua Zhao; |
| 335 | Breaking The Likelihood Trap: Consistent Generative Recommendation with Graph-structured Model Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose Consistent Graph-structured Generative Recommendation (Congrats). |
Qiya Yang; Xiaoxi Liang; Zeping Xiao; Ying Cao; YingJie Deng; Yuxin Ren; Yalong Wang; Yongqi Liu; |
| 336 | Enhancing Protein Representation Learning Via Manifold Restore Mixing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Based on the findings, we propose a simple yet effective DA method, Manifold Restore Mixing (MRM), for protein representation learning. |
Yizhou Dang; Chuang Zhao; Lianbo Ma; Guibing Guo; Xingwei Wang; Zhu Sun; |
| 337 | VCAgent: A Mutation-Guided Self-Reflective Agent Framework for Virtual Cell Modeling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose VCAgent, a self-evolving framework that optimizes how biological knowledge from external APIs is structured and integrated into LLM reasoning. |
Zhiyun Li; Rong Han; Xiaoyu Wang; Guofeng Zhang; Weixi Gao; Yusheng Su; Zihan Tian; Xiaohong Liu; Guangyu Wang; |
| 338 | DivCDSR: A Model-Agnostic Framework for Diverse Cross-Domain Sequential Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Through rigorous empirical experiments and theoretical analysis, we pinpoint two fundamental determinants driving this decline: (1) Domain Homogeneity, where excessive similarity between domains enforces preference redundancy; and (2) Information Asymmetry, where insufficient signal from the source domain fails to meaningfully perturb target-domain distributions. To address these challenges, we propose DivCDSR, a novel model-agnostic framework designed to enhance diversity in CDSR. |
Shu Chen; Yuhan Zhao; Weixin Chen; Weike Pan; Li Chen; |
| 339 | Driving Reaction Trajectories Via Latent Flow Matching Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose LatentRxnFlow, a new reaction prediction paradigm that models reactions as continuous latent trajectories anchored at the thermodynamic product state. |
Yili Shen; Xiangliang Zhang; |
| 340 | TransXion: A High-Fidelity Graph Benchmark for Realistic Anti-Money Laundering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose TransXion, a benchmark ecosystem for Anti-Money Laundering (AML) research that integrates profile-aware simulation of normal activity with stochastic, non-template synthesis of illicit subgraphs.TransXion jointly models persistent entity profiles and conditional transaction behavior, enabling evaluation of ”out-of-character” anomalies where observed activity contradicts an entity’s socio-economic context. |
Keyang Chen; Mingxuan Jiang; Yongsheng Zhao; Zeping Li; Zaiyuan Chen; Weiqi Luo; Zhixin Li; Sen Liu; Yinan Jing; Guangnan Ye; Xihong Wu; Hongfeng Chai; |
| 341 | StormMind: Disentangled Layerwise Modeling for Convective Weather Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce StormMind, a physically grounded framework that forecasts convective evolution by modeling causal interactions across stratified atmospheric layers. |
Jun Chen; Minghui Qiu; Lin Chen; Yan Fang; Shuxin Zhong; Binghong Chen; Kaishun Wu; |
| 342 | PAUSE: A User-Centric Benchmark for Personal AI Assistants in Unified Service Environments Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce PAUSE, a user-centric benchmark for evaluating personal AI assistants in stateful, service-integrated environments. |
Haoyu Chen; Xirui Shi; Yuyao Wang; Jerry Chen; Di Niu; |
| 343 | RIPCN: A Road Impedance Principal Component Network for Probabilistic Traffic Flow Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing PTFF approaches still face two key challenges: (1) how to uncover and model the causes of traffic flow uncertainty for reliable forecasting, and (2) how to capture the spatiotemporal correlations of uncertainty for accurate prediction. To address these challenges, we propose RIPCN, a Road Impedance Principal Component Network that integrates domain-specific transportation theory with spatiotemporal principal component learning for PTFF. |
Haochen Lv; Yan Lin; Shengnan Guo; Xiaowei Mao; Hong Nie; Letian Gong; Youfang Lin; Huaiyu Wan; |
| 344 | FARM: Frequency-Aware Model for Cross-Domain Live-Streaming Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we propose a Frequency-Aware Model for Cross-Domain Live-Streaming Recommendation, termed as FARM. |
Xiaodong Li; Ruochen Yang; Shuang Wen; Shen Wang; Yueyang Liu; Guoquan Wang; Weisong Hu; Qiang Luo; Jiawei Sheng; Tingwen Liu; Jiangxia Cao; Shuang Yang; Zhaojie Liu; |
| 345 | G-STAR: Graph-based Scheduling with Trace-driven Adaptive Routing for Industrial LLM-based Multi-Agent Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing orchestration strategies for LLM-MAS mainly rely on static heuristics, implicit LLM-based routing, or reinforcement learning, which suffer from brittleness under workload drift, prohibitive online exploration costs, and inherent governance risks. To address these issues, we propose G-STAR, a general graph-based scheduling framework that formalizes complex MAS pipelines as attributed Directed Acyclic Graphs (DAGs). |
Jiabao Song; Yu Xia; Beibei Kong; Lei Cheng; Chengxiang Zhuo; Zang Li; Chenyun Yu; |
| 346 | Causal Methods for LLM Development and Evaluation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our contribution is threefold: (1) We explain how causal methods can help develop modern LLM development and evaluation: LLM development relies heavily on logged data, which are often subject to confounding and distribution shifts; evaluation uses learned but potentially biased judges; and deployment environments are non-stationary. |
Dennis Frauen; Marie Brockschmidt; Konstantin Hess; Haorui Ma; Yuchen Ma; Abdurahman Maarouf; Maresa Schr{\o}der; Jonas Schweisthal; Yuxin Wang; Athiya Deviyani; Sonali Parbhoo; Rahul G. Krishnan; Stefan Feuerriegel; |
| 347 | StaR: Stateful Dynamic-Graph Root Cause Analysis Through Memory-Enhanced Causality Discovery Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In reality, modern systems exhibit dynamic topologies (e.g., due to version updates) and stateful failure patterns (e.g., slow memory leaks), where static and memoryless models fail to capture. To address these challenges, we propose StaR, a stateful RCA framework that reformulates the Granger causal discovery process by embedding Temporal Graph Networks as the underlying predictive engine. |
Haiyu Huang; Man Tik Ng; Jiewei Lyu; Yujie Huang; Guangba Yu; Yilun Wang; Michael R. Lyu; |
| 348 | Heterogeneous Multi-Agent Reinforcement Learning with Attention for Cooperative and Scalable Feature Transformation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To address them, we propose a novel heterogeneous multi-agent RL framework to enable cooperative and scalable feature transformation. |
Tao Zhe; Huazhen Fang; Kunpeng Liu; Qian Lou; Tamzidul Hoque; Dongjie Wang; |
| 349 | LatentCRS: A Variational EM Framework for Bridging Semantics and Behavior in LLM-based Conversational Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This discrepancy arises from a fundamental representation gap: while LLMs operate within a semantic space, they lack the behavioral grounding needed to encode user behavioral patterns, such as item co-occurrences, which are crucial for accurate recommendations. To address this, we propose a model-agnostic Variational EM Framework for Bridging Semantics and Behavior in LLM-based Conversational Recommendation (LatentCRS). |
Guanrong Li; Kuo Tian; Jinnan Qi; Qinghan Fu; Zhen Wu; Rui Xia; Xinyu Dai; |
| 350 | AlphaForgeBench: Benchmarking End-to-End Trading Strategy Design with Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: These deficiencies collectively undermine the validity and trustworthiness of numerous existing online and offline financial trading benchmarks, rendering their evaluations unreliable, non-reproducible, and uninformative for meaningful model comparison. To address these limitations, we introduce AlphaForgeBench, a principled evaluation framework that reconceptualizes the role of LLMs from stochastic execution agents to quantitative researchers capable of systematic financial reasoning. |
Wentao Zhang; Mingxuan Zhao; Jincheng Gao; Jieshun You; Huaiyu Jia; Yilei Zhao; Bo An; Shuo Sun; |
| 351 | Causal Scaffolding for Physical Reasoning: A Benchmark for Causally-Informed Physical World Understanding in VLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Understanding and reasoning about the physical world is the foundation of intelligent behavior, yet state-of-the-art vision-language models (VLMs) still fail at causal physical reasoning, often producing plausible but incorrect answers. To address this gap, we introduce CausalPhys, a benchmark of over 3,000 carefully curated video- and image-based questions spanning four domains: Perception, Anticipation, Intervention, and Goal Orientation. |
Tianyi Tang; Zhuoyi Lin; Zeyu Feng; Tianyi Ma; Yew-Soon Ong; Ivor Tsang; Haiyan Yin; |
| 352 | Multi-Agent Debate Based Concept Augmentation for Enhanced Cognitive Diagnosis Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose Multi-Agent based Concept Augmentation for Cognitive Diagnosis (MACA-CD), a novel approach that enhances CD by generating and fusing reliable concept descriptions and relations based solely on concept names. |
Pengyang Shao; Lei Chen; Fei Liu; Yonghui Yang; Xun Yang; Meng Wang; |
| 353 | CloudCons: A Comprehensive End-to-End Benchmark for Cloud Resource Consolidation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: The actual decision utility of these advanced models remains unverified, rendering their practical value for downstream tasks uncertain. To bridge this gap, we propose CloudCons, a comprehensive end-to-end benchmark designed to evaluate forecasting models within the specific context of cloud resource consolidation. |
Xiaobin Zhang; Lefei Shen; Mouxiang Chen; Zhuo Li; Hongkai Li; Han Fu; Jianling Sun; Xiaoxue Ren; Chenghao Liu; |
| 354 | Dynamic Spectral Denoising with Global-Context Attention for Multi-Behavior Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing methods typically address these issues in isolation and often fail when entanglement makes reliability estimation itself unstable. To resolve this robustness bottleneck, we propose Dynamic Spectral Denoising with Global-Context Attention for Multi-Behavior Recommendation (SpectraMB), a target-oriented model that performs representation purification before reliability-aware fusion. |
Miaomiao Cai; Yunshan Ma; Fangqi Zhu; Junfeng Fang; Zhijie Zhang; Zhiyong Cheng; Xiang Wang; See-Kiong Ng; |
| 355 | TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Varied datasets, metrics, and tampering configurations make it difficult to compare safety, utility, and robustness across different models and defenses. To address this, we introduce TamperBench, the first unified framework to systematically evaluate the tamper resistance of LLMs. |
Saad Hossain; Tom Tseng; Punya Syon Pandey; Samanvay Vajpayee; Matthew Kowal; Nayeema Nonta; Samuel Simko; Stephen Casper; Zhijing Jin; Kellin Pelrine; Sirisha Rambhatla; |
| 356 | Taming Update Drift in Asynchronous Federated Learning Via Orthogonal Calibration Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose OrthoFL, an orthogonal calibration framework that decouples global and local learning progress to reduce interference. |
Jiayun Zhang; Shuheng Li; Haiyu Huang; Xiaofan Yu; Chenyang An; Rajesh K. Gupta; Jingbo Shang; |
| 357 | MedDreamer: Model-Based Reinforcement Learning with Latent Imagination on Complex EHRs for Clinical Decision Support Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: They are also predominantly model-free and largely depend on retrospective data, which could lead to insufficient exploration and bias by historical behaviors. To address these limitations, we propose medDreamer, a novel model-based reinforcement learning framework for personalized treatment recommendation. |
Qianyi Xu; Gousia Habib; Feng Wu; Dilruk Perera; Mengling Feng; |
| 358 | FilDeep: Learning Large Deformations of Elastic-Plastic Solids with Multi-Fidelity Data Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: During the dataset construction process, a dilemma stands between data quantity and data accuracy, leading to suboptimal performance in the DL models. To address this challenge, we focus on a representative application of large deformations, the stretch bending problem, and propose FilDeep, a Fidelity-based Deep Learning framework for large Deformation of elastic-plastic solids. |
Jianheng Tang; Shilong Tao; Zhe Feng; Haonan Sun; Menglu Wang; Zhanxing Zhu; Yunhuai Liu; |
| 359 | Structure-Aware Abstraction of Hierarchical Time Series Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a novel problem of hierarchical time series abstraction (HTSA), which seeks a small set of structure-aware subseries that jointly capture temporal dynamics and hierarchical organization. |
Yihan Wu; Xuliang Zhu; Guozhong Li; Kai Wang; Xuemin Lin; |
| 360 | ScTranslation: A Comprehensive Benchmark for Single-Cell Multi-Omics Modality Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Despite the development of translation models, there is still a lack of systematic benchmark evaluation in terms of datasets, evaluation metrics, and influencing factors. To address this, we present scTranslation, a comprehensive benchmark for single-cell multi-omics modality translation tasks. |
Jiabei Cheng; Jingbo Zhou; Jun Xia; Changkai Li; Zhen Lei; Chang Yu; Stan Z. Li; |
| 361 | Hierarchical Reinforcement Learning for Cooperative Air-Ground Delivery in Urban System Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, effective dispatching in such heterogeneous systems faces two critical challenges: i) the heterogeneity between flight and road dynamics, ii) the scalability bottleneck raised by the exponential decision variables in large-scale fleets. To address these challenges, we propose HRL4AG, a Hierarchical Reinforcement Learning framework for cooperative Air-Ground delivery. |
Songxin Lei; Chunming Ma; Haomin Wen; Yexin Li; Lizhenghe Chen; Qianyu Yang; Fugee Tsung; Lei Chen; Sijie Ruan; Yuxuan Liang; |
| 362 | OceanVerse: Evaluable 4D Ocean Element Reconstruction Dataset Under Realistic Sparsity Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, fragmented data and interdisciplinary differences create barriers to the availability of AI-ready open data, further hindering ML practitioners from designing specialized models. To solve this problem, we present the first oceanic 4D sparse observation reconstruction dataset, named OceanVerse. |
Bin Lu; Jingjing Shen; Ze Zhao; Jianping Zhou; Haonan Qi; Luyu Han; Xiaoying Gan; Meng Jin; Lei Zhou; Luoyi Fu; Xinbing Wang; Chenghu Zhou; |
| 363 | Holographic Quantum Transformer: A Generalist Neuro-Symbolic Architecture for Solving Frustrated Systems Via Generative Attention Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce the Holographic Quantum Transformer (HQT), a physics-inspired generative architecture that leverages global self-attention to resolve non-local entanglement patterns. |
Xingran Guo; Tiaojie Xiao; Jie Liu; Keqin Li; |
| 364 | Scaling Agentic Capabilities Via Grounded Interaction Synthesis Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce Grounded Agentic Interaction Synthesis (GAIS), a framework that automates the scalable construction of diverse environments and complex tasks via a two-phase grounding mechanism. |
Wenhang Shi; Jinhao Dong; Yiren Chen; Zhe Zhao; Shuqing Bian; Wei Lu; Xiaoyong Du; |
| 365 | FLASH: Fast Generative Retrieval Via Autoregressive Semantic Hashing with Provably Distance Bounds Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose Flash (Fast Generative Retrieval via Autoregressive Semantic Hashing), a framework that integrates random orthogonal projection hashing (ROPH) with autoregressive hash code generation. |
Yifei Zhang; Hao Zhu; Haoran Shi; Yanyu Chen; Xiaolin Han; Yupei Zhang; Lingyun Song; Wenxuan Wang; Chao Zhou; Xuequn Shang; Piotr Koniusz; |
| 366 | When Gradient Boosting Meets Adapter: Exploring Weak Learners for Parameter-Efficient Fine-tuning of LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose eXtreme Gradient Boosting LoRA (XGBLoRA), a novel framework grounded in gradient boosting theory. |
Yifei Zhang; Hao Zhu; Haoran Shi; Junhao Dong; Lingyun Song; Xiaolin Han; Yanyu Chen; Wenxuan Wang; Han Yu; Xuequn Shang; Piotr Koniusz; |
| 367 | FireSentry: A Multi-Modal Spatio-temporal Benchmark Dataset for Fine-Grained Wildfire Spread Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing research predominantly focuses on coarse spatiotemporal scales and relies on low-resolution satellite data, capturing only macroscopic fire states while fundamentally constraining high-precision localized fire dynamics modeling capabilities. To bridge this gap, we present FireSentry, a provincial-scale multi-modal wildfire dataset characterized by sub-meter spatial and sub-second temporal resolution. |
Nan Zhou; Huandong Wang; Jiahao Li; Han Li; Yali Song; Qiuhua Wang; Yong Li; Xinlei Chen; |
| 368 | Structured Inductive Bias for Multi-timescale Knowledge Tracing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This architectural bias overlooks the hierarchical and co-evolutionary nature of learning dynamics, often leading to degraded generalization under limited learning evidence. To address this limitation, we propose Frequency-aware Structured Knowledge Tracing (FSKT), which introduces Experiential Learning Theory (ELT) as a structured inductive bias to explicitly model the co-evolution of multi-timescale cognitive dynamics. |
Xinjia Ou; Tao Huang; Shengze Hu; Huali Yang; Zhuoran Xu; Jing Geng; Yuxia Chen; Junjie Hu; |
| 369 | UniLLM: A Unified Large Language Model for Multi?Modal Urban Dynamics Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose UniLLM, a unified large language model for multi-modal urban dynamics prediction. |
Yuhang Liu; Yingxue Zhang; Xin Zhang; Yanhua Li; Jun Luo; |
| 370 | OneLive: Dynamically Unified Generative Framework for Live-Streaming Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, the inherent complexity of live-streaming prevents the direct transfer of these methods to live-streaming scenario, where continuously evolving content, limited lifecycles, strict real-time constraints, and heterogeneous multi-objectives introduce unique challenges that invalidate static tokenization and conventional model framework. To address these issues, we propose OneLive, a dynamically unified generative recommendation framework tailored for live-streaming scenario. |
Shen Wang; Yusheng Huang; Ruochen Yang; Shuang Wen; Pengbo Xu; Jiangxia Cao; Yueyang Liu; Kuo Cai; Chengcheng Guo; Shiyao Wang; Xinchen Luo; Qiang Luo; Ruiming Tang; Shuang Yang; Zhaojie Liu; |
| 371 | Speak-to-Structure: Evaluating LLMs in Open-domain Natural Language-Driven Molecule Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing datasets and benchmarks for molecule-text alignment are predominantly built on one-to-one mappings, measuring LLMs’ ability to retrieve a single, pre-defined answer, rather than their creative potential to generate diverse, yet equally valid, molecular candidates. To address this critical gap, we propose Speak-to-Structure (S2-Bench), the first benchmark to evaluate LLMs in open-domain natural language-driven molecule generation. |
Jiatong Li; Junxian Li; Weida Wang; Yunqing Liu; Changmeng Zheng; Yatao Bian; Dongzhan Zhou; Xiao-Yong Wei; Qing Li; |
| 372 | Benchmarking LLM Agents on Real-World Biological Database Curation for Data-Driven Scientific Discovery Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While LLM-based agents have catalyzed progress in downstream scientific modeling, their potential to automate the critical upstream challenge of database curation remains largely untapped. To bridge this gap, we introduce BioDataLab, a rigorous benchmark comprising 100 tasks meticulously derived from 57 high-impact database publications. |
Jiaxian Yan; Xi Fang; Jintao Zhu; Chenmin Wu; Yuhang Yang; Chenxi Du; Meijing Fang; Kai Zhang; Zaixi Zhang; Qi Liu; |
| 373 | CoPack: Collaborate Simulation and Reality for Robot Packing Learning in Real-world and Physical Engine Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, a simulation-to-reality gap persists due to dynamic variations in physical properties of real-world objects, such as various friction coefficients, elasticity, and non-uniform weight distributions. To bridge this gap, we propose a hybrid RL framework that collaborates with physical simulation with real-world data feedback. |
Lidi Zhang; Han Wu; Liyu Zhang; Ruofeng Liu; Haotian Wang; Chao Li; Desheng Zhang; Yunhuai Liu; Tian He; |
| 374 | CAAD: Causality-Aware Multivariate Time Series Anomaly Detection Via Multi-Scale Alignment and Structural Causal Consistency Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a novel framework (CAAD) that reframes anomaly detection as the continuous verification of Granger causality consistency through exogenous variables. |
Xin Wang; Yunshi Wen; Yanan He; Haotian Xu; Youlan Zhao; Michel Ferreira Cardia Haddad; Tengfei Ma; |
| 375 | D3-Subsidy: Online and Sequential Driver Subsidy Decision-Making for Large-Scale Ride-Hailing Market Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: These requirements rule out expensive per-order optimization, calling for a forward-looking, constraint-aware city-level controller for online sequential decision making. To meet these requirements, we introduce D3-Subsidy (Dynamic Driver-side Diffusion-based Subsidy), a hierarchical diffusion-based framework for deployable city-wide subsidy control. |
Taijie Chen; Rui Su; Siyuan Feng; Laoming Zhang; Hongyang Zhang; Haijiao Wang; Zhaofeng Ma; Jintao Ke; Li Ma; |
| 376 | Rec2: Embedding Table Reconstruction for Deep Recommender Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: As a result, they fail to fully exploit the potential of feature fields and their interactions. To address this limitation, we propose the Rec2 framework (Reconstruction for Recommender Systems), which aims to optimize the organization of embedding tables by efficiently determining which features should be split or aggregated. |
Xianquan Wang; Zhaocheng Du; Song-Li Wu; Zirui Liu; Haotian Zhang; Jintao Zhang; Jieming Zhu; Shuai Wang; Kai Zhang; |
| 377 | Q-Regularized Generative Auto-Bidding: From Suboptimal Trajectories to Optimal Policies Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: The suboptimal trajectories further exacerbate the difficulty of policy learning. To address these challenges, we proposes QGA, a novel Q-value regularized Generative Auto-bidding method. |
Mingming Zhang; Na Li; Feiqing Zhuang; Hongyang Zheng; Jiangbing Zhou; Wuyin Wang; Shengjie Sun; Xiaowei Chen; Junxiong Zhu; Lixin Zou; Chenliang Li; |
| 378 | Aligning Large Language Models with Searcher Preferences Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce SearchLLM, the first large language model (LLM) for open-ended generative search. |
Wei Wu; Peilun Zhou; Liyi Chen; Qimeng Wang; Chengqiang Lu; Yan Gao; Yi Wu; Yao Hu; Hui Xiong; |
| 379 | Scalable and Traceable Joint Uplift Modeling for Multi-Lever Online Marketing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, most existing uplift models focus primarily on single-category incentives; a straightforward extension of these models to multi-category scenarios leads to an explosion in parameter scale and a high risk of overfitting. To address this problem, this paper proposes a network named Multi-treatment Decomposable Low-Rank Interaction (M-DLRI). |
Zhe Wang; Rui Wang; Ziyu Guan; Yaming Yang; Bin Tong; Wei Zhao; Guan Wang; |
| 380 | Beyond Knowledge to Agency: Evaluating Expertise, Autonomy, and Integrity in Finance with CNFinBench Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing benchmarks focus on rule-based QA, lacking agentic execution modeling, overlooking compliance drift in adversarial interactions, and relying on binary safety metrics that fail to capture behavioral degradation. To bridge these gaps, we present CNFinBench, a comprehensive benchmark spanning 29 subtasks grounded in the triad of expertise, autonomy, and integrity. |
Jinru Ding; Chao Ding; Yidong Jiang; Wenrao Pang; Boyi Xiao; Zhiqiang Liu; Jiayuan Chen; Yun Zhong; Tiantian Yuan; Junming Guan; Dawei Cheng; Jie Xu; |
| 381 | Pick Up Where You Left Off: An Efficient Solution for Continuous Vector Similarity Search Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While recent efforts attempt to reuse prior results, they either sacrifice accuracy through semantic caching or yield only marginal efficiency gains. To address this, we propose Reuse, an end-to-end framework that decomposes CVSS into two synergistic components: (1) Reuse Trigger that decides when to reuse prior search results, and (2) Reuse Searcher that addresses how to reuse them effectively. |
Zhuanglin Zheng; Yuxiang Zeng; Yunzhen Chi; Yongxin Tong; |
| 382 | PathCRF: Ball-Free Soccer Event Detection Via Possession Path Inference from Player Trajectories Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: As a result, comprehensive data collection in soccer is largely confined to top-tier competitions, limiting the broader adoption of data-driven analysis in this domain. To address this challenge, this paper proposes PathCRF, a framework for detecting on-ball soccer events using only player tracking data. |
Hyunsung Kim; Kunhee Lee; Sangwoo Seo; Sang-Ki Ko; Jinsung Yoon; Chanyoung Park; |
| 383 | DisCo: Diffusion-guided Unbiased Discriminative Learning for Unsupervised Graph Domain Adaptation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Recent approaches usually utilize graph contrastive learning and pseudo-labeling to learn from unlabeled target data, which could introduce potential biased representations and supervision of target graphs resulting from serious shifts across two domains. Towards this end, we propose a novel framework named Diffusion-guided Unbiased Discriminative Learning (DisCo) for unsupervised graph domain adaptation. |
Haodong Zhang; Tao Ren; Changhu Wang; Yifan Wang; Wei Ju; Huaizhi Tang; Junyu Luo; Zimo Wang; Ziyue Qiao; Xian-Sheng Hua; Xiao Luo; |
| 384 | DTBench: A Synthetic Benchmark for Document-to-Table Extraction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Based on this approach, we present DTBench, a synthetic benchmark that adopts a proposed two-level taxonomy of Doc2Table capabilities, covering 5 major categories and 13 subcategories. |
Yuxiang Guo; Zhuoran Du; Nan Tang; Kezheng Tang; Congcong Ge; Yunjun Gao; |
| 385 | SurveyReview: A Reviewer-Aligned Benchmark for Survey Evaluators Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing approaches largely rely on off-the-shelf LLM-as-a-judge methods without systematic alignment to human reviewers, and there remains a lack of systematic frameworks for quantifying alignment with human reviewers. To address this gap, we propose SurveyReview, a reviewer-aligned, multi-dimensional benchmark and dataset for survey evaluation. |
Yuheng Zhang; Yuanchun Wang; Fanjin Zhang; Ruyu Zhao; Juanzi Li; Jie Tang; Jing Zhang; |
| 386 | Semantic Association Vs. Position: Which Information Do Attention Heads Prefer? Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This raises a fundamental interpretability question: Which does each attention head relatively prefer, SAI or PI? To address this question, based on theoretical analysis and derivations, we propose a unified relative-preference measurement method. |
Mengwei Wang; Simin Niu; Sensen Zhang; Hanyu Wang; Shichao Song; Zhiqiang Yin; Jiawei Yang; Xun Liang; |
| 387 | SL-BiLEM: Structured Learnable Behavior-in-the-Loop Epidemic Modeling for Forecasting and Policy Evaluation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose SL-BiLEM (Structured Learnable Behavior-in-the-Loop Epidemic Model), leveraging physical constraints as regularization for robust extrapolation. |
Haochun Wang; Sendong Zhao; Jingbo Wang; Yanrui Du; Ting Liu; Bing Qin; |
| 388 | TF-SNO: Time-Frequency Gated Spectral Neural Operators for Learning Non-Stationary Partial Differential Equations Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While efficient in PDE solving, many spectral neural operators apply a shared spectral response across rollout stages, leading to mismatch with time-varying spectra in non-stationary systems. To address this issue, we propose Time-Frequency Gated Spectral Neural Operator (TF-SNO), a state-adaptive framework with learnable time-frequency gating inside spectral blocks. |
Yitian Zhou; Chaoning Zhang; Zhenzhen Huang; Haoxuan Yu; Jiaquan Zhang; Yiran Li; Fan Mo; Kuien Liu; Jie Zou; Caiyan Qin; Yang Yang; |
| 389 | CausalMoE: A Billion-Scale Multimodal Foundation Model for Granger Causal Discovery with Pattern-Routed Heterogeneous Experts Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose CausalMoE, a billion-scale multimodal Granger causal foundation model that explicitly models patch-level heterogeneity. |
Bo Liu; Di Dai; Jingwei Liu; Jiarui Jin; Xiaocheng Fang; Guangkun Nie; Hongyan Li; Shenda Hong; |
| 390 | Semantic-Symbolic Knowledge Consensus for Multilingual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose SeSyCo, a Semantic-Symbolic Knowledge Consensus framework. |
Yu Zhang; Ran Song; Xiaofei Gao; Shuting Jiang; Zhengtao Yu; |
| 391 | Distribution-Aware End-to-End Embedding for Streaming Numerical Features in Click-Through Rate Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we propose DAES, an end-to-end framework designed to tackle numerical feature embedding in streaming training scenarios by integrating distributional information with an adaptive modulation mechanism. |
Jiahao Liu; Hongji Ruan; Weimin Zhang; Ziye Tong; Derick Tang; Zhanpeng Zeng; Qinsong Zeng; Peng Zhang; Tun Lu; Ning Gu; |
| 392 | Towards Trustworthy Multimodal Moderation Via Policy-Aligned Reasoning and Hierarchical Labeling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, current approaches largely rely on noisy, label-driven learning, lacking alignment with moderation rules and producing opaque decisions that hinder human review. Therefore, we propose Hierarchical Guard (Hi-Guard), a multimodal moderation framework that introduces a new policy-aligned decision paradigm. |
Anqi Li; Wenwei Jin; Jintao Tong; Pengda Qin; Jiawei Li; Guo Lu; |
| 393 | CDRRM: Contrast-Driven Rubric Generation for Reliable and Interpretable Reward Modeling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While recent rubric-based approaches enhance evaluation transparency, they lack systematic quality control, yielding noisy and redundant criteria, failing to mitigate persistent biases (e.g., verbosity, position) in LLM evaluators, and creating a scalability-reliability trade-off. To address these limitations, we propose CDRRM (Contrast-Driven Rubric Reward Model), a framework built on a novel Contrast-then-Synthesis paradigm for high-quality rubric generation and guided preference judgment. |
Dengcan Liu; Fengkai Yang; Xiaohan Wang; Shurui Yan; Jiajun Chai; Jiahao Li; Yikun Ban; Zhendong Mao; Wei Lin; Guojun Yin; |
| 394 | Mitigating Neuro-Symbolic Reasoning Shortcuts with Data-Driven Knowledge Augmentation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Inspired by recent theories, we find that existing methods fail to address the reasoning shortcut issue when the knowledge base lacks sufficient complexity, highlighting their vulnerability in real-world applications. In this work, we present a novel method called DKA to address this issue. |
Yu-Feng Li; Xiao-Wen Yang; Wen-Da Wei; Jie-Jing Shao; Lan-Zhe Guo; |
| 395 | CLASS: Deep Partial Label Feature Selection with Cluster-Guided Disambiguation and Structured Sparsity Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Nevertheless, existing methods suffer from at least one of two issues, i.e., redundant features and the uncertainty of label disambiguation. To address these problems, we propose a unified and deep partial label feature selection method with CLuster-guided disAmbiguation and Structured Sparsity (CLASS), which simultaneously preserve discriminative features and promotes candidate label disambiguation by bidirectional optimization. |
Tingjin Luo; Mengyuan Tong; Qingyang Shu; Yueying Liu; Hao Zhou; Zhen Wang; |
| 396 | BioFlowBench: A Comprehensive Benchmark for Evaluating Bioinformatics Tool-use Capabilities of LLMs and Agents Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this study, we propose BioFlowBench, a comprehensive benchmark designed to shift from static knowledge assessment to dynamic execution evaluation in bioinformatics tool utilization. |
Yufei Hou; Jiajia Wang; Ke Xiang; Qingqing Long; Yuanchun Zhou; Zhen Meng; |
| 397 | UniEdit: A Graph-based MoE Alternative to Sequence Generation for Molecular Editing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, treating molecules as 1D text strings (SMILES) introduces significant challenges in controllability and structural validity. In this paper, we question whether sequence generation is truly optimal for this topological task. |
Jiajun Yu; Zhihao Wu; Yizhen Zheng; Shirui Pan; Jiajun Bu; Haishuai Wang; |
| 398 | TIDE: Static-Context Guided Prompt Retrieval for Flood Inundation Forecasting Under Missing Data Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, in practice, frequent data gaps arise from sensor outages, sparse observation networks, and uneven data infrastructure—especially in resource-constrained regions—posing a major challenge for flood forecasting. To address this issue, we propose TIDE, a static-context–guided prompt retrieval framework that leverages always-available hydro-environmental attributes and geomorphology as invariant anchors to recover missing evidence. |
Jianping Zhu; Weijia Zhang; Hao Liu; Bo Jin; Xiaopeng Wei; Hui Xiong; |
| 399 | ECHO: Adaptive Community Search Over Multimodal Graphs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, for the first time, we study the community search problem over multimodal graphs. |
Chengyang Luo; Zixing Ding; Qing Liu; Yifan Zhu; Yunjun Gao; |
| 400 | From Tokenizer Bias to Backbone Capability: A Controlled Study of LLMs for Time Series Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We observe that when trained and evaluated on small datasets, the Tokenizer–Detokenizer components often overfit to the specific data distribution, thereby masking the intrinsic predictive capability of the LLM backbone. To investigate the inherent potential of LLMs in this context, we design three models with identical architectures but distinct pre-training strategies. |
Xinyu Zhang; Shanshan Feng; Xutao Li; Kenghong Lin; Fan Li; Pengfei Jia; |
| 401 | TimeRadar: A Domain-Rotatable Foundation Model for Time Series Anomaly Detection Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This limitation arises because such abnormal patterns can closely resemble the regular patterns when presented in the same time/frequency domain. To address this issue, we introduce TimeRadar, an innovative TSFM built in a fractional time–frequency domain to support generalist TSAD across diverse unseen datasets. |
Hui He; Hezhe Qiao; Yutong Chen; Kun Yi; Guansong Pang; |
| 402 | GraphCliff: Short-Long Range Gating for Modeling Critical Activity Changes Caused By Subtle Molecular Differences Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our analysis shows that the embedding distances of conventional graph neural networks fail to reflect the activity differences, collapsing structurally similar yet functionally divergent molecules into nearly indistinguishable representations. To recover sensitivity to such local changes while preserving global molecular context, we propose GraphCliff, which integrates short- and long-range information at the node level through a locally conditioned gating mechanism. |
Hajung Kim; Jueon Park; Junseok Choe; Seungheun Baek; Hyeon Hwang; Jaewoo Kang; |
| 403 | Advanced Global Wildfire Activity Modeling with Hierarchical Graph ODE Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While deep learning has recently achieved significant breakthroughs in global weather forecasting, its potential for global wildfire behavior prediction remains underexplored. In this work, we reframe this problem and introduce the Hierarchical Graph ODE (HiGO), a novel framework designed to learn the multi-scale, continuous-time dynamics of wildfires. |
Fan Xu; Wei Gong; Hao Wu; Lilan Peng; Nan Wang; Qingsong Wen; Xian Wu; Kun Wang; Xibin Zhao; |
| 404 | Learning in The Right Subspace: Personalized Differential Private Federated Learning with Noise Filtering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Such uniform privacy configurations typically necessitate compliance with the most stringent budget, which not only leads to the wasteful underutilization of privacy budgets for certain clients but also compromises overall model utility. To address this limitation, we propose FedSPA, a Subspace Projection Aggregation personalized differential private Federated learning framework. |
Tianchi Liao; Xiaojun Deng; Lele Fu; Sheng Huang; Bowen Deng; Hong-Ning Dai; Chuan Chen; |
| 405 | Accelerated Coordinate Descent for Directed Densest Subgraph Discovery Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing DDS solutions often provide weaker theoretical guarantees. To tackle these issues, we present a theoretically efficient (1+ε) approximate DDS discovery algorithm in this paper. |
Luocheng Liang; Yingli Zhou; Yixiang Fang; |
| 406 | The Eminence in Shadow: Exploiting Feature Boundary Ambiguity for Robust Backdoor Attacks Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Influence function analysis further quantifies significant parameter shifts caused by these margin samples, with minimal impact on clean accuracy, formally grounding why such low poison rates suffice for efficacious attacks. Leveraging these insights, we propose Eminence, an explainable and robust black-box backdoor framework with provable theoretical guarantees and inherent stealth properties. |
Zhou Feng; Jiahao Chen; Chunyi Zhou; Yuwen Pu; Tianyu Du; Jinbao Li; Jianhai Chen; Shouling Ji; |
| 407 | U-EHR: A Self-Evolving EHR Agent with Step-Level Credit Assignment and UCB-Guided Memory Retrieval Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose U-EHR, a Unified EHR Agent with Retrospective Memory Evolution that enables continuous capability improvement through closed-loop experiential learning. |
Hao Wu; Zihan Wang; Ziyang Rao; Heyi Lin; Jinjing Zhu; Qianyi Cai; Yi Zhou; An Lin; Hao Wang; Hui Xiong; |
| 408 | MM-SpuBench: Towards Better Understanding of Spurious Biases in Multimodal LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, both the presence and severity of spurious biases in MLLMs remain poorly understood. In this work, we address this gap by analyzing the spurious biases in the multimodal setting and uncovering the specific inference-time data patterns that can manifest this problem. |
Wenqian Ye; Bohan Liu; Guangtao Zheng; Di Wang; Xu Cao; Yunsheng Ma; Bolin Lai; James M. Rehg; Aidong Zhang; |
| 409 | LLMSynthor: Macro-Aligned Micro-Records Synthesis with Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While Large Language Models (LLMs) can generate realistic micro-records using rich real-world priors learned from vast corpora, naive record-by-record sampling is inefficient and fails to enforce alignment with target macro-statistics. Given this, we propose LLMSynthor, a framework that transforms a pre-trained LLM into a macro-aware simulator capable of synthesizing realistic micro-records aligned with given macro-statistics. |
Yihong Tang; Menglin Kong; Junlin He; Tong Nie; Wei Ma; Lijun Sun; |
| 410 | LatentFlow: Discovering Latent Continuous Dynamics Across Channels for Multivariate Time Series Anomaly Detection Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose LatentFlow, a novel framework that treats channel dependency evolution as a latent continuous dynamic process. |
Lijun Sun; Shuai Zhang; Xin Xue; Lanhao Li; Haoyi Zhou; Jianxin Li; |
| 411 | MLB: A Scenario-Driven Benchmark for Evaluating Large Language Models in Clinical Applications Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce MLB, a comprehensive Medical LLM Benchmark that characterizes model capability from foundational knowledge to complex, scenario-driven clinical reasoning. |
Qing He; Dongsheng Bi; Jianrong Lu; Minghui Yang; Zixiao Chen; Jiacheng Lu; Jing Chen; Nannan Du; Xiao Cui; Sijing Wu; Peng Xiang; Yingying Hu; Yi Guo; Chunpu Li; Shaoyang Li; Zhuo Dong; Ming Jiang; Shuai Guo; Liyun Feng; Jin Peng; Zhou Yang; Han Ying; Jie Zheng; Yujie Yang; Jian Wang; Jinjie Gu; Junwei Liu; |
| 412 | Adaptive Momentum By Momentum for Deep Neural Network Training Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Motivated by the optimal heavy-ball momentum for quadratic objectives, this paper proposes a new adaptive momentum mechanism that reduces the burden of momentum tuning. |
Tao Sun; Huaming Ling; Zuoqiang Shi; Dongsheng Li; Bao Wang; |
| 413 | On Saddle Point Avoidance and Stationary Distribution of Sharpness-Aware Minimization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce three new theoretical results to enhance the understanding of (U)SAM. |
Tao Sun; Fan Jia; Bao Wang; |
| 414 | Generative Recommendation for Large-Scale Advertising Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a production-oriented generative recommender co-designed across architecture, learning, and serving, named GR4AD (Generative Recommendation for ADdvertising). |
Ben Xue; Dan Liu; Lixiang Wang; Mingjie Sun; Peng Wang; Pengfei Zhang; Shaoyun Shi; Tianyu Xu; Yunhao Sha; Zhiqiang Liu; Bo Kong; Bo Wang; Hang Yang; Jieting Xue; Junhao Wang; Shengyu Wang; Shuping Hui; Wencai Ye; Xiao Lin; Yongzhi Li; Yuhang Chen; Zhihui Yin; Quan Chen; Shiyang Wen; Wenjin Wu; Guorui Zhou; Changcheng Li; Peng Jiang; |
| 415 | MTGenRec: An Efficient Distributed Training System for Generative Recommendation Models in Meituan Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: As such, we introduce MTGenRec as an efficient and scalable system for GRM training. |
Yuxiang Wang; Chi Ma; Xiao Yan; Mincong Huang; Xiaoguang Li; Ruidong Han; Bin Yin; Shangyu Chen; Xiang Li; Fei Jiang; Lei Yu; Chuan Liu; Wei Lin; Haowei Han; Xiaokai Zhou; Bo Du; Jiawei Jiang; |
| 416 | PRBench: A Standardized Probabilistic Robustness Benchmark Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Thus, we introduce PRBench, the first benchmark dedicated to evaluating PR performance achieved by different robustness training methods. |
Yi Zhang; Zheng Wang; Zhen Chen; Wenjie Ruan; Qing Guo; Siddartha Khastgir; Carsten Maple; Xingyu Zhao; |
| 417 | From GPS Points to Travel Patterns: Flexible and Semantic Trajectory Generation with LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing methods fail to explicitly capture travel patterns and can only generate fixed-length trajectories under a single condition. To address these limitations, we propose HTP, which Hierarchically generates Travel patterns first and then generates GPS Points by using large language models (LLMs), rather than directly generating GPS points. |
Silin Zhou; Chenhao Wang; Yuntao Wen; Shuo Shang; Lisi Chen; Panos Kalnis; |
| 418 | LoRAShield: Data-Free Editing Alignment for Secure Personalized LoRA Sharing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, this ”share-and-play” ecosystem introduces critical but unnoticed risks: benign LoRAs can be weaponized by adversaries to generate harmful content (e.g., political, defamatory imagery), undermining creator rights and platform safety. To bridge this gap, we propose LoRAShield, the first data-free editing framework for securing LoRA models against misuse. |
Jiahao Chen; Junhao Li; Yiming Wang; Yong Yang; Yi Jiang; Chunyi Zhou; Qingming Li; Tianyu Du; Shouling Ji; |
| 419 | AnchorMoE: Interpretable Time Series Classification Via Anchor-Routed MoE Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, isolating the temporal segments that drive model predictions is challenging because discriminative signals in real-world time series are typically sparse, heterogeneous, and heavily obscured by background noise. This paper, therefore, proposes AnchorMoE, an interpretable-by-construction classification framework. |
Tao Xie; Zexi Tan; Haoyi Xiao; Mengke Li; Yiqun Zhang; Yang Lu; Cuie Yang; Yiu-ming Cheung; |
| 420 | FLaG: Fine-Grained Latent Grouping for Hallucination Detection Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we formulate hallucination detection as a mechanism-aware evidence aggregation problem, where diverse representation- and token-level signals must be interpreted under multiple latent explanations. |
Wentao Ye; Liyao Li; Zhiqing Xiao; Muzhi Zhu; Jiaqi Hu; Zhanming Shen; Xiaomeng Hu; Sean Du; Haobo Wang; |
| 421 | SkillTracer: Structural Failure Attribution and Refinement of Agentic Skills in Long-Horizon Web Tasks Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce SkillTracer, a framework that represents skills as attributed plan graphs structured by hierarchical nodes and verifiable edge transitions, enabling programmatic verification of execution progress. |
Yuyang Li; Yiran Dou; Jie-Jing Shao; Yueming Lyu; Ivor Tsang; Haiyan Yin; |
| 422 | G2LoRA: Gradient Orthogonal Low-Rank Adaptation Framework for Graph Continual Learning on Text-Attributed Graphs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we study graph continual learning for LLM-as-Aligner models on TAGs, with the goal of mitigating interference while promoting positive transfer across tasks. |
Yuhan Wang; Yibo Ding; Yutong Ye; Mufan Zhao; Wenbo Zhang; Ruijie Wang; Jianxin Li; |
| 423 | PEANuT: Parameter-Efficient Adaptation with Weight-aware Neural Tweakers Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose PEANuT, a novel PEFT framework that introduces weight-aware neural tweakers, compact neural modules that generate task-adaptive updates conditioned on frozen pre-trained weights. |
Yibo Zhong; Haoxiang Jiang; Lincan Li; Ryumei Nakada; Tianci Liu; Linjun Zhang; Huaxiu Yao; Haoyu Wang; |
| 424 | ITDR: An Instruction Tuning Dataset for Enhancing Large Language Models in Recommendations Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Large language models (LLMs) have demonstrated outstanding performance in natural language processing tasks. |
Zekun Liu; Xiaowen Huang; Jitao Sang; |
| 425 | Continual-GraphLLM: Dynamic Graph Large Language Model with Invariance Regularized Adaptive Multi-Scale Experts Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This motivates a largely unexplored problem of continual learning on DyTAGs, which aims to adapt to constantly evolving graph structural-textual patterns while retaining past knowledge, which imposes two challenges: 1) unlike common graphs, graph structure and textual semantics in emerging DyTAG patterns jointly evolve, requiring dynamic graph LLMs to adapt structure, text, and graph-text fusion simultaneously; and 2) updating dynamic graph LLMs to fit a new pattern may destroy the global graph-text fusion capabilities and bias the model towards recent local dynamics. To address these challenges, we propose a novel Continual Learning Dynamic Graph LLM framework (Continual-GraphLLM) to continually adapt to incoming patterns by routing them to experts specialized in similar past patterns, while mitigating the overwriting of previously learned patterns by assigning new experts to unseen patterns. |
Tianhang Wan; Xin Wang; Haibo Chen; Longtao Huang; Wenwu Zhu; |
| 426 | UniHam: A Large-Scale SOC-Complete Dataset and Benchmark for Hamiltonian Learning in Materials Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, progress toward general-purpose materials foundation models is limited by a data bottleneck: existing Hamiltonian datasets are typically small, lack structural diversity, and often omit essential relativistic physics such as spin–orbit coupling (SOC). We therefore construct UniHam, a large-scale Hamiltonian dataset and benchmark suite comprising 100,000+ DFT-computed complex-valued Hermitian Hamiltonians with full SOC, covering 72 elements and a wide range of crystal geometries and symmetries (spanning diverse lattice types and space-group families). |
Yuewen Huang; Pin Chen; Yutong Lu; |
| 427 | Beyond Independent Manipulation: Individual Fairness-aware Strategic Classification with Peer Imitation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This induces a mismatch between classical SC formulations and fairness-aware decision settings, where independent models no longer accurately characterize strategic manipulations. To address this issue, we introduce individual fairness-aware strategic classification (IFSC), a framework that models peer-driven manipulation arising from individual fairness, where agents imitate nearby positively decided peers to obtain favorable outcomes. |
Xinpeng Lv; Yunxin Mao; Renzhe Xu; Jinxuan Yang; Chunyuan Zheng; Yuanlong Chen; Wanrong Huang; Shaowu Yang; Wenjing Yang; Peng Cui; Xinwang Liu; Haotian Wang; |
| 428 | FlowPath: From Discrete Paths to Continuous Semantic Flows for Knowledge Graph Completion Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Traditional path-based methods formulate reasoning as a discrete multi-hop traversal, which suffers from exponential search space and error accumulation.In this paper, we propose FlowPath, which rethinks the reasoning process by transforming discrete symbolic paths into a continuous semantic flow in the latent space. |
Xin Song; Haiyan Liu; Ye Wang; Yuying Liu; Liqun Gao; Bin Zhou; |
| 429 | Breaking Robustness Barriers in Cognitive Diagnosis: A One-Shot Neural Architecture Search Perspective Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Furthermore, current cognitive diagnosis models(CDMs) rely heavily on researchers’ domain expertise for structural design, which fails to exhaustively explore architectural possibilities, thus leaving model architectures’ full potential untapped. To address this issue, we propose OSCD, an evolutionary multi-objective One-Shot neural architecture search method for Cognitive Diagnosis, designed to efficiently and robustly improve the model’s capability in assessing learner proficiency. |
Ziwen Wang; Shangshang Yang; Xiaoshan Yu; Haiping Ma; Xingyi Zhang; |
| 430 | MDL: A Unified Multi-Distribution Learner in Large-scale Industrial Recommendation Through Tokenization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Industrial recommender systems increasingly adopt multi-scenario learning (MSL) and multi-task learning (MTL) to handle diverse user interactions and contexts, but existing approaches suffer from two critical drawbacks: (1) underutilization of large-scale model parameters due to limited interaction with complex feature modules, and (2) difficulty in jointly modeling scenario and task information in a unified framework. To address these challenges, we propose a unified Multi-Distribution Learning (MDL) framework, inspired by the ”prompting” paradigm in large language models (LLMs). |
Shanlei Mu; Yuchen Jiang; Shikang Wu; Shiyong Hong; Tianmu Sha; Junjie Zhang; Jie Zhu; Zhe Chen; Zhe Wang; Jingjian Lin; |
| 431 | MSN: A Memory-based Sparse Activation Scaling Framework for Large-scale Industrial Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Recent sparse activation scaling methods, such as Sparse Mixture-of-Experts, reduce computation by activating only a subset of parameters, but still suffer from high memory access costs and limited personalization capacity due to the large size and small number of experts. To address these challenges, we propose MSN, a memory-based sparse activation scaling framework for recommendation models. |
Shikang Wu; Hui Lu; Jinqiu Jin; Zheng Chai; Shiyong Hong; Junjie Zhang; Shanlei Mu; Kaiyuan Ma; Tianyi Liu; Yuchao Zheng; Zhe Wang; Jingjian Lin; |
| 432 | CRAG-MM: Multi-modal Multi-turn Comprehensive RAG Benchmark Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While Multi-Modal Retrieval-Augmented Generation (MM-RAG) plays a key role in grounding these queries in factual knowledge, the field lacks a comprehensive benchmark tailored to the unique challenges of wearable, egocentric scenarios. To fill this gap, we present CRAG-MM, a Comprehensive RAG benchmark for Multi-modal Multi-turn conversations. |
Jiaqi Wang; Xiao Yang; Kai Sun; Parth Suresh; Sanat Sharma; Adam Czyzewski; Derek Andersen; Surya Appini; Arkav Banerjee; Sajal Choudhary; Shervin Ghasemlou; Ziqiang Guan; Akil Iyer; Haidar Khan; Lingkun Kong; Yuanhang Luo; Tiffany Ma; Zhen Qiao; Tammy Stark; David Tran; Wenfang Xu; Skyler Yeatman; Chen Zhou; Gunveer Gujral; Yinglong Xia; Seungwhan Moon; Nicolas Scheffer; Nirav Shah; Eun Chang; Yue Liu; Florian Metze; Zhaleh Feizollahi; Andrea Jessee; Mangesh Pujari; Ahmed Aly; Babak Damavandi; Rakesh Wanga; Anuj Kumar; Rohit Patel; Wen-tau Yih; Xin Luna Dong; |
| 433 | Effective and Robust Single-cell Cross-omics Annotation Via Vector-Quantized Autoencoders Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper presents a novel discrete representation learning based method for effective and robust cross-omics cell-type annotation, which is called scCoA-VQA — the abbreviation of single-cell Cross-omics Annotation via Vector-Quantized Autoencoders. |
Han Peng; Wuchao Liu; Yifang Cai; Wengen Li; Yichao Zhang; Jihong Guan; Shuigeng Zhou; |
| 434 | Flow Learners for PDEs: Toward A Physics-to-Physics Paradigm for Scientific Computing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We argue that the core issue is the abstraction used to train learned solvers. |
Yilong Dai; Shengyu Chen; Xiaowei Jia; Runlong Yu; |
| 435 | EmergentBridge: Improving Zero-Shot Cross-Modal Transfer in Unified Multimodal Embedding Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Addressing this sparse-pairing regime is therefore essential for scaling unified embedding systems to new tasks without curating exhaustive pairwise data. We propose EmergentBridge, an embedding-level bridging framework that improves performance on these unpaired pairs without requiring exhaustive pairwise supervision. |
Jincheng Xie; Xingchen Xiao; Runheng Liu; Zhongyi Huang; Yu Zheng; Heyan Huang; |
| 436 | Atomic Intent Reasoning: Bringing LLM Semantics to Industrial Cross-Domain Recommendations Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: \% Although large language models (LLMs) offer powerful semantic understanding and reasoning capabilities to alleviate semantic gap issues, their inference costs remain prohibitive under critical online inference latency constraints. To address these issues, this paper introduces AIR (Atomic Intent Reasoning), an LLM-driven cross-domain recommendation framework designed for industrial-grade deployment. |
Zhuohang Jiang; Yuxin Chen; Shijie Wang; Haohao Qu; Jindong Zhou; Wenqi Fan; Qing Li; Dongxu Liang; Jun Wang; |
| 437 | Search-on-Graph: Iterative Informed Navigation for Large Language Model Reasoning on Knowledge Graphs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose Search-on-Graph (SoG), a method that strengthens the connection between path selection and reasoning by having the LLM itself select which relations to follow, informed by both the available KG structure and the complete reasoning history. |
Jia Ao Sun; Hao Yu; Fabrizio Gotti; Fengran Mo; Yihong Wu; Yuchen Hui; Zhan Su; Lingfeng Xiao; Jian-Yun Nie; |
| 438 | ProEx: A Unified Framework Leveraging Large Language Model with Profile Extrapolation for Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Consequently, an intuitive solution is to generate multiple profiles for each user (or item), each reflecting a distinct aspect of their characteristics. In light of this, we propose a unified recommendation framework with multi-faceted profile extrapolation (ProEx) in this paper. |
Yi Zhang; Yiwen Zhang; Yu Wang; Tong Chen; Hongzhi Yin; |
| 439 | Unifying Behavior Modeling and Semantic Generation for Generative Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose OMG, a GR method that unifies behavior modeling and semantic generation to produce recommendations that seamlessly integrate both information. |
Binquan Wu; Xinbo Chen; Yicheng Luo; Yuhao Ke; Jingye Li; Kun Zeng; Qianli Ma; |
| 440 | Interest Entropy: Rethinking Contrastive Learning for Sequential Recommendation with Interest Uncertainty Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This approach can avoid harmful semantic discrepancy of positive pairs and reduce the effect of the semantic bias, leading to improved performance. |
Binquan Wu; Kun Zeng; Yicheng Luo; Junhao Zheng; Qianli Ma; |
| 441 | WISE: Hierarchical Worker Scheduling for Efficient Multi-Source Urban Delivery Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we explore a multi-source urban delivery scenario in which each worker can dynamically select the pickup location for assigned but unpicked-up orders from multiple candidates. |
Wenjun Lyu; Fangyu Li; Shanshan Wang; Yikang Zhang; Haotian Wang; Yunhuai Liu; Tian He; Desheng Zhang; |
| 442 | Sparse Additive Models for Domain Generalization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, feature representations from existing methods often exhibit weak interpretability. To bridge this gap, we propose Sparse Additive Domain Generalization (SpADG). |
Jiayi Wang; Han Li; |
| 443 | RepoMod-Bench: A Benchmark for Code Repository Modernization Via Implementation-Agnostic Testing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This visibility allows agents to ”cheat” via test-driven overfitting, while the manual process of porting internal unit tests to a new language remains unscalable and error-prone. We address these limitations by introducing a benchmarking framework for repository-level code modernization built on a novel implementation-agnostic evaluation paradigm. |
Xuefeng Li; Nir Ben-Israel; Yotam Raz; Belal Ahmed; Doron Serebro; Antoine Raux; |
| 444 | Physics-Informed Teleconnection-Aware Transformer for Global Subseasonal-to-Seasonal Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce TelePiT, a novel deep learning architecture that enhances global S2S forecasting through integrated multi-scale physics and teleconnection awareness. |
Tengfei Lyu; Weijia Zhang; Hao Liu; |
| 445 | Offline Policy Enhancement and Transfer By Combining Experimental and External One-Sided Treatment Data Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this article, we investigate a novel setting for offline policy enhancement and transfer that involves two distinct datasets: an experimental dataset and an external one-sided treatment dataset. |
Xueqing Liu; Qinwei Yang; Zhiyu Hao; Peng Wu; |
| 446 | MotRNA: Encoding RNA Motifs Via Explicit N-gram Memory Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While current RNA foundation models have revolutionized sequence modeling through Transformer architectures, they predominantly prioritize modeling global dependencies within the raw sequence. To address this limitation, we propose MotRNA, a motif-aware RNA language model integrating an Explicit N-gram Memory mechanism. |
Xiangyu Ji; Xin Wang; Yang Zhang; Yongxin Li; Penglin Ge; Zirui Chen; Shengming Zhang; |
| 447 | UrbanExpert: Task-Conditioned Multi-Modal Fusion Via Semantic Expert Routing for Urban Socioeconomic Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose UrbanExpert, a multi-task framework that explicitly conditions multi-modal fusion on task semantics while accommodating incomplete modality observations. |
Zechen Li; Hongwei Jia; Weiming Huang; Kai Zhao; Meng Chen; |
| 448 | Multi-View Urban Region Embedding Via Commonality-Specificity Disentanglement Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, these approaches often fail to effectively balance cross-view commonality modeling with the preservation of view-specific characteristics. To address this limitation, we propose ComSRE, a novel region embedding framework that explicitly disentangles shared and distinctive components in multi-view region representations. |
Zechen Li; Hongwei Jia; Kai Zhao; Weiming Huang; Meng Chen; |
| 449 | MiCU: End-to-End Smart Home Command Understanding with Large Language Model Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, while they perform well on precise utterances (e.g., turn on the bedroom light), they struggle with ambiguous or misaligned commands (e.g., make the bedroom cozy). Large language models (LLMs) generalize well across various domains and can outperform traditional rule-based systems on such tasks, but their effectiveness is often constrained by scarce domain-specific data, insufficient task-specific adaptation, and high computational costs. |
Haowei Han; Kexin Hu; Weiwei Cai; Debiao Zhang; Bin Qin; Yuxiang Wang; Jiawei Jiang; Xiao Yan; Bo Du; |
| 450 | Neuron-Anchored Rule Extraction for Large Language Models Via Contrastive Hierarchical Ablation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce MechaRule, a pipeline that grounds rule extraction in LLM circuits by localizing sparse agonist activations whose ablation disrupts rule-related behavior. |
Francesco Sovrano; Gabriele Dominici; Marc Langheinrich; |
| 451 | SBFRec: Semantic-Behavioral Fusion with Trajectory Smoothing for Generative Sequential Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose SBFRec, a Semantic-Behavioral Flow Matching framework for generative sequential recommendation. |
Rui Zhang; Chongyang He; Fengyun Li; |
| 452 | Spend Search Where It Pays: Value-Guided Structured Sampling and Optimization for Generative Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Conventional likelihood-dominated decoding (e.g., beam search) exhibits a myopic bias toward locally probable prefixes, which causes two critical failures: (1) insufficient exploration, where high-reward items in low-probability branches are prematurely pruned and rarely sampled, and (2) advantage compression, where trajectories sharing high-probability prefixes receive highly correlated rewards with low within-group variance, yielding a weak comparative signal for RL. To address these challenges, we propose V-STAR, a Value-guided Sampling and Tree-structured Advantage Reinforcement framework. |
Jie Jiang; Yangru Huang; Zeyu Wang; Changping Wang; Yuling Xiong; Jun Zhang; Huan Yu; |
| 453 | S-GRec: Personalized Semantic-Aware Generative Recommendation with Asymmetric Advantage Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper presents S-GRec, a semantic-aware framework that decouples an online lightweight generator from an offline LLM-based semantic judge for train-time supervision. |
Jie Jiang; Hongbo Tang; Wenjie Wu; Yangru Huang; ZhenMao Li; Qian Li; Changping Wang; Jun Zhang; Huan Yu; |
| 454 | Online Learning for Wild Streaming Data with Delayed Feedback Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we propose an OLWDF algorithm by extracting geometric information from wild streaming data to mitigate the negative impact of delayed feedback. |
Yulin Wang; Yi He; Dianlong You; Di Wu; |
| 455 | Sparsity Curse: Understanding RLVR Model Parameter Space from Model Merging Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Unlike SFT models that converge to shared, flat basins and merge naturally, RLVR models suffer severe degradation under standard merging methods. Through systematic empirical analysis of the update geometry, we characterize the mechanisms behind this failure and propose Sensitivity-aware Resolving Merging (SAR-Merging), a merging recipe tailored for the unique structure of RLVR parameter spaces. |
Chenrui Wu; Zexi Li; Jiajun Bu; Jiangchuan Liu; Haishuai Wang; |
| 456 | Native Hierarchical and Compositional Representations with Subspace Embeddings Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a fundamentally different approach: representing concepts as linear subspaces. |
Gabriel Moreira; Zita Marinho; Manuel Marques; Jo{\~a}o Paulo Costeira; Chenyan Xiong; |
| 457 | LISRec: Modeling User Preferences with Learned Item Shortcuts for Sequential Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: User-item interaction histories are pivotal for sequential recommendation systems but often include noise, such as unintended clicks or actions that fail to reflect genuine user preferences. To address this, we propose Learned Item Shortcuts for Sequential Recommendation (LISRec), a novel framework that explicitly captures stable preferences by extracting personalized semantic shortcuts from historical interactions. |
Haidong Xin; Zhenghao Liu; Sen Mei; Yukun Yan; Shi Yu; Shuo Wang; Zulong Chen; Yu Gu; Ge Yu; Chenyan Xiong; |
| 458 | Structure Is All You Need to Reuse: Accelerating GraphRAG Via Meta-Structure-Aware KV Caching Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose MetaKV, the first structure-aware KV caching mechanism that explicitly decouples static structural logic from dynamic entity semantics in GraphRAG inference. |
Ruikun Luo; Changwei Gu; Jing Yang; Hongming Liang; Yuan Gao; Xiaofen Wang; Qiang He; Song Wu; Laurence T. Yang; Hai Jin; |
| 459 | Spatiotemporal Graph Learning with Direct Volumetric Information Passing and Feature Enhancement Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a dual-module framework, Cell-embedded and Feature-enhanced Graph Neural Network (CeFeGNN), for learning spatiotemporal dynamics. |
Yuan Mi; Qi Wang; Xueqin Hu; Yike Guo; Ji-Rong Wen; Yang Liu; Hao Sun; |
| 460 | Certified Signed Graph Unlearning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To fill this research gap, we propose Certified Signed Graph Unlearning (CSGU), which leverages the sociological principles underlying signed graphs, providing provable privacy guarantees while maintaining model utility. |
Junpeng Zhao; Lin Li; Yu Yang; Kaixi Hu; Kaize Shi; Jingling Yuan; Guandong Xu; |
| 461 | PrePrompt: Predictive Prompting for Class Incremental Learning Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we propose Predictive Prompting (PrePrompt), a novel CIL framework that circumvents correlation-based limitations by leveraging the inherent classification ability of pre-trained models to predict task-specific prompts. |
Libo Huang; Xiangqi Li; Jiarui Zhao; Zhulin An; Chuanguang Yang; Boyu Diao; Fei Wang; Yan Zeng; Zhifeng Hao; Yongjun Xu; |
| 462 | LLM-based Few-Shot Early Rumor Detection with Imitation Agent Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose a novel EARD framework that combines an autonomous agent and an LLM-based detection model, where the agent acts as a reliable decision-maker for early time point determination, while the LLM serves as a powerful rumor detector. |
Fengzhu Zeng; Qian Shao; Ling Cheng; Wei Gao; Shih-Fen Cheng; Jing Ma; Cheng Niu; |
| 463 | MOBI: Monolithic Graph-Language Modeling Beyond Modality Interference Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This separation fails to strike an effective balance between modality fusion and interference, exhibiting limited cross-modal interaction while leaving interference between modalities largely unresolved. To tackle the above challenges, we propose MOBI (Monolithic Graph-Language Modeling Beyond Modality Interference), a monolithic graph-language model that unifies graph encoding and language decoding within a single backbone for end-to-end graph-text fusion. |
Zhiyao Zhou; Yugang Ji; Ziwen Xu; Zhuonan Zheng; Sheng Zhou; Weigao Wen; Jiawei Chen; Ming Gu; Chun Chen; Can Wang; |
| 464 | M2NO: An Efficient Multi-Resolution Operator Framework for Dynamic Multi-Scale PDE Solvers Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Solving high-dimensional partial differential equations (PDEs) efficiently requires handling multi-scale features across varying resolutions. To address this challenge, we present the Multiwavelet-based Multigrid Neural Operator (M2NO), a deep learning framework that integrates a multigrid structure with predefined multiwavelet spaces. |
Zhihao Li; Zhilu Lai; Xiaobo Zhang; Wei Wang; |
| 465 | Revisiting Redundancy in Diffusion Transformers: A Temporal-Spatial Joint Caching Strategy for Efficient Sampling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: More crucially, we identify a previously underexplored form of efficiency, namely spatial redundancy, characterized by high similarity between adjacent transformer blocks within the same timestep. Motivated by this dual-dimensional redundancy, we propose Temporal-Spatial Joint Cache, a training-free inference acceleration strategy that dynamically determines optimal reuse operations across temporal and spatial dimensions. |
Chenxi Du; Yongheng Deng; Ju Ren; Yaoxue Zhang; |
| 466 | PROBE: VLM-Guided Discrete Structural Reconfiguration for Customized and Efficient Video Retrieval Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we propose an efficient VLM-guided video retrieval paradigm PROBE that leverages a frozen vision–language model (VLM) to inject rich semantic structure into a reusable hash index. |
Yiyang Gu; Kaili Liu; Tao Zhe; Binqi Chen; Jiayue Fan; Junwei Yang; Zequn Liu; Zhiping Xiao; Chong Chen; Xiao Luo; Xian-Sheng Hua; Ming Zhang; |
| 467 | Clarify-Then-Search: A Clarification Benchmark for Deep Search with End-to-End Nugget Restoration Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We run a deep-search backbone (we use WebDancer in this study) once per q* to archive evidence and construct a static golden reference as weighted, evidence-grounded nuggets with traceable source identifiers. |
Deqiang Huang; Jingbo Zhou; Xinjiang Lu; Tong Xu; Hua Wu; Enhong Chen; |
| 468 | Thought-Augmented Planning for LLM-Powered Interactive Recommender Agent Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, due to limited planning and generalization capabilities, existing formulations of LLM-powered interactive recommender agents struggle to effectively address diverse and complex user intents, such as intuitive, unrefined, or occasionally ambiguous requests. To tackle this challenge, we propose a novel ThoughtAugmented Interactive Recommender Agent system (TAIRA) that addresses complex user intents through distilled thought patterns. |
Haocheng Yu; Yaxiong Wu; Hao Wang; Wei Guo; Yong Liu; Yawen Li; Yuyang Ye; Junping Du; Enhong Chen; |
| 469 | Uncertainty-Aware Planning for Disambiguating User Intent in Interactive LLM Agents: Application to Baidu Maps Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While generating clarification questions can mitigate this issue, existing methods—which rely on prompt-based LLM assessments or supervised fine-tuning (SFT) of LLMs with limited annotated data—struggle to reliably determine when clarification is necessary, resulting in cold-start issues and reduced adaptability. To address this gap, we propose an uncertainty-aware dynamic planning framework for intent disambiguation in interactive agent systems, exemplified by Baidu Maps. |
Deqiang Huang; Xinjiang Lu; Jingbo Zhou; Nijia Lu; Fuxin Li; Bo Hong; Chuanming Zhang; Tong Xu; Enhong Chen; |
| 470 | Dynamic Discard Deep Learning for Rice Yield Prediction on Mixed-Accuracy Datasets Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose Dynamic Discard Deep Learning (DDL), a framework that combines soft probabilistic discard with phased training control and adaptive task weighting. |
He Xu; Xinge Zhao; Zhixuan Che; Zihan Liu; Yuxi Xie; Jinrong Shen; Dan Xia; Yongqiu Xia; |
| 471 | VQFlow: A Benchmark Dataset for Encrypted Video Streaming Traffic Across QoS Configurations Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present VQFlow, a large-scale and publicly available dataset that systematically captures encrypted video streaming traffic under controlled variations of key QoS parameters, including resolution, frame rate, and bitrate control policies. |
Ziming Zhao; Zhaoxuan Li; Tingting Li; Fan Zhang; |
| 472 | Enhancing Biomedical AI Foundations: Genomic Literature Knowledge Base Boosts LLMs’ Mastery of Biomedical Literature Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Peered-reviewed literature provides reliable biomedical knowledge, which is essential for large language models (LLMs) in solving complex biomedical problems. However, how … |
Yuanhao Huang; Zhaowei Han; Kevin Chang; Tiancheng Jiao; Jie Liu; |
| 473 | SpectrumWorld: Artificial Intelligence Foundation for Spectroscopy Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Deep learning holds immense promise for spectroscopy, yet research and evaluation in this emerging field often lack standardized formulations. To address this issue, we introduce SpectrumWorld, a unified infrastructure for AI-driven spectroscopy. |
Zhuo Yang; Jiaqing Xie; Shuaike Shen; Daolang Wang; Yeyun Chen; Ben Gao; Shuzhou Sun; Biqing Qi; Dongzhan Zhou; LEI BAI; Linjiang Chen; Shufei Zhang; Qinying Gu; Jun Jiang; Tianfan Fu; Yuqiang Li; |
| 474 | {GS-Fuse}: Granger-Supervised Gated Fusion and Multi-Granularity Alignment for Event-Driven Financial Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose GS-Fuse, a multimodal event-based forecasting framework that employs (i) a Granger-supervised, causal-aware gated fusion module, which learns to open toward event text only when it provides incremental predictive value beyond historical prices, and (ii) a multi-granularity alignment mechanism that jointly aligns high-level event representations and fine-grained textual cues with future market trajectories. |
Yang Zhang; En Chun; Ziyun Mao; Yulu Wu; Jun Wang; |
| 475 | Deep Doubly Debiased Longitudinal Effect Estimation with ICE G-Computation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose D3-Net, a framework that mitigates error propagation in ICE training and then applies a robust final correction. |
Wenxin Chen; Weishen Pan; Kyra Gan; Fei Wang; |
| 476 | MOSIC: Model-Agnostic Optimal Subgroup Identification with Multi-Constraint for Improved Reliability Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a unified optimization framework that directly solves the primal constrained optimization problem to identify optimal subgroups. |
Wenxin Chen; Weishen Pan; Kyra Gan; Fei Wang; |
| 477 | Awaken The Giant: Activating LLMs Via Deep Model Guidance for Boundary-aware Medication Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In contrast, deep models offer fine-grained probability outputs but lack contextual reasoning needed for complex boundary cases. To address this, we propose a boundary-aware medication recommendation framework (GiantMed) that activates the potential of LLM giant under deep model guidance. |
Hang Lv; Zixuan Guo; Yanchao Tan; Wanzi Shao; Hengyu Zhang; Carl Yang; |
| 478 | MTFM: A Scalable and Alignment-free Foundation Model for Industrial Recommendation in Meituan Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Industrial recommendation systems typically involve multiple scenarios, yet existing cross-domain (CDR) and multi-scenario (MSR) methods often require prohibitive resources and strict input alignment, limiting their extensibility. We propose MTFM (Meituan Foundation Model for Recommendation), a transformer-based framework that addresses these challenges. |
Xin Song; Zhilin Guan; Ruidong Han; Binghao Tang; Tianwen Chen; Bing Li; Zihao Li; Han Zhang; Fei Jiang; Qing Wang; Zikang Xu; Fengyi Li; Chunzhen Jing; Lei Yu; Wei Lin; |
| 479 | Discriminative Anchor Learning with Distribution Alignment for Multi-modal Remote Sensing Clustering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To address the problem, we proposed a discriminative anchor learning with distribution alignment for multi-modal RSI clustering. |
Yu Yun; Quanxue Gao; Yu Duan; |
| 480 | GREPO: A Benchmark for Graph Neural Networks on Repository-Level Bug Localization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Graph Neural Networks (GNNs) offer a promising alternative due to their ability to model complex, repository-wide dependencies; however, their application has been hindered by the lack of a dedicated benchmark. To address this gap, we introduce GREPO, the first GNN benchmark for repository-scale bug localization tasks. |
Juntong Wang; Libin Chen; Xiyuan Wang; Shijia Kang; Haotong Yang; Da Zheng; Muhan Zhang; |
| 481 | Caduceus: MoE Foundation Models for Unifying Biological and Natural Language Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Concretely, we introduce Caduceus, a family of MoE-enhanced foundation models built with a hierarchical pre-training paradigm to jointly integrate biological and natural language. |
Mingze Yin; Yiheng Zhu; Jialu Wu; Jian Ma; Hanjing Zhou; Mingyang Li; Yuhua Zhou; Jintai Chen; Tingjun Hou; Jieping Ye; Aimin Pan; |
| 482 | AdPilot: Towards Fully Autonomous Advertising Delivery Via Agentic Reinforcement Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present AdPilot, the first fully autonomous agent for end-to-end advertising delivery. |
Shuoshuo Sun; Qi He; Xiaoting Li; Ziyang Song; Shengqi Dai; Ruize Wang; Ying Cheng; Zhangbin Zhu; Lingling Yao; Lei Xiao; Haijie Gu; Jie Jiang; |
| 483 | Dual-Difficulty Curriculum Learning for Direct Preference Optimization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we reframe alignment difficulty as a two-dimensional space spanned by Prompt Complexity (PC) and Pairwise Distinguishability (PD), providing a more principled foundation for alignment. |
Mengyang Li; Haozhan Geng; Zhong Zhang; Shuang Liu; |
| 484 | LENS-SFL: Learning-Driven Contracts Framework for Personalized Split Federated Learning Under Strong Uncertainty Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose LENS-SFL, a learning-driven framework for personalized SFL under strong incomplete information. |
Jianfeng Lu; Yitian Huang; Yun Xin; Zhongbo Wu; Weigang Li; Guanghui Wen; |
| 485 | PrismFed: Joint Optimization Via Dynamic Bayesian Persuasion for Multi-Task Federated Learning Under Incomplete Information Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing approaches predominantly rely on indirect information completion or inference techniques, which are often unstable and insufficiently adaptive in time-varying environments, thereby limiting performance gains. To address these challenges and effectively incentivize client participation, we propose PrismFed, a joint optimization framework via dynamic Bayesian persuasion for multi-task federated learning under incomplete information. |
Jianfeng Lu; Shicheng Xie; Yun Xin; Shuqin Cao; Weigang Li; Guanghui Wen; |
| 486 | Explicit V.s. Implicit Memory: Exploring Multi-hop Complex Reasoning Over Personalized Information Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, in the real world, complex tasks often require multi-hop reasoning on a large amount of user information, which poses significant challenges for current memory approaches. To address this limitation, we propose the multi-hop personalized reasoning task to explore how different memory mechanisms perform in multi-hop reasoning over personalized information. |
Zeyu Zhang; Yang Zhang; Haoran Tan; Rui Li; Xu Chen; |
| 487 | General Protein Pretraining or Domain-Specific Designs? Benchmarking Protein Modeling on Realistic Applications Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce Protap, a comprehensive benchmark that systematically compares backbone architectures, pretraining strategies, and domain-specific models across diverse and realistic downstream protein applications. |
Shuo Yan; Yuliang Yan; Bin Ma; Chenao Li; Haochun Tang; Jiahua Lu; Minhua Lin; Yuyuan Feng; Enyan Dai; |
| 488 | A Serial Two-Stage Framework for Robust Multimodal Fake News Detection Via Adaptive Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Despite substantial progress, real-world deployment of multimodal fake news detection models remains constrained by an ”impossible triangle” of accuracy, inference efficiency, and robustness. To address these challenges, we propose DAR-Lite, a serial two-stage framework that rethinks the detection pipeline through explicit decoupling of representation denoising and contextual reasoning. |
Maolin Wang; Ziting Mai; Zichun Liu; Beining Bao; Hongyu Chen; Junjie Liu; Yunbo Zhang; Bingkun Zhao; Tianshuo Wei; Jian Liu; Chenbin Zhang; Haoran Yang; |
| 489 | Graph Neural Multilevel Preconditioners for Iterative Solvers Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose a Graph Neural Multilevel Preconditioner (GMP) that adopts an AMG hierarchy as a structural prior and learns smoothing, restriction, and interpolation operators in a unified framework. |
Zechen Zhang; Rui Peng Li; Yousef Saad; |
| 490 | The Forgetting-Learning Trade-off: Making Reinforcement Learning Work for Protein Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Reinforcement learning (RL) is increasingly applied to Protein Language Models (PLMs), yet its effectiveness varies across tasks, and standard metrics such as pass@k can rise even … |
Hanqun Cao; Hongrui Zhang; Junde Xu; Zhou Zhang; Lingdong Shen; Minghao Sun; Ge Liu; Jinbo Xu; Wu-Jun Li; Jinren Ni; Cesar de la Fuente-Nunez; Tianfan Fu; Shuting Jin; Pheng-Ann Heng; Fang Wu; |
| 491 | CORF-Net: Cross-Order Representation Fusion Network for Denoised Survey Response Modeling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Unfortunately, most existing recommendation models overlook the importance of capturing high-order feature interactions and their synergistic fusion with low-order features for complementary learning. To address these challenges, we propose a novel Cross-Order Representation Fusion Network (CORF-Net) and a corresponding two-phase denoising strategy. |
Haoze Wu; Jian Ding; Chenghui Yu; Bingfeng Deng; Hongyu Xiong; Kun Xu; |
| 492 | Beyond Linear Dynamics: Neural Bilinear Dynamical Models for Time Series Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing approaches that explicitly model system dynamics typically rely on linear assumptions or Koopman-based linearizations, which may inadequately capture complex nonlinear behaviors and lead to error accumulation in long-horizon prediction. To address this limitation, we propose the Neural Bilinear Dynamical Model (NBDM), which models nonlinear system dynamics through a bilinear latent dynamical formulation. |
Mengzhou Gao; Huangqian Yu; Pengfei Jiao; |
| 493 | Differential-Integral Neural Operator for Long-Term Turbulence Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose the Differential-Integral Neural Operator (DINO), a novel framework designed from a first-principles approach of operator decomposition. |
Hao Wu; Yuan Gao; Fan Xu; Fan Zhang; Qingsong Wen; Xiaomeng Huang; Xian Wu; |
| 494 | PCR-CA: Parallel Codebook Representations with Contrastive Alignment for Multiple-Category App Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose PCR-CA (Parallel Codebook Representations with Contrastive Alignment), an end-to-end framework for improved CTR (Click-through Rate) prediction. |
Bin Tan; Wangyao Ge; Yidi Wang; Xin Liu; Jeffrey Burtoft; Hao Fan; Hui Wang; |
| 495 | Orbit-Adaptive Zero-Shot Forecasting on Spatio-Temporal Graph Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Spatio-temporal graph forecasting is crucial for numerous real-world applications but often suffers from severe data scarcity in target domains, necessitating knowledge transfer from data-rich sources. In this work, we push this to the extreme by studying zero-shot spatio-temporal graph learning, where only the target graph topology is accessible and no temporal observations from the target domain are available at all. |
Yue Xu; Wenying Duan; Xiaoxi He; Shuai Ma; |
| 496 | Climber-Pilot: A Non-Myopic Generative Recommendation Model Towards Better Instruction-Following Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we present Climber-Pilot, a unified generative retrieval framework to address both limitations. |
Da Guo; Shijia Wang; Qiang Xiao; Yintao Ren; Weisheng Li; Songpei Xu; Ming Yue; Bin Huang; Guanlin Wu; Chuanjiang Luo; |
| 497 | Temporal Graph Prototype-conditioned Conformal Prediction for Fraud Detection Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Fraudulent interactions are often embedded in benign-dominated neighborhoods that dilute calibration signals, while extreme class imbalance leaves scarce labeled-fraud support in the calibration split and leads to overly conservative class-conditional thresholds. To address these issues, we propose ProtoCP, a conformal prediction framework for edge-level fraud detection on temporal graphs. |
Xudong Chen; Shengbo Gong; Lu Cheng; Wei Jin; |
| 498 | Caesar: Optimizing Federated Learning Via Low-deviation Compression Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To strike a delicate trade-off between model accuracy and traffic cost, we propose Caesar,, a novel FL framework with a low-deviation compression approach. |
Jiaming Yan; Jianchun Liu; Hongli Xu; Zhenguo Ma; Shilong Wang; |
| 499 | Collaborative Deterministic-Probabilistic Learning for Real-World Spatiotemporal Dynamics Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose CoST, a Collaborative framework designed for diverse SpatioTemporal scientific systems. |
Zhi Sheng; Yuan Yuan; Yudi Zhang; Jingtao Ding; Yong Li; |
| 500 | Debiased Negative Mining Improves Out-of-distribution Detection with Pre-trained Vision-Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we develop a theoretical framework for correcting the sampling bias of negatives labels by indirectly approximating the distribution of negative labels. |
Bo Peng; Jie Lu; Guangquan Zhang; Zhen Fang; |
This table only includes 500 papers selected by our daily digest algorithm. To continue with the full list (~1,400 papers), please visit Paper Digest: KDD-2026 (Full List).