Paper Digest: IJCAI 2026 Papers & Highlights
The International Joint Conference on Artificial Intelligence (IJCAI) is one of the top artificial intelligence conferences in the world. In 2026, it was held in Bremen, Germany. 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 IJCAI-2026
Literature review on a topic
Generate a written review of IJCAI-2026 research on any topic, with each claim cited to specific papers.
Browse & explore
Browse ~ 4,300 authors (IJCAI-2026), or explore the “Best Paper” Digest listing the most influential IJCAI papers of recent years.
Note: IJCAI-2026 accepts more than 1,000 papers, this page only includes 500 of them selected by our daily paper digest algorithm. Interested users can choose to read All 1,000 IJCAI-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: IJCAI 2026 Papers & Highlights
| Paper | Author(s) | |
|---|---|---|
| 1 | MathCritique: Enhancing LLM Reasoning Via Critique Models with Test-Time and Training-Time Supervision Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Building on the findings, we propose a critique-in-the-loop self-improvement method that incorporates critique-based supervision into the actor’s self-training process. |
Zhiheng Xi; Dingwen Yang; Jixuan Huang; Jiafu Tang; Xin Guo; Guanyu Li; Yiwen Ding; Wei He; Boyang Hong; Shihan Dou; WenYu Zhan; Xiao Wang; Xiaowei Shi; Yitao Zhai; Rongxiang Weng; Jingang Wang; Rui Zheng; Tao Ji; Tao Gui; Zuxuan Wu; Qi Zhang; Xipeng Qiu; Xuanjing Huang; Yu-Gang Jiang; |
| 2 | CollabLLM: From Passive Responders to Active Collaborators (Extended Abstract) Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: As a result, they often respond passively to ambiguous or open-ended user requests, failing to help users reach their ultimate intents and leading to inefficient conversations. To address these limitations, we introduce CollabLLM, a novel and general training framework that enhances multiturn human-LLM collaboration. |
Shirley Wu; Michel Galley; Baolin Peng; Hao Cheng; Gavin Li; Yao Dou; Weixin Cai; James Zou; Jure Leskovec; Jianfeng Gao; |
| 3 | A Comprehensive Survey of Deep Learning for Multivariate Time Series Forecasting: A Channel Strategy Perspective Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: This study systematically reviews the channel modeling strategies for time series and proposes a taxonomy organized into three hierarchical levels: the strategy perspective, the mechanism perspective, and the characteristic perspective. |
Xiangfei Qiu; Hanyin Cheng; Xingjian Wu; Junkai Lu; Jilin Hu; Chenjuan Guo; Christian S. Jensen; Bin Yang; |
| 4 | System 1&2 Synergy Via Dynamic Model Interpolation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We argue that this paradigm is misaligned: output length is merely a symptom of the model’s cognitive configuration, not the root cause. In this work, we shift the focus to capability control, which modulates how models think rather than what they produce. |
Chenxu Yang; Qingyi Si; Chong Tian; Xiyu Liu; Dingyu Yao; Chuanyu Qin; Zheng Lin; Weiping Wang; Jiaqi Wang; |
| 5 | DoMoE: Domain-Aware Semantic Expert Prediction for Efficient MoE Inference Under Expert Offloading Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose DoMoE, a domain-aware MoE inference system that exploits domain locality in inference workloads. |
Yao Mu; Fahao Chen; Wenbin Zhu; Mengying Zhao; Zhaoyan Shen; Dongxiao Yu; |
| 6 | TraceBrain: An Open-Source Framework for Agentic Trace Management Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Many existing observability platforms treat these traces primarily as passive logging artifacts, lacking the unified infrastructure to operationalize them for active governance and agent adaptation across heterogeneous single-agent and multi-agent workflows. To address this gap, we introduce TraceBrain, an open-source infrastructure for autonomous agent trace management. |
Quy Minh Le; Oscar Cao; Hoang Quoc Viet Pham; Hoang Thanh Lam; Hoang D. Nguyen; |
| 7 | Dual-View Self-Supervised Pre-Training for Expert Finding Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a Dual-view Self-Supervised pre-training framework for Expert Finding (SSEF) that simultaneously pre-trains expert and question representations from large-scale unlabeled data. |
Mingqiao Zhang; Hongtao Liu; Yinghui Wang; Yumeng Wang; Qiyao Peng; |
| 8 | RareDASH: A Dynamic Multi-Agent System for Holistic Rare Disease Care Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Inspired by recent studies of agent skills, we propose RareDASH, a multi-agent system (MAS) featuring dynamic workflow orchestration designed to provide a comprehensive solution for the full life-cycle of rare disease care. |
Jialun Zhong; Jiayang Yu; Yanzeng Li; Meng Qin; Lei Zou; Yuqian Wang; Ying Zhang; Hanna Li; Liying Yan; Jie Qiao; |
| 9 | Learning to Harvest: VR-Guided Expert Behaviour Capture for Decision Modelling in Agricultural Robots Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While deep learning has significantly enhanced robotic perception in agriculture, autonomous decision-making in dense and occluded environments remains a persistent challenge. This paper proposes a VR-based expert motion capture framework to bridge this gap by integrating high-fidelity virtual environments with human expertise. |
Yining Lang; Zhaoxin Li; Xiujuan Chai; |
| 10 | One-Step Self-Aligned Anchor Learning for Multi-View Clustering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Current research fails to adequately address two pivotal aspects of this challenge: first, the construction of anchor graphs and the alignment of anchors are two independent stages, overlooking their potential synergistic reinforcement; second, selecting anchors from different views as an alignment baseline often renders the clustering performance highly sensitive to the baseline choice. To address these issues, we propose a unified framework termed One-Step Self-Aligned Anchor Learning for Multi-View Clustering (OSAA-MVC). |
Zijian Chen; Miao Jia; Xingchen Hu; Jiyuan Liu; Huan Chen; Siwei Wang; Jincai Huang; |
| 11 | A Survey on 3D Skeleton Based Person Re-Identification: Taxonomy, Advances, Challenges, and Interdisciplinary Prospects Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we provide a comprehensive review and analysis of recent SRID advances. |
Haocong Rao; Chunyan Miao; |
| 12 | From Human Videos to Robot Manipulation: A Survey on Scalable Vision-Language-Action Learning with Human-Centric Data Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We categorize existing approaches into four classes based on the action-related information they derive: (i) latent action representations that encode inter-frame changes; (ii) predictive world models that forecast future frames; (iii) explicit 2D supervision that extracts image-plane cues; and (iv) explicit 3D reconstruction that recovers geometry or motion. Beyond this taxonomy, we highlight three key open challenges in this area: structuring unstructured videos into training-ready episodes, grounding video-derived supervision into robot-executable actions under embodiment and viewpoint heterogeneity, and designing evaluation protocols that better predict real-world deployment performance and transfer efficiency, thereby informing future research directions. |
Zhiyuan Feng; Qixiu Li; Huizhi Liang; Rushuai Yang; Yichao Shen; Zhiying Du; Zhaowei Zhang; Yu Deng; Li Zhao; Hao Zhao; Zongqing Lu; Oier Mees; Marc Pollefeys; Jiaolong Yang; Baining Guo; |
| 13 | CAMERA: Adapting to Semantic Camouflage in Unsupervised Text-Attributed Graph Fraud Detection Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To bridge the gaps, we propose a Case-Adaptive Multi-cue Expert fRAmework (CAMERA) for unsupervised TAGFD. |
Junjun Pan; Yixin Liu; Yu Zheng; Lianhua Chi; Alan Wee-Chung Liew; Shirui Pan; |
| 14 | Distribution-Aware Energy Minimization: Physical-Inspired Efficient Active Learning and Quantum Potentials Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a general active learning framework based on Distribution-Aware Energy Minimization, which reformulates sample selection as minimizing the energy function for the distributional discrepancy between the selected subset and the global uncertainty field. |
Zhicheng Yao; Wenguo Yang; Yancheng Chen; Dun Ma; Shengminjie Chen; Xiaoming Sun; |
| 15 | Gradient Enhancement Task Aware Post-training Quantization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper introduces Gradient Enhancement Task Aware Post-training Quantization, i.e., GTAQ, to address the generalization issue. |
Yihua Shao; Yan Gu; Minxi Yan; Siyu Chen; Haiyang Liu; Ziyang Yan; Yongjia Li; Yan Wang; Qun Song; Hao Tang; Haotong Qin; Jingcai Guo; Nicu Sebe; |
| 16 | SMLDR: Spectral Memory Learner with Dual-Retrieval for Time Series Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper re-examines frequency-domain modeling from the perspective of spectral non-identifiability and proposes a Spectral Memory Learner with Dual Retrieval (SMLDR) for time series forecasting. |
Zhenxin Li; Longquan Liao; Wenchang Zhang; Jiaying Zhang; Kaiwen Wei; Jiang Zhong; Linjiang Zheng; |
| 17 | Robust Federated Hyperspectral Image Clustering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While Federated Learning offers a decentralized solution, existing frameworks in remote sensing are predominantly confined to supervised paradigms and struggle to address the heavy reliance on annotations and Non-IID distributions inherent among clients. To overcome these limitations, we propose a novel framework named Robust Federated HSI Clustering(RFHC) that enables collaborative unsupervised learning without requiring raw data exchange. |
Xiang Yang; Zhengzhong Zhu; Dayu Hu; Xiaowen Ma; Zihao Li; Wenxuan Tu; Taichun Zhou; Wenxin Zhang; Renxiang Guan; |
| 18 | Towards Automated Kernel Generation in The Era of LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: The performance of modern AI systems is fundamentally constrained by the quality of their underlying GPU kernels, which translate high-level algorithmic semantics into low-level … |
Yang Yu; Peiyu Zang; Chi Hsu Tsai; Haiming Wu; Yixin Shen; Jialing Zhang; Haoyu Wang; Zhiyou Xiao; Jingze Shi; Yuyu Luo; Wentao Zhang; Chunlei Men; Guang Liu; Yonghua Lin; |
| 19 | Towards Comprehensive Post Safety Alignment of Large Language Models Via Safety Patching Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we propose a novel post safety alignment (PSA) method to address these inherent and emerging safety challenges, including safety enhancement, over-safety mitigation, and utility preservation. |
Weixiang Zhao; Yulin Hu; Yang Deng; Jiahe Guo; Xingyu Sui; Yanyan Zhao; Bing Qin; Ting Liu; |
| 20 | MELLA: Bridging Linguistic Capability and Cultural Groundedness for Low-Resource Language MLLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Multimodal Large Language Models (MLLMs) perform strongly in high-resource languages, yet often produce fluent but culturally "thin" descriptions in low-resource settings. |
Yufei Gao; Jiaying Fei; Nuo Chen; Ruirui Chen; Guohang Yan; Yunshi Lan; Botian Shi; |
| 21 | Cost of Structural Learning Under Censored Feedback: A Threshold-Bandit Approach Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We show that a centralized algorithm (C-TAC) achieves cumulative regret O(log T), decomposed into a structural-search term that captures the cost of resolving feasibility under censored feedback and a statistical-monitoring term for value estimation. |
Michael Ledford; William Regli; |
| 22 | EVENTTSF: Event-Aware Non-Stationary Time Series Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose event-aware non-stationary time series forecasting EventTSF, an autoregressive diffusion framework that integrates historical time series and textual events via step-wise diffusion. |
Yunfeng Ge; Ming Jin; Yiji Zhao; Hongyan Li; Bo Du; Chang Xu; Shirui Pan; |
| 23 | No More Shortcuts: Network Traffic Anomaly Detection Via Bidirectional Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Nevertheless, these methods are susceptible to an identical shortcut issue, where models indiscriminately reconstruct both normal and anomalous inputs, leading to anomaly overgeneralization. To address this limitation, we propose BiPred, the first prediction-based detection paradigm for NTAD. |
Xinglin Lian; Chengtai Cao; Fanglin Yu; Ting Zhong; Fan Zhou; |
| 24 | Understanding and Exploiting Phase Sensitivity for Attacking Large Vision–Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Inspired by the cognitive science, in this paper, we make the first attempt to investigate the interference of adversarial perturbation from the perspectives of image phase, and find that LVLMs are sensitive to the phase-aware image structure. Motivated by this, we propose a novel LVLM attack method called BadPhase with further backdoor designs, to implant adversarial phase as triggers into any image inputs via data poisoning so as to control the LVLMs’ predictions. |
Daizong Liu; Junhao Dong; Xiang Fang; Hongyang He; Keyan Jin; Zhongliang Guo; Xiaoye Qu; Keke Tang; |
| 25 | Deep Learning and Foundation Models for Weather Prediction: A Survey Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: This paper reviews DL and foundation models for weather prediction by highlighting their strengths and limitations. |
Jimeng Shi; Azam Shirali; Bowen Jin; Sizhe Zhou; Wei Hu; Rahuul Rangaraj; Zhaonan Wang; Yanzhao Wu; Leonardo Bobadilla; Upmanu Lall; Shaowen Wang; Jiawei Han; Giri Narasimhan; |
| 26 | Unified Sequence Modeling for Remote Sensing: A Parameter-Efficient Foundation Model Via Prompt-Driven Granularity Alignment Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While vision–language models (VLMs) offer a route toward unification, their computational cost can hinder deployment. In this work, we propose RS-Florence, a compact unified model that addresses these tasks through a Prompt-Driven Sequence-to-Sequence framework. |
Yang Liu; Weixing Luo; Huaizhou Qi; Suisui Jia; Yongjing Guo; |
| 27 | Instance-Aligned Semantic Reconstruction for Incomplete Multi-View Clustering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose IASR, an Instance-Aligned Semantic Reconstruction framework for IMVC. |
Weiqing Yan; Yongteng Du; Peng Song; Chang Tang; |
| 28 | Can Quantum Federated Learning Withstand Circuit-Level Backdoors? Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This work proposes a novel CircUit-Level backdoor Threat (CULT) model that formalizes four stealthy attacks by exploiting quantum-aware mechanisms, including Grover, Pauli, Bit-flip, and Sign-flip. |
Aakar Mathur; Ruknuddin Mohammed; Ashish Gupta; |
| 29 | Towards Fair Graph Learning Without Demographic Supervision Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In real-world settings, however, such information is often unavailable or legally prohibited to infer due to privacy concerns, legal restrictions, or regulatory constraints, which substantially limits the applicability of these methods. To address this challenge, we propose Demographic-Independent Fair Graph Learning (DIFGL), a novel framework for fair graph learning without demographic supervision. |
Zichong Wang; Zhipeng Yin; Mo Sha; Xiaofeng Gao; Xiaoli Li; Wenbin Zhang; |
| 30 | Learning Counterfactual Fairness from Authentic Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, most existing methods assume that all observed variables are directly influenced by sensitive attributes, an overly strong and often unrealistic assumption in real-world graphs. To address this limitation, we propose Graph Counterfactual Fairness (GCFair), a novel framework that achieves counterfactual fairness by explicitly identifying and disentangling the subsets of node features and graph structures genuinely affected by sensitive attributes. |
Zichong Wang; Zhipeng Yin; Zhong Chen; Jack Yang; Jun Liu; Wenbin Zhang; |
| 31 | Beyond Uniform Updates: Drift Pattern Aware Online Time Series Forecasting Under Delayed Feedback Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We view delayed residuals as compressed observations of latent drift over the horizon, and propose PADRE, a drift evidence driven framework that converts each delayed feedback event into a context-sensitive adaptation decision. |
Xingwang Li; Fei Teng; Cong Zhou; Qiang Duan; |
| 32 | ResearchEnvBench: Benchmarking Agents on Environment Synthesis for Research Code Execution Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce ResearchEnvBench, a benchmark for environment synthesis in research code execution. |
Yubang Wang; Chenxi Zhang; Bowen Chen; Zezheng Huai; Zihao Dai; Xinchi Chen; Yuxin Wang; Yining Zheng; Jingjing Gong; Xipeng Qiu; |
| 33 | MA-RWG: A Multi-Agent Framework for Thematically Structuring and Generation of Related Work Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Unlike surveys that provide broad literature overviews, RWG synthesizes prior studies for a single focal paper, requiring contextual fit, cross-paper comparison, and accurate attribution. To address this gap, we propose MA-RWG, a fully automated multi-agent framework that generates polished related work sections from only a title and abstract. |
Zhuang Liu; Jian Liu; Chun Kang; Chenbin Zhang; Rui Li; Fanhu Zeng; Yong Dai; Lei Sha; |
| 34 | Wavelength.AI: Extending The Collaborative Game Wavelength As A Testbed for Studying Shared Understanding in Human–Agent Collaboration Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We interpret higher team scores as evidence for better shared understanding in a preliminary user study with 24 human–AI teams. |
Katelyn Morrison; Gabriel Enrique Gonzalez; Zahra Ashktorab; Matt Riemer; Andrew Anderson; Djallel Bouneffouf; Justin D. Weisz; |
| 35 | BrainCGT: A Brain Graph Transformer for Modeling Causal Connectivity in Neurological Disorder Diagnosis Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: As a result, direction-specific disease mechanisms are not explicitly modeled, and interpretability is often limited. To address this gap, we present BrainCGT, a brain graph transformer designed to model causal connectivity inferred from fMRI time-series data. |
Ahsan Shehzad; Dongyu Zhang; Shagufta Abid; Shuo Yu; Xin Zheng; Hongfei Lin; Feng Xia; |
| 36 | I-EDI: Robust Self-Evolution Agents Via Verifiable Counterfactual Simulation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Such reasoning appears valid in-distribution but often fails the moment the task shifts slightly. We argue that robust evolution implies Structural Invariance: a reasoning path is valid only if its core dependency graph remains isomorphic under counterfactual perturbations. |
Runze Fan; Yong Li; |
| 37 | PAAL: Pattern-Anchor Alignment for Continual Knowledge Graph Embedding Under Structural Distribution Shift Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This presents a challenge that the structural distribution of historical data may diverge from that of emerging data, creating a distributional mismatch that complicates the adaptation to new trends. To address this, we propose Pattern-Anchor Alignment (PAAL), which introduces relation-level structural anchors to explicitly model these structural shifts. |
Yue Jian; Lin Li; Kaize Shi; Junwei Zhou; Yu Yang; |
| 38 | Streamlining Long-Chain Reasoning Via Differentiable Hierarchical Fusion Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present Differentiable Hierarchical Fusion (DHF), a novel framework that merges reasoning models with efficient base models via differentiable optimization to produce concise, accurate outputs. |
Chuangen Gao; Wenlun Zhang; Shang Wang; Shuyang Gu; |
| 39 | GroupMIL: Semantic Group Based Multiple Instance Learning for Whole Slide Image Analysing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose GroupMIL, a novel framework that introduces a differentiable grouping mechanism into the MIL framework. |
Zhao Yao; Zhenmi Xie; Mengxin Tian; Guoqing Wu; Yaonan Wang; Min Liu; |
| 40 | Theoretical Analysis of Multi-Objective Evolutionary Algorithms on Integer Spaces with Local Optima Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We conduct a running time analysis on the proposed benchmark and derive several theoretical results. |
Yuetong Sun; Zeqiong Lv; Shengjie Ren; Zimin Liang; Miqing Li; Chao Qian; |
| 41 | VLAs Are Confined Yet Capable of Generalizing to Novel Tasks Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Vision-language-action models (VLAs) often achieve high performance on demonstrated tasks but struggle significantly when required to extrapolate, recombining skills used in different tasks in novel ways. |
Quanyi Li; |
| 42 | Sprint or Delve: A Distribution-Aware Approach to Efficient Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To address this, we first empirically observe that reasoning lengths are well approximated by a log-normal distribution, and provide an intuitive explanation for this phenomenon. Based on this insight, we propose the Powered Length Penalty (PLP), an adaptive regularizer that penalizes redundancy in short sequences while gradually reducing penalties for longer sequences, preserving deep reasoning. |
Zehui Ling; Deshu Chen; Hongwei Zhang; Yifeng Jiao; Xin Guo; Zenglin Xu; Yuan Cheng; |
| 43 | EyeCue: Driver Cognitive Distraction Detection Via Gaze-Empowered Egocentric Video Understanding Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose EyeCue, a gaze-empowered egocentric video understanding framework, to detect driver cognitive distraction. |
Lang Zhang; JinYi Yoon; Matthew Corbett; Abhijit Sarkar; Bo Ji; |
| 44 | Re-Weighting Cross-Modal Pairs Via Rank Consistency for Noise-Robust Retrieval Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing methods typically re-weight training pairs by estimating semantic matching degrees from the model’s own similarity predictions, which are inherently unreliable under noise and often overestimate partially aligned pairs. To overcome this limitation, we introduce a novel semantic matching degree estimation method based on ranking consistency. |
Weiran Pan; Wei Wei; |
| 45 | Debate with Myself: Zero-Shot Event Causality Identification with Adversarial Evidence Integration Via Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Although Large Language Models (LLMs) show strong promise for few-shot and zero-shot information extraction, they are prone to “causal hallucination,” generating unreliable and spurious causal links. To address these limitations, we propose LLM-SD (Large Language Model Self-Debate), a novel framework that formulates ECI as a structured debate among multiple identical instances of a single LLM. |
Zefan Zeng; Yuehang Si; Xingchen Hu; Qing Cheng; Jiakun Liu; Zhong Liu; |
| 46 | FedCIGAR: A Personalized Reconstruction Approach for Federated Graph-Level Anomaly Detection Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing methods suffer from poor generalization due to the reliance on unrealistic synthetic anomalies and insufficient personalization capabilities under data heterogeneity. To address these challenges, we propose a novel Federated graph-level anomaly detection approach with Cluster-adaptIve GAted Reconstruction (FedCIGAR). |
Yunfeng Zhao; Yixin Liu; Qingfeng Chen; Shiyuan Li; Yue Tan; Shirui Pan; |
| 47 | OrthKD: Extracting Generalized Clinical Knowledge from Heterogeneous Teachers for Lightweight Deployment Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In our setting, this assumption fails: a strong CNN teacher (EfficientNet-B3, 0.876 QWK) and a weaker Transformer teacher (Swin-Base, 0.830 QWK) are complementary, yet the Transformer’s logits can still mislead the student. We therefore propose OrthKD, a selective-trust distillation framework that transfers full supervision from the strong CNN, uses feature-only distillation from the weak ViT, and enforces orthogonality between teacher-specific student projections to encourage complementary rather than redundant evidence. |
Yi Xu; Cheng Chen; Mufan Cao; |
| 48 | Rethinking Thinking Steps in Overthinking: Towards More Effective Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing approaches primarily adopt coarse-grained reasoning strategies, such as truncating Chains-of-Thought or switching reasoning modes, which reduce verbosity but are insufficient to actively guide reasoning toward more effective trajectories.To address these issues, we propose a training-free, interpretable framework that selects thinking words via attention heads to guide LRMs toward more effective reasoning. Specifically, we categorize thinking steps into effective and redundant states, identify the attention head that best discriminates between them as the Thinking Partition Head to construct an Effective Thinking Representation Space, and compute the Information Gain Ratio (IGR) between candidate thinking words and this space to select the word that steers reasoning toward a more effective direction.Extensive experiments on mathematical and scientific reasoning benchmarks, including AIME24, AMC23, MATH-500, GSM8K, and GPQA-D, show that our method consistently outperforms the strong baseline DEER, achieving average improvements of 1.2–1.3% in accuracy and 2.5–4.5% in compression rate. |
Dezhi Zhao; Xin Liu; Xiaocheng Feng; Hui Wang; Bing Qin; |
| 49 | Toward Trustworthy Recommender Systems in The Era of Agentic AI: From Relational User Modeling to Generative Personalization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: The talk aims to provide a unified view of recommender systems as relational, generative, agentic, and trustworthy AI systems. |
Wenqi Fan; |
| 50 | Interaction Effects in Hybrid Compression of Small Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce an interaction coefficient that isolates non-additive effects and apply it to Falcon3-1B-Base and LLaMA-3.2-1B, with a limited study on Qwen2.5-1.5B. |
Iheb Bouriel; Qassim Nasir; Manar Abu Talib; |
| 51 | Open-Vocabulary Object 6D Pose Estimation Via Modulated Textual Semantics Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a framework that modulates static textual embeddings into adaptable semantic guidance for RGB-D open-vocabulary 6D pose estimation. |
Zixuan Sun; Hui Shuai; Qingshan Liu; |
| 52 | On The Impact of Crossover in Many-Objective Optimization: A Runtime Analysis of NSGA-III Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, the benefits of using crossover in many-objective optimization are theoretically not understood, except for specifically designed benchmark functions tuned to particular crossover operators, and still lag significantly behind its practical use. In this paper, we build upon this line of research and present a theoretical runtime analysis of the widely used NSGA-III algorithm on the classical m-objective m-OneJumpZeroJump function (m-OJZJ for short). |
Andre Opris; |
| 53 | Conspiracy Spoofing Detection Via Structure-Augmented Generative Graph Model Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Instead, certain consistent trading patterns, such as motif structures, remain robust for analysis across different distributions. Therefore, this paper introduces the Structure-Augmented Generative Graph Model (SAG^2M) to detect conspiracy spoofing through substructure frequency-augmented detection. |
Sheng Xiang; Ziwen Xu; Yidong Jiang; Dawei Cheng; Hui Zhao; |
| 54 | Progressive Subexpression Reuse in Symbolic Regression: Insights from RL-based Search and A Genetic Programming Realization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Symbolic regression (SR) aims to recover compact and interpretable mathematical expressions from data.Genetic programming (GP) directly searches over symbolic structures, but its population dynamics can make it difficult to reliably preserve and accumulate useful subexpressions.In contrast, reinforcement learning (RL)-based SR has shown strong empirical performance, suggesting that learned sampling dynamics may capture useful regularities in symbolic search.Motivated by this contrast, we analyze expressions sampled during RL training and identify a recurring pattern, termed progressive subexpression reuse, where useful simple subexpressions emerge early, become increasingly frequent, and support the formation of more complex structures.Based on this observation, we propose Reinforcement Genetic Programming (RGP), a purely GP-based and non-RL framework that explicitly realizes a stage-wise retention–reintroduction loop through a dynamically maintained subexpression pool and pool-guided population initialization.Experiments on standard SR benchmarks show that RGP matches or outperforms strong baselines without RL policy training, suggesting that progressive subexpression reuse is an effective mechanism for SR search. |
Xiangdong Wu; Wenjun Wu; Bingrun Chen; Junle Wang; Zhaoxin Fan; Haoyi Zhou; Pengju Zhang; Rongye Shi; |
| 55 | H^2Net: Homo- and Heterogeneous Networks for Unified Segmentation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Unified segmentation aims to consolidate multiple vision tasks into a single model, yet faces two core challenges: learning robust homogeneous features (e.g., shared low- and mid-level cues) to enable cross-domain knowledge transfer, while disentangling heterogeneous features (e.g., task-specific semantic objectives) to avoid negative transfer and preserve task independence.To address these challenges, we propose the Homo- and Heterogeneous Network (H2Net), a unified framework that jointly models shared homogeneous representations and task-specific heterogeneous features. |
Jinyu Han; Changguang Wu; Fuming Sun; Mengyin Wang; Jinhui Tang; |
| 56 | How Well Do Large-Scale Chemical Language Models Transfer to Downstream Tasks? Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, the common belief that increasing training resources, such as model size, dataset size, and training compute, improves both pre-training loss and downstream task performance has not been systematically validated in the chemical domain. In this work, we evaluate this assumption by pre-training CLMs while scaling training resources and measuring transfer performance across diverse molecular property prediction (MPP) tasks. |
Tatsuya Sagawa; Ryosuke Kojima; |
| 57 | An Information-theoretic Propagation Denoising and Fusion Framework for Fake News Detection Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we alleviate the unreliability of synthetic propagation from the mutual information perspective and propose a novel information-theoretic propagation denoising and fusion (InfoPDF) framework to learn effective representations from both real and synthetic propagation. |
Mengyang Chen; Lingwei Wei; Wei Zhou; Songlin Hu; |
| 58 | TrajAR: Long-Term Trajectory Prediction at Urban Intersections Via Multi-scale Interaction Perception Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing solutions inadequately incorporate these interactions and suffer from error accumulation or overall bias when performing long-term prediction. To overcome these challenges, we propose a long-term Trajectory prediction multi-scale AutoRegressive framework (TrajAR), which follows an encoder-decoder structure. |
Letian Gong; Yan Lin; Xinyue Zhang; Yiwei Shuang; Guanyu Yao; Cheng Long; Shengnan Guo; Youfang Lin; Huaiyu Wan; |
| 59 | Complex-Valued Residual Diffusion with GRPO for Pansharpening Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, enhancing spatial textures without introducing spectral distortion remains challenging due to the inherent spectral–spatial trade-off. To address this issue, we propose a two-stage pansharpening framework that tackles the problem from both modeling and optimization perspectives. |
Zhiyuan Wang; Dong Li; Kaixin Fu; Chunhui Luo; Xueyang Fu; |
| 60 | From Discrete to Continuous: Progressive Hybrid-Distributional Learning for Gradual Emotion Transitions Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing methods often rely on one-hot supervision, which fails to reflect the progressive nature of human emotions, particularly for neutral-valence emotions with subtle trajectories. To address this limitation, we propose a pseudo soft-label guided Progressive Hybrid-Distributional (PHD) learning framework. |
Yunhe Xie; Yang Li; |
| 61 | What Affects The Stability of Tool Learning? An Empirical Study on The Robustness of Tool Learning Frameworks Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Without understanding the impact of these factors, it can lead to inconsistent results, inefficient model deployment, and suboptimal tool utilization, ultimately hindering the practical integration and scalability of LLMs in real-world scenarios. Therefore, in this paper, we explore the impact of both internal and external factors on the performance of tool learning frameworks. |
Chengrui Huang; Zhengliang Shi; Yuntao Wen; Xiuying Chen; Peng Han; Shen Gao; Shuo Shang; |
| 62 | FedFINFO: A General Full-Informativeness Federated Graph Learning from Open Cross-Domain Data Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We proposed a counterfactual multi-view framework to explicitly learn a structure masker for extracting consensus subgraphs. |
Wan Zhang; Xiaoqian Jiang; Ye Wang; Zhiqiang Xu; Jing Zhang; |
| 63 | Parameterized Approximation Schemes for Fair Clustering in Doubling Metrics Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we focus on the k-center problem in bounded doubling metrics under two popular fairness requirements: group fairness and data summarization fairness, referred to Group Fair k-Center (Gf-k-Cen) and Data Summarization Fair k-Center (Dsf-k-Cen), respectively. |
Xiaoliang Wu; Ting Liang; Zhize Li; Qilong Feng; |
| 64 | DiG-Plan: Mitigating Early Commitment for Tool-Graph Planning Via Diffusion Guidance Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: A controlled study shows that masked denoising raises Pass@10 solution coverage from 0.320 to 0.943 over AR sampling under matched compute. Motivated by this, we propose DiG-Plan, a framework that decouples combinatorial exploration from structural refinement. |
Yansi Li; Zhuosheng Zhang; |
| 65 | PCEvo: Path-Consistent Molecular Representation Via Virtual Evolutionary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Under the few-shot setting, models trained with scarce supervision often learn brittle structure–property relationships, resulting in substantially higher prediction errors and reduced generalization to unseen molecules. To address this limitation, we propose PCEvo, a path-consistent representation method that learns from virtual paths through dynamic structural evolution. |
Kun Li; Longtao Hu; Jiajun Yu; Yida Xiong; Hongzhi Zhang; Jiameng Chen; Xiantao Cai; Jia Wu; Wenbin Hu; |
| 66 | Improving Scientific Formula Verbalization in Large Speech Language Models for Accessible Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose Formula-Speech, the first end-to-end LSLM designed for scientific formula verbalization. |
Xueyi Li; Tianqiao Liu; Zitao Liu; Teng Guo; Yongdong Wu; |
| 67 | Disentangled Graph-Enhanced Large Language Models for Fair Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Recent approaches integrate Graph Neural Networks (GNNs) to enhance structural modeling, yet they largely overlook fairness, leaving models vulnerable to bias amplification across graph and text modalities. To address this issue, we propose FairGEnt, a disentangled graph-enhanced large language model for fair graph learning. |
Zhipeng Yin; Zichong Wang; Zhong Chen; Jack Yang; Xin Ning; Wenbin Zhang; |
| 68 | Toward LoRA Copyright Protection with An Authorized Dual-Watermarking Framework Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, the growing prevalence of LoRA and its critical role in customized AI services have raised urgent concerns about LoRA copyright protection. To address this gap, we propose LoRA2D, an authorized dual-watermarking framework specifically designed to protect LoRA modules in T2I diffusion models. |
Zhipeng Yin; Zichong Wang; Ruijun Chen; Xin Ning; Xingyu Zhang; Wenbin Zhang; |
| 69 | MC-RAG System: A Structure-Driven RAG System for Multi-Constraint Queries Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present Structure-Driven RAG System for Multi-Constraint Queries(MC-RAG), a structure-driven RAG system that reformulates retrieval as a subgraph matching problem over a knowledge graph. |
Xiao Zhang; Yang Wan; Yi Li; Miao Xie; Chunli Lv; |
| 70 | GraphSculptor: Sculpting Pre-training Core Sets for Graph Self-supervised Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, empirical evidence suggests that these datasets contain substantial redundancy—our analysis reveals that uniformly subsampling 50% of graphs retains over 96% of downstream performance. To exploit this redundancy, we introduce GraphSculptor for pre-training coreset construction. |
Chuang Liu; Zelin Yao; Xueqi Ma; Luzhi Wang; Mukun Chen; Pinghua Xu; Wenbin Hu; |
| 71 | IPSM-Bench: A New Intermediate Phase Segmentation Benchmark in Microstructure Images of Zinc-Based Absorbable Biomaterials Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we construct IPSM-Bench, the largest high-quality dataset for zinc-alloy intermediate phase segmentation. |
Jinglin Xu; Shangyan Zhao; Jiabo Wang; Xinghong Mu; Yulong Lei; Jiacheng Zhang; Hongbo Sun; Yageng Li; |
| 72 | Continual Unsupervised Domain Adaptation for Cardiac Image Segmentation with Style-Adapting Generative Replay and Prototype Consolidation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this study, we propose a novel continual UDA framework that enforces dual-level alignment at the input and feature levels. |
Shun Xiang; Yan Yi; Haiyong Chen; Yuanquan Wang; Yining Wang; |
| 73 | Exploring The System 1 Thinking Capability of Large Reasoning Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose S1-Bench, a multi-domain, multilingual benchmark comprising model-simple system 1 questions. |
Wenyuan Zhang; Shuaiyi Nie; Xinghua Zhang; Zefeng Zhang; Tingwen Liu; |
| 74 | A₃B₂: Adaptive Asymmetric Adapter for Alleviating Branch Bias in Vision-Language Image Classification with Few-Shot Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Through extensive analysis, we reveal a Branch Bias issue in vision–language image classification: adapting the image encoder does not always improve performance under out-of-distribution settings. Motivated by this observation, we propose A₃B₂, an Adaptive Asymmetric Adapter that alleviates Branch Bias in few-shot learning. |
Yiyun Zhou; Zhonghua Jiang; Wenkang Han; Kunxi Li; Mingjing Xu; Chang Yao; Jingyuan Chen; |
| 75 | Trust, But Verify: Uncertainty-Driven Evidential Multimodal Representation Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Most existing methods overlook this hierarchy, applying a single uncertainty model. We propose Adaptive Evidential Multimodal Representation Learning (AEMRL), a framework aligned with this multi-level view. |
Yupeng Han; Kai Zhang; Xianquan Wang; Zhihong Pan; Ze Liu; Jiyuan He; |
| 76 | TTS-Design: Test-Time Compute Scaling for Structure-Guided Protein Design Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose TTS-Design, a test-time compute scaling framework that enhances protein sequence design without retraining models or relying on larger training data. |
Zizhe Jin; Yizhen Zheng; Huan Yee Koh; Jiaxin Ju; Jiapu Wang; Shirui Pan; |
| 77 | About Time: Model-Free Reinforcement Learning with Timed Reward Machines Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose timed reward machines (TRMs), which are an extension of reward machines that incorporate timing constraints into the reward structure. |
Rajarshi Roy; Anirban Majumdar; Ritam Raha; David Parker; Marta Kwiatkowska; |
| 78 | Patient-Visit-Spanned Hypergraph Learning for EHR-based Diagnosis Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing HGNNs struggle to capture patient-visit long-range dependencies when processing EHR-derived hypergraphs. To tackle this issue, we propose a Patient-Visit-Spanned HyperGraph Learning (PVHGL) framework specifically designed for diagnosis prediction. |
Ye Yuan; Haiyan Wang; Lun Hu; Xin Luo; |
| 79 | WBMCF: Robust Spatiotemporal Forecasting of Terrorism Fatalities with Multi-Scale Time–Frequency Fusion Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, real-world terrorism data are characterized by extreme sparsity, abrupt volatility, and weak, rapidly shifting non-Euclidean spatial relationships, posing substantial challenges for existing spatiotemporal forecasting models in learning stable multi-scale dependencies. To address these challenges, we propose a robust spatiotemporal forecasting framework, termed WBMCF. |
Zhenkai Qin; Baozhong Wei; Huan Zeng; Caifeng Gao; Ziqian Lin; |
| 80 | Rule-Bottleneck RL: Learning to Decide and Explain for Sequential Resource Allocation Via LLM Agents in Public Health Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In contrast, large language model (LLM) agents provide human-readable reasoning but often struggle with effective long-term decision making. To bridge this gap, we introduce Rule-Bottleneck RL (RBRL), the first LLM agent framework for resource allocation problems that jointly optimizes language-based decision policy and explainability. |
Guojun Xiong; Mauricio Tec; Haichuan Wang; Francesca Dominici; Joseph Ngonzi; Adeline Boatin; Milind Tambe; |
| 81 | CasUGC: Aligning User-Generated Comment Evolution with Cascade Dynamics for Popularity Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: During the cascade propagation process, user-generated comments continually evolve, thereby substantially affecting overall information popularity.However, existing methods primarily focus on learning structural–temporal cascade dynamics while neglecting the modeling of user-generated comment evolution, leading to suboptimal predictions.In this paper, we propose a novel framework, CasUGC, that aligns Cascade dynamics with User-Generated Comment evolution for popularity prediction.Specifically, we develop a dual-granularity alignment strategy that bridges the representation gap between comment semantics and structural–temporal dynamics at both the user and cascade levels. |
Yifan Meng; Xigang Sun; Anran Zhang; Jiaqi Jiang; Jiahui Jin; |
| 82 | GMM-TDQN:Two-Stage Multi-Objective Reinforcement Learning for Large-Scale Edge Server Deployment Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose GMM-TDQN, a two-stage multi-objective reinforcement learning framework for large-scale edge server deployment. |
Zhou Zhou; Tingyu Zheng; Yifu Zeng; |
| 83 | Cross-Relational Preference Learning for Better LLM Instruction Following Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While existing approaches often rely on preference learning to enhance this ability, they typically overlook the relationships between the permissible response spaces of different instructions, which restricts a model to align with subtle and diverse constraint variations. To address this, we propose Cross-Relational Preference Learning (CRPL), a novel framework for constructing preference data that explicitly models inter-instruction relationships through two key techniques: Cross-Relationship Perturbation and Cross-Region Pair Sampling. |
Runsheng Li; Kai Sun; Bin Shi; Bo Dong; |
| 84 | RM-Distiller: Exploiting Generative LLM for Reward Model Distillation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing approaches predominantly treat teacher models as simple binary annotators, failing to fully exploit the rich knowledge and capabilities for RM distillation. To address this, we propose RM-Distiller, a framework designed to systematically exploit the multifaceted capabilities of teacher LLMs: (1) Refinement capability, which synthesizes highly correlated response pairs to create fine-grained and contrastive signals. |
Hongli Zhou; Hui Huang; Wei Liu; Chenglong Wang; Xingyuan Bu; Lvyuan Han; Fuhai Song; Muyun Yang; Wenhao Jiang; Hailong Cao; Tiejun Zhao; |
| 85 | Beyond The Mean: Gaussian Distributional Successor Features for Zero-Shot Non-Linear Reward Adaptation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present this framework for efficient representation of aleatoric uncertainty, without resorting to computationally expensive existing distributional methods. |
Yong Zhao; Wen Sun; Jianhua He; Peng Wang; Qubeijian Wang; |
| 86 | Learning with Foresight: Enhancing Neural Routing Policy Via Multi-Node Lookahead Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we introduce Multi-node Lookahead Prediction (MnLP), a novel training strategy that extends the supervised learning paradigm to predict multiple future nodes simultaneously. |
Xia Jiang; Yaoxin Wu; Yew-Soon Ong; Yingqian Zhang; |
| 87 | THGAgents: Traceable Biomedical Hypothesis Generation Via Dynamic Causal Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: As such, both current Retrieval-augmented generation methods lacking causal reasoning capabilities, and the static traditional knowledge graphs failing to reflect evolving scientific knowledge, present obstacles to utilizing LLMs as scientific discovery tools. In response to these ongoing challenges, we present THGAgents. |
Mingjian Yang; Kun Dong; Kevin Lim; Juan Liu; |
| 88 | MedVCoT: Bridging The Modality Gap in Medical VQA Through Latent Visual Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, the modality gap for medical visual question answering is quite severe when continuous visual signals are forcibly projected into discrete text space for reasoning, and the loss of necessary diagnostic information leads to low precision and black-box opacity. To address this problem, we propose MedVCoT, which incorporates latent visual reasoning into the medical visual question answering(VQA) domain. |
Bo Xu; Quanhao Zhu; Boling Zhu; Chenyuan Wang; Liang Zhao; Hongfei Lin; Feng Xia; |
| 89 | Can Stationary Distributions of Scale-Invariant Neural Networks Be Described By The Thermodynamics of An Ideal Gas? Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Building on this perspective, we develop a thermodynamic framework to describe the stationary distributions of stochastic gradient descent (SGD) with weight decay for scale-invariant neural networks, a setting that both reflects practical architectures with normalization layers and permits theoretical analysis. |
Ildus Sadrtdinov; Ekaterina Lobacheva; Ivan Klimov; Mikhail Burtsev; Mikhail I. Katsnelson; Dmitry Vetrov; |
| 90 | Learning Heterogeneous Global Local Frequency Dependencies in Diffusion-Based Image Compression Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: These two forms of dependency differ substantially in both scale and semantic level, yet most methods overlook this distinction. To address this issue, we propose a learning heterogeneous global local frequency dependencies in diffusion-based image compression which uses Fourier and Mamba jointly models both global and local frequency correlations(FMDiff). |
YuBing Luo; Zekai Ji; Jia Qin; Zhihang Chen; Tengyue Guo; Pinle Qin; Rui Chai; Jianchao Zeng; |
| 91 | SPACE: Structure-Preserving Cross-Modal Image Enhancement for Extreme Low-Light Conditions Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Building upon LAMP, we propose SPACE, a Structure Preservation Aware Cross-modal Enhancement framework that explicitly leverages geometric priors. |
Yue Zhang; Zhiliang Wu; Yuxuan Hou; Hehe Fan; |
| 92 | Test-Time Adaptation for Graph Learning: A Systematic Survey Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this survey, we provide a comprehensive review of test-time adaptation on graphs, an emerging yet underexplored research direction. |
Jiayi Chen; Xin Zheng; Bo Li; Zeyu Wang; Yanqing Guo; Feng Xia; |
| 93 | HealthMamba: An Uncertainty-aware Spatiotemporal Graph State Space Model for Effective and Reliable Healthcare Facility Visit Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To advance existing research, we propose HealthMamba, an uncertainty-aware spatiotemporal framework for accurate and reliable healthcare facility visit prediction. |
Dahai Yu; Lin Jiang; Rongchao Xu; Guang Wang; |
| 94 | Beyond Top-1: Addressing Inconsistencies in Evaluating Counterfactual Explanations for Recommender Systems (Extended Abstract) Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose extending top-1 evaluation to list-wise top-k protocols that assess explanation effectiveness across multiple highly ranked outputs. |
Amir Reza Mohammadi; Andreas Peintner; Michael M. Müller; Eva Zangerle; |
| 95 | SpeciFuse: Learning Degradation-Type Specificity for Robust Infrared and Visible Image Fusion Under Composite Degradations Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing degradation-resistant infrared-visible image fusion methods struggle to effectively handle composite degradations, where multiple degradation types exhibit intricate coupling and mutual interference. To address this challenge, we propose SpeciFuse, an infrared-visible image fusion network that learns degradation-specific representations. |
Xuan Li; Zhaoming Feng; Xiang Yuan; Huabing Zhou; Jiayi Ma; |
| 96 | SAM-GPT: Hilbert Curve Enhanced Mamba for Brain Lesion Segmentation and VLM-based Analysis Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Based on the findings, we propose SAM-GPT, a novel framework that leverages segmentation-derived spatial priors to support VLM-based lesion classification. |
Jinfu Wang; Qiyuan Wang; Yunfei Liang; Kaipeng Wang; Jinhua Zhao; |
| 97 | A Comprehensive Survey of Interaction Techniques in 3D Scene Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: A curated list of the related papers mentioned in this work can be found at Awesome-Interactive-Techniques-in-3D-Scene-Generation-Lists. |
Yuqi Li; Siwei Meng; Chuanguang Yang; Weilun Feng; Junming Liu; Zhulin An; Yikai Wang; Yingli Tian; |
| 98 | Causal Path Alignment: Anchoring The Optimization Trajectory for Controllable In-Parameter Knowledge Editing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We diagnose the root cause as a shortcut learning pathology, where the optimization objective overfits subject representations while bypassing the essential relational context. To rectify this, we propose Causal Path Alignment (CPA), a principled framework designed to anchor the optimization trajectory to valid causal pathways. |
Xiyu Liu; Zhengxiao Liu; Naibin Gu; Zheng Lin; Weiping Wang; |
| 99 | DanceStyleCam: Style-Based 3D Multi-Style Dance Camera Movement Synthesis Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we introduce DanceStyleCam, a unified framework that incorporates the style-consistent characteristic into dance camera movement synthesis with diverse stylistic characteristics. |
Xiaoying Huang; Sanyi Zhang; Xirui Wang; Qin Zhang; Long Ye; |
| 100 | Band Together: Untargeted Adversarial Training with Multimodal Coordination Against Evasion-Based Promotion Attacks Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This phenomenon dilutes the attack effectiveness and leads robust training to underestimate worst-case risks. To address this issue, we propose Untargeted Adversarial Training with Multimodal Coordination (UAT-MC). |
Guanmeng Xian; Ning Yang; Philip S. Yu; |
| 101 | Manifold-Constrained Adversarial Training for Long-Tailed Robustness Via Geometric Alignment Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose \emph{Manifold-Constrained Adversarial Training (MCAT)}, a unified framework that enforces the semantic validity of adversarial examples by penalizing deviations from class-conditional manifolds in feature space, while promoting balanced geometric separation across classes via an ETF-inspired regularization. |
Guanmeng Xian; Ning Yang; Philip S. Yu; |
| 102 | Coarse-to-Fine Latent Guidance: A Multi-Scale Diffusion Transformer for Traffic Flow Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing methods struggle to reconcile these conflicting resolutions, leading to sub-optimal forecasting. To address this, we propose the Multi-Scale Spatial-Temporal Diffusion Transformer (MS-STDT). |
Zetao Li; Silin Zhou; Zheng Hu; Shimin Cai; Tao Zhou; |
| 103 | Disentangling Data Distribution for Optimal and Communication-Efficient Federated Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we propose a novel FedDistr algorithm, which employs stable diffusion models to decouple and recover data distributions. |
Xinyuan Zhao; Hanlin Gu; Lixin Fan; Yuxing Han; Qiang Yang; |
| 104 | One for Exploration and Another for Exploitation: A Dual-Population MOEA Framework with Provable Benefits Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Conversely, solutions with high exploratory potential that can lead the search toward more promising regions may themselves be of low quality. To address this issue, this paper proposes a dual-population MOEA with Exploration and Exploitation Decoupled (MOEA/EED): the exploration population uses a simple aging mechanism, while the exploitation population preserves the currently optimal solutions. |
Chenglin Jiang; Shengjie Ren; Zimin Liang; Miqing Li; Chao Qian; |
| 105 | Detection-Explanation-Improvement: A Closed-Loop Framework of Enhancing Anomaly Detection with Counterfactual Explanations Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While recent advances in explainable artificial intelligence have focused on explaining why individual instances are detected as anomalous, comparatively little attention has been paid to how such explanations can be systematically exploited to improve the detectors themselves. To address this gap, we propose EAD‑CE (Enhancing Anomaly Detection with Counterfactual Explanations), a model‑agnostic, closed‑loop framework that tightly integrates detection, explanation, and improvement. |
Peng Zhou; Zhiyong Huang; Yuanting Yan; |
| 106 | A3fford-HOI: Anatomy-Aligned Affordance Disentanglement for Fine-grained and Generalizable Hand Object Interaction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Along with HOI-X, we propose A3fford-HOI, a fine-grained and generalizable Hand Object Interaction framework with Anatomy-Aligned Affordance Disentanglement. |
Xurui Hu; Xingqun Qi; Bingkun Yang; Chen Su; Yiwei Ru; Junhui Yin; Muyi Sun; Man Zhang; |
| 107 | BEVFormer++: Temporal Amplified BEVformer with Explicit Parameter Prediction for Automatic Trajectory Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Vision-based trajectory prediction with BEV representations has achieved promising results, yet existing methods often suffer from limited temporal modeling and insufficient characterization of motion dynamics. To address these issues, we propose a temporally enhanced framework with explicit motion parameter prediction. |
Jiabin Fang; Xu Zhang; Zhuoming Ding; Xuan Liu; Meifang Zhang; Jin Yuan; Yuyi Wang; |
| 108 | G-VTM: A Multimodal Vision-Trajectory Model for Generalized Vehicle Trajectory Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This study faces two key challenges: (1) Generalize across junctions with heterogeneous map semantics and traffic behavioral patterns, where the former arises from differences in road topologies and traffic regulations, and the latter reflects diverse behavioral intentions of road users; (2) Scenario-adaptive interaction modeling, where single-modality trajectory learning captures local spatio-temporal correlation, but lacks map constraint and direction-aware interaction contexts. To overcome these challenges, we propose G-VTM, a generalized vision-trajectory model. |
Xinyue Zhang; Letian Gong; Yan Lin; Jinjun Cheng; Junlin Zhang; Guanyu Yao; Shengnan Guo; Youfang Lin; Shaojiang Wang; Huaiyu Wan; |
| 109 | Computing Epistemtic EF1 and Pareto-Optimal Allocations of Indivisible Chores Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we present a pseudo-polynomial time algorithm for computing an allocation of chores that is both EEF1 and PO. |
Jugal Garg; Aniket Murhekar; |
| 110 | PID-Controlled Constrained RL for Hub-based Joint Pricing, Dispatching, and Routing with Service Guarantees Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Conventional constrained reinforcement learning often struggles in this mixed continuous–combinatorial action space, suffering from oscillatory behavior in Lagrangian dual variables and unstable constraint satisfaction. To address this, we propose PID-SACA, a unified framework that integrates an entropy-regularized actor–critic policy for continuous pricing and dispatching assisted by an embedded routing solver for execution-aware feedback. |
Pengfei Du; Yucen Gao; Bin Wang; Xiaochun Yang; |
| 111 | Verifiable PDE Reasoning and Modeling with Neurosymbolics Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Second, our Lean Finder accelerates PDE formalization via a semantics-aware search engine for Lean/Mathlib that retrieves relevant theorems, outperforming GPT models and gaining significant traction in the AI-for-math community. Through these efforts, we aim to design a semantics-first LLM that autoformalizes informal PDE problems into machine-checked specifications and synthesizes solver-ready code. |
Wuyang Chen; |
| 112 | Toward Reliable Agents Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Learned agents that control traffic signals or call software tools are usually trained in simulators or fixed benchmarks, yet must act in worlds that differ. Many reliability … |
Hua Wei; |
| 113 | Resisting Label Drift: Real-Time Multi-View Clustering with Semantic Consistency Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In addition, they neglect semantic consistency, causing the cluster labels of identical concepts to drift unpredictably due to independent processing. To address these limitations, we propose a real-time semantic consistent incremental multi-view clustering framework. |
Qi Liu; Suyuan Liu; Hao Tan; Yangfan Du; Bowen Zhang; Wenpeng Lu; Xinwang Liu; |
| 114 | ManiSplat: Manipulation Trajectory Synthesis from Monocular Video Via Decoupled 3D Gaussian Splatting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While recent advances in 3D Gaussian Splatting have enabled high-fidelity static reconstruction, extending it to interactive environments with articulated robots and manipulable objects remains difficult due to complex contact interactions and abrupt pose changes. To address these challenges, we introduce ManiSplat, a unified framework that reconstructs controllable and decoupled Gaussian digital twins directly from monocular ego-view robotic videos. |
Wenhao Hu; Haonan Zhou; Liu Liu; Yun Du; Xinjie Wang; Ziang Li; Zhizhong Su; Gaoang Wang; |
| 115 | Online Self-Calibration Against Hallucination in Vision-Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To obtain reliable self-supervision for online learning, we identify a Generative-Discriminative Gap within LVLMs, where models exhibit higher accuracy on discriminative verification than open-ended generation. Leveraging this capability, we propose Online Self-CAlibRation (OSCAR), a framework that integrates Monte Carlo Tree Search with a Dual-Granularity Reward Mechanism to construct preference data and iteratively refines the model via Direct Preference Optimization. |
Minghui Chen; Chenxu Yang; Hengjie Zhu; Dayan Wu; Qingyi Si; Zheng Lin; |
| 116 | TrafficPDE: A Guidebook to Deployable AI-Driven Transportation Systems Through The Perception-Decision-Explanation Triangle Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Deploying AI in real-world intelligent transportation systems (ITS) remains hard: traffic data is noisy and incomplete, learned policies rarely transfer to new cities, and black-box models cannot earn the trust of operators and public officials. Drawing on years of joint experience in ITS industry and academia (including traffic signal control systems deployed across multiple cities and AI for one of the world’s busiest metro networks), this paper presents TrafficPDE: a practitioner’s guidebook organized around the Perception-Decision-Explanation (PDE) triangle. |
Ziyue Li; |
| 117 | World4V2X: A Consistency-driven World Model for Robust V2X Cooperative Perception Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Therefore, when observations are partially occluded or degraded, these methods are unable to leverage historical context for compensation, leading to unstable perception and reduced detection accuracy. To address these challenges, we propose World4V2X, the first world model framework tailored for V2X cooperative perception. |
Rui Wang; Shuai Wang; Xiangyi Qin; Ze Yu; Xiaojun Tan; |
| 118 | Diverge to Converge: Mutual Heterogeneous Learning for Robust Pruning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose Mutual Heterogeneous Learning (MHL), a framework enabling robust pruning via single-model inference. |
Jinhui Yu; Zikai Zhang; Khaled A. Harras; Yidong Li; |
| 119 | Retrieval-Guided Completion Hashing with Token–Patch Alignment for Incomplete Cross-Modal Retrieval Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, in practical applications, multimodal data often suffer from modality missing issues, which cause semantic incompleteness and thus severely impair both cross-modal alignment and hashing-based retrieval performance. To address these issues, this paper proposes a novel incomplete cross-modal retrieval framework, called retrieval-guided completion hashing with token–patch alignment (RGCH-TPA). |
Zhixi Luo; Zhenqiu Shu; |
| 120 | Performance-Driven Demonstration Selection for In-Context Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Most existing selection methods rely on heuristic or proxy signals, such as similarity, diversity, or uncertainty, and select demonstrations independently, which may misalign with downstream performance and overlook set-level composition effects. Therefore, we propose Performance-Driven Demonstration Selection (PDDS), which directly aligns demonstration selection with ICL performance. |
Wenqiang Wang; Mingbo Yang; Aiping Zhang; Yan Xiao; Peng Chen; Jianjie Huang; Xiaochun Cao; |
| 121 | Coarse-to-Fine Domain Incremental Learning with Attentive Distillation for Mining Footprint Segmentation in Multispectral Imagery Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Although large-scale datasets with coarse boundaries are widely available, leveraging them to improve fine-grained segmentation is challenging due to significant domain shift. To address this, we propose MineC2FNet, a coarse-to-fine domain incremental learning framework that exploits abundant coarse data to enhance fine-grained mining footprint segmentation. |
Alif Tri Handoyo; Vincent C.S. Lee; Rizka Widyarini Purwanto; Alex M. Lechner; Deanna Kemp; Muhamad Risqi U. Saputra; |
| 122 | MFMSRNet: An Interpretable Multi-frequency and Multi-scale Riemannian Network for Motor Imagery Decoding Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This work proposes the Multi-frequency and Multi-scale Riemannian Network (MFMSRNet), an interpretable end-to-end geometry-aware framework for MI EEG decoding on the SPD manifold. |
Wenhao Rao; Xujie Zhao; Jianhui Zhao; Bo Du; Feixiang Tang; |
| 123 | D²G-TO: Task-aware and OOD-guided Discrete Graph Diffusion for Robust CNS Drug Discovery Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In an Alzheimer’s disease case study, we subject the generated molecules to cross-property pharmacological prediction and systematic ADMET profiling, followed by structure based molecular docking against BACE-1 to assess binding-mode plausibility. |
Xue Zhai; Chu-An Yang; Minghao Liu; Xu Dong; Han Wang; Weiwei Han; Ting Gao; LiHong Hu; |
| 124 | StreamMTS: Towards Streaming Multivariate Time Series Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a streaming MTS prediction framework. |
Binwu Wang; Jiaming Ma; Yudong Zhang; Pengkun Wang; Zhengyang Zhou; Xu Wang; Yang Wang; |
| 125 | DiSGMM: A Method for Time-varying Microscopic Weight Completion on Road Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: During a time slot, the available weights typically cover only some road segments. Weight completion recovers distributions for the weights of every road segment at the current time slot.This problem involves two challenges: (i) contending with two layers of sparsity, where weights are missing at both the network layer (many road segments lack weights) and the segment layer (a segment may have insufficient weights to enable accurate distribution estimation); and (ii) achieving a weight distribution representation that is closed-form and can capture complex conditions flexibly, including heavy tails and multiple clusters.To address these challenges, we propose DiSGMM that combines sparsity-aware embeddings with spatiotemporal modeling to leverage sparse known weights alongside learned segment properties and long-range correlations for distribution estimation. |
Yan Lin; Jilin Hu; Shengnan Guo; Christian S. Jensen; Youfang Lin; Huaiyu Wan; |
| 126 | AnoMamba: Aligning Reconstruction with Time Series Anomaly Detection Via Selective Global Dependency Modeling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Consequently, anomalies that violate global dependencies can also be reconstructed well, leading to a misalignment between reconstruction and detection. To address this challenge, we propose AnoMamba, a novel TSAD framework that aligns reconstruction with anomaly detection by enhancing global dependency modeling. |
Junqi Chen; Xu Tan; Jie Chen; Susanto Rahardja; |
| 127 | Temporal-Synergistic Policy Optimization for Unsupervised Low-Light Image Enhancement Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Furthermore, they often lead to artifacts or unnatural visual effects in this ill-posed inverse problem. To address these issues, we propose an unsupervised low-light enhancement framework based on Group Relative Policy Optimization (GRPO), which utilizes perceptual preferences to directly optimize the diffusion policy. |
Yuanfei Bao; Dong Li; Jie Huang; Xingbo Wang; Xueyang Fu; |
| 128 | Interactive All-in-One Image Restoration and Fusion Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Supervised infrared-visible image fusion (IVIF) often overfits limited training distributions, creating a critical generalization gap under open-world degradations (rain, haze, low light, noise, blur). To address this issue, we propose AIR-Fusion, a parameter-efficient adaptation of a frozen, restoration-capable latent diffusion backbone for degraded IVIF without full fine-tuning, transferring restoration priors for robust fusion. |
Bing Cao; Qiang Zhang; Xingxin Xu; Pengfei Zhu; |
| 129 | Neurosymbolic Framework for Concept-Driven Logical Reasoning in Skeleton-Based Human Action Recognition Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce a neurosymbolic formulation of skeleton-based HAR that reframes action recognition as concept-driven first-order logical reasoning over motion primitives. |
Talha Ilyas; Deval Mehta; Zongyuan Ge; |
| 130 | Towards Fine-Grained Code-Switch Speech Translation with Semantic Space Alignment Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Previous studies mainly rely on the models themselves to implicitly learn semantic representations and resort to costly manual annotations. To mitigate these limitations, we propose enhancing Large Language Models (LLMs) with a Mixture-of-Experts (MoE) speech projector composed of language expert groups, where each group specializes in the semantic space of a specific language for fine-grained speech feature modeling. |
Yan Gao; Yazheng Yang; Zhibin Lan; Yidong Chen; Min Zhang; Daimeng Wei; Derek F. Wong; Jinsong Su; |
| 131 | Tracking Topological Shifts: How Can Dynamic Graph Invariant Learning Enable Reliable Out-of-Time Spatio-Temporal Prediction? Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While out-of-distribution (OOD) learning holds promise for robustness, existing methods rely on static graph structures, failing to capture the inherent topological dynamics of real-world traffic systems and thus limiting long-term deployment reliability. To bridge this gap, we propose DynaSTar, a Dynamic Spatio-Temporal Graph Invariant Learning model designed for reliable out-of-time (OOT) traffic prediction under evolving topologies. |
Xinyan Hao; Huaiyu Wan; Shengnan Guo; Shaojiang Wang; Youfang Lin; |
| 132 | LISA: Language-guided Interference-aware Spatial-Frequency Attention for Driver Gaze Estimation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose LISA, a Language-guided Interference-aware Spatial-Frequency Attention framework that combines frequency-domain priors with vision-language knowledge. |
Jun Ma; Zhenye Yang; Ruichen Zhou; Pei Zhang; Huan Li; Jinpeng Chen; |
| 133 | Structured Modality-Aware Token Interaction for Multimodal Medical Imaging Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose Modality-Aware Token Interaction (MATI), an architecturally lightweight and backbone-agnostic module that structures multimodal interaction within a single token stream by partitioning embedding channels into modality-aligned subspaces. |
Selene Tomassini; Hafiza Ayesha Hoor Chaudhry; Alessandro Galdelli; Paolo Giorgini; |
| 134 | ICFD-31k: A Large-Scale Dataset and Benchmark for Real-Time Conversational Fraud Detection Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Furthermore, the lack of large-scale, publicly available datasets remains a critical barrier impacting research on robust, real-time countermeasures. In view of this, the proposed work introduces ICFD-31k, the first Indian Conversational Fraud Dataset, representing a new benchmark containing over 31,000 realistic conversational transcripts. |
Rishi Ahuja; Kumar Prateek; Simranjit Singh; |
| 135 | Beyond The Clouds: Reliable and Cloud-Aware Spatiotemporal Fusion Via Adversarial Regression Wavelets Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing methods rely on cloud-free reference images, a constraint that fails in realistic, cloud-prone scenarios. To overcome this, we propose the Cloud-Aware Wavelet Generative Adversarial Network (CLAW-GAN), a novel framework for high-fidelity reconstruction under cloud-contaminated conditions. |
Sichen Lu; Mingfei Li; Juanjuan Jing; Junhua Yu; Lei Yang; Boyang Nie; Jinsong Zhou; |
| 136 | FAIRGAME: A Framework for AI Agents Bias Recognition Using Game Theory (Extended Abstract) Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present FAIRGAME (Framework for AI Agents Bias Recognition using Game Theory), an open-source framework that simulates game-theoretic scenarios with LLM-based agents to systematically uncover biases arising from model choice, language, agent personality, and more. |
Alessio Buscemi; Daniele Proverbio; Alessandro Di Stefano; The-Anh Han; German Castignani; Pietro Liò; |
| 137 | From Values to Tokens: An LLM-Driven Framework for Context-Aware Time Series Forecasting Via Symbolic Discretization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Despite recent advances, forecasting accuracy remains limited due to the challenge of integrating historical numerical sequences with contextual features, which often comprise unstructured textual data. To address this challenge, we propose TokenCast, a large language model (LLM) driven framework that leverages language-based symbolic representations as a unified intermediary for context-aware time series forecasting. |
Xiaoyu Tao; Shilong Zhang; Mingyue Cheng; Daoyu Wang; Tingyue Pan; Bokai Pan; Changqing Zhang; Shijin Wang; |
| 138 | Safe Multi-Objective Linear Bandits with Hierarchical Preferences Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we study a multi-objective stochastic linear bandit framework that incorporates hierarchical preferences together with safety constraints, requiring the learner to remain competitive with respect to a known baseline policy. |
Bo Xue; Mengxia He; Yilu Liu; Ji Cheng; Zhe Zhao; Qingfu Zhang; |
| 139 | Opinion Maximization in Social Networks: An Inverse Optimization Perspective Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper provides an inverse optimization perspective for OM by reformulating it as an opinion minimization (OMin) problem, whose objective function holds succinct expression and desired properties. |
Yilu Liu; Bo Xue; Yiming Yao; Qingfu Zhang; |
| 140 | LLM As Clinical Graph Structure Refiner: Enhancing Representation Learning in EEG Seizure Diagnosis Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Motivated by the remarkable reasoning and contextual understanding capabilities of large language models (LLMs), we explore the idea of using LLMs as graph edge refiners. |
Lincan Li; Zheng Chen; Yushun Dong; |
| 141 | From Compression to Construction: Pseudo Neighbor Augmentation Sampling for Dynamic Link Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: It inevitably makes them lose rich context such as high order structural information and temporal patterns, and often underperform on nodes with sparse historical interaction with other nodes. To this aim, we propose a novel context construction based approach named PeNS that adopts Pseudo Neighbor Augmentation Sampling Strategy for more accurate dynamic link prediction. |
Zhigang Yu; Hao Yan; Changjun Fan; Senzhang Wang; |
| 142 | VGAS: Value-Guided Action-Chunk Selection for Few-Shot Vision-Language-Action Adaptation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We study few-shot VLA adaptation from a generation-selection perspective and propose a novel framework, VGAS (Value-Guided Action-chunk Selection). |
Changhua Xu; En Yu; Junyu Xuan; Jie Lu; |
| 143 | Toward Synthesizability-Aware Multi-Step Retrosynthetic Planning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose GuideRetro, a synthesizability-aware framework for multi-step retrosynthetic planning that integrates global synthesizability knowledge into step-wise retrosynthetic prediction. |
Yujie Chen; AJie Lin; Tengfei Ma; Shu Wu; Leyi Wei; Yiping Liu; Xiangxiang Zeng; |
| 144 | Accelerated Distributed Riemannian Optimization Algorithms with Random Shuffling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose accelerated distributed Riemannian stochastic gradient descent algorithms with random shuffling in the cases of both centralized and decentralized learning. |
Wenhan Xian; Heng Huang; |
| 145 | DELTA: Disentangled Hierarchical Interaction and Adaptive Adjustment for Emotion and Intent Understanding in Multimodal Conversations Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, prior works largely ignore redundancy interference and suffer from insufficient interaction and inter-task noise propagation due to their reliance on shallow mechanisms. To overcome these limitations, we propose a novel framework named Disentangled Hierarchical Interaction and Adaptive Adjustment (DELTA) for MC-EIU. |
Shenjie Jiang; Xiangfeng Liu; Xianghua Li; Xuecheng Wu; |
| 146 | Bridging Inter-View and Client Heterogeneity: Federated Multi-View Clustering Under Non-IID Data Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In practice, non-IID distributions with partial and imbalanced categories cause clients to learn biased and local representations, leading to model bias and unstable federated training performance. To address these issues, we propose a FedMVC framework called Bridging Inter-View and Client Heterogeneity: Federated Multi-View Clustering under Non-IID Data (H²-FedMVC), which tackles both inter-view and client heterogeneity in mixed-view settings. |
Jiazhen Wang; Xinyue Chen; Shuaiyu Liu; Zican He; Yazhou Ren; Yi Wang; Shuyin Xia; |
| 147 | Addressing Downward Memory Loss in Hierarchical GNN Forecasters Through Memory-Buffered Decoding Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose HiGFlow, an HGNN forecaster that explicitly preserves multiscale trends through a self-updating memory buffer that integrates into the coarse-to-fine information flow. |
Thomas Bailie; S. Karthik Mukkavilli; Varvara Vetrova; Yun Sing Koh; |
| 148 | First Mathematical Runtime Analyses of Multi-Objective Evolutionary Algorithms for Multi-Valued Decision Variables Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we begin to fill this research gap. |
Mingfeng Li; Zheng Cheng; Weijie Zheng; Benjamin Doerr; |
| 149 | Toward A More Discriminative Learnware Paradigm Via Explicitly Distinctive Specification Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we design an Explicitly Distinctive Specification (EDS) that enforces specification uniqueness, improving the discriminative capability of the learnware paradigm and avoiding ambiguity caused by overlapping task distributions. |
Wenlu Yang; Wei Chen; Zhenan He; |
| 150 | Harmonizing Federated Heterogeneous Optimization Via Adaptive Objective Rectification Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we introduce HaFedHo, an adaptive objective rectification method that harmonizes local training with the ideal data-centralized objective, requiring minimal modifications to the standard federated learning framework. |
Jianrong Lu; Bangwei Li; Zhuoya Gu; Peng Fang; Ziming Zhao; Jianhai Chen; |
| 151 | Controlling Decision Drift in Multimodal Sentiment Analysis with Missing Modalities Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In addition, unreliable modalities may dominate fusion, resulting in representation shift across modality combinations and unstable sentiment representations. To address these challenges, we propose a two-level reference alignment framework. |
Chenglizhao Chen; Yuchen Cao; Xinyu Liu; Mengke Song; Guisheng Zhang; Xiaomin Yu; |
| 152 | Mitigating Tool Overuse for LLMs Via Active Knowledge Boundary Probing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: (2) Tool overuse propagation: the student inherits the misaligned tool-use strategy from teacher model. To address these challenges, we propose RADAR, an automated framework for knowledge boundary discovery and tool overuse mitigation. |
Zhaoyu Yang; Wenjun Ke; Yuanyao Li; Yuchen Liu; Junqi Xu; Peng Wang; Hengyuan Xu; |
| 153 | Probabilistic Verification of Recurrent Neural Networks for Single and Multi-Agent Reinforcement Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose RNN Probabilistic Verification (RNN-ProVe), a probabilistic framework that estimates the likelihood of undesired behaviors in RNN-based policies. |
Luca Marzari; Enrico Marchesini; |
| 154 | A Survey on The Verification of Reinforcement Learning Policies Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce a taxonomy that clarifies relationships among existing approaches along three axes: verification paradigm (formal versus probabilistic), temporal scope (step-wise versus multi-step), and guarantees strength. |
Luca Marzari; Ezio Bartocci; Enrico Marchesini; |
| 155 | Bridging The Biophysical Gap: Holistic Environmental Awareness for 3D Linker Design Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing methods often suffer from environmental blindness, treating the inter-fragment space as a vacuum and yielding candidates with poor binding affinity or severe steric clashes. To address this, we propose LinkerBridge, an equivariant framework that unifies biochemical semantics with physical constraints through two innovations: a Contextual Interaction-Aware Representation module that internalizes pre-existing biochemical semantics, and a Differentiable Physical Guidance mechanism derived from Van der Waals potentials to steer generation away from collision zones. |
Mengwei Sun; Chengwei Ai; Xiaoyi Liu; Shiqiang Ma; Qiaozhen Meng; Fei Guo; |
| 156 | Robust Contrastive Graph Clustering with Adaptive Local-Global Integration Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: These limitations lead to suboptimal node representations, especially in real-world graphs with fragmented structures and ambiguous cluster boundaries. To address these limitations, a contrastive graph clustering framework is proposed to jointly integrate multi-scale local structures with global semantics via attention mechanisms. |
Lei Zhang; Fubo Sun; Haipeng Yang; Zhong Guan; Likang Wu; |
| 157 | CodeDelegator: Mitigating Context Pollution Via Role Separation in Code-as-Action Agents Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose CodeDelegator, a multi-agent framework that separates planning from implementation via role specialization. |
Tianxiang Fei; Cheng Chen; Yue Pan; Mao Zheng; Mingyang Song; |
| 158 | G2C-MT: Graph-Guided Context Selection for Document-Level Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Effective document-level machine translation (DocMT) requires capturing long-range discourse dependencies. Recent work has explored retrieval-based and discourse-aware context … |
Baijun Ji; Zixuan Zhou; Xiangyu Duan; Yu Liu; Longbo Sun; Rupu Wei; Bohong Zhao; |
| 159 | PROB-EMOE: A Probabilistic Ensemble Mixture-of-Experts Framework for Metro Network Expansion Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing models often struggle to capture heterogeneous interaction patterns in changing topologies and overlook inherent uncertainty and over-dispersion issues. To bridge these gaps, we propose PROB-EMOE, a planning-oriented probabilistic framework tailored for network expansion. |
Fangyi Ding; Zhan Zhao; Zhi Li; Xudong Guo; Ning Zhang; Yamin Wang; Yihong Tang; |
| 160 | Latents-Inv:Robust Semantic Watermark Via Dual-Path Mutual Information Redundancy for Diffusion Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing methods are highly vulnerable to adversarial attacks, especially geometric transformations (e.g., rotation, cropping) and latent-space manipulations via proxy models, limiting the reliability of watermark verification in practical deployment. To address this issue, we propose a robust and fully reversible, flow-based watermarking framework with dual encoding paths, which preserves high visual fidelity of watermarked image while ensuring resilient identity recovery under adversarial attacks. |
Cong Li; Lingyun Yu; Peiqi Jiang; Hongtao Xie; |
| 161 | GeoMind: Explicit Spatial Reasoning Via Dual-Reference Geometric Modeling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Their reliance on implicit geometric encoding often leads to severe hallucinations and inconsistencies in spatial reasoning tasks. To address this, we introduce GeoMind, a model-then-reason framework that employs a single LLM to autoregressively generate an explicit Geometric Description Language (GDL) map, serving as a grounded context to derive the final answer. |
Xing Wei; Aoxiang Tian; Shaofan Liu; Jiansheng Peng; Chong Zhao; Xiang Bi; Yang Lu; Benhong Zhang; Fan Yang; |
| 162 | Beyond Client Clustering: Fine-Grained Preference Alignment in Federated RLHF Via Self-Evolving Routing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing approaches typically rely on rigid client-level clustering, which overlooks intra-client heterogeneity and fails to adapt to the multifaceted needs of individual users. To address this, we propose FedPrism, a novel framework that shifts alignment granularity from the coarse client level to the precise instance level. |
Ke Wang; Shaojing Fu; Yuchuan Luo; Guilin Deng; Silong Chen; Zheng Yuan; Lin Liu; |
| 163 | Property Enhanced Instruction Tuning for Multi-Task Molecule Generation with Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this work, we present a two-step framework PEIT (Property Enhanced Instruction Tuning) to improve LLMs for molecular-related tasks. |
Xuan Lin; Long Chen; Yile Wang; Yangyang Chen; Xiangxiang Zeng; |
| 164 | HiCD: Hyperbolic Insight Through Decomposed Educational Graphs for Long-Tailed Cognitive Diagnosis Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing graph-based CD models struggle to handle the pronounced long-tail distributions in educational data, where most students and concepts interact with only a limited number of exercises, resulting in suboptimal representation learning and poor generalization to low-frequency instances. To address this challenge, we propose HiCD (Hyperbolic insight for Cognitive Diagnosis), a novel hyperbolic model that embeds students, exercises, and concepts into non-Euclidean space. |
Shengwei Ji; Wenli Wang; Yongqiang Xie; Fei Liu; Yonghui Yang; |
| 165 | CoDA: Co-adaptive Dual-path Alignment for Vision-Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose Co-adaptive Dual-path Alignment (CoDA), a new adaptation framework that explicitly disentangles and coordinates cross-modal semantic alignment and intra-modal structural consistency. |
Yi Zhang; Rui Zhu; Channi Li; Xiaoxu Li; Zhanyu Ma; Jing-Hao Xue; |
| 166 | Absorbing Gradient Conflicts: Modeling Semantic Variance Via Kent Distributions for Cross-Modal Hashing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, prevalent methods model class proxies as deterministic points in the embedding space. This rigid assumption causes severe gradient conflicts in multi-label scenarios, where gradient conflicts arising from label co-occurrence lead to severe gradient contention and optimization collapse.To resolve this, we propose Kent-based Distributional Proxy Hashing (KDPH), a novel framework that shifts proxy representation from static points to flexible anisotropic Kent distributions on the hypersphere. |
Hengjie Zhu; Dayan Wu; Zihao Zhang; Xinze Liu; Jingxuan Yu; Peng Fu; Zheng Lin; Weiping Wang; |
| 167 | Harnessing Multiple Large Language Models: A Survey on LLM Ensemble Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: This paper presents the first systematic review of recent developments in LLM Ensemble. |
Zhijun Chen; Xiaodong Lu; Jingzheng Li; Pengpeng Chen; Zhuoran Li; Kai Sun; Yuankai Luo; Qianren Mao; Ming Li; Likang Xiao; Dingqi Yang; Yikun Ban; Hailong Sun; |
| 168 | SRJudge: Empowering Large Language Models with Selective Reasoning for Fine-Grained Knowledge Concept Tagging Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a novel three-stage Select-Reason-Judge (SRJudge) framework, which empowers LLMs with selective reasoning capability for fine-grained knowledge concept tagging. |
Zhiwei Yang; Jiahua Yang; Huiru Lin; Xing Chen; Quanlong Guan; |
| 169 | Improving Group Robustness on Spurious Correlation Via Evidential Alignment (Extended Abstract) Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose Evidential Alignment, a framework that leverages uncertainty quantification to identify and suppress spurious correlations without requiring group annotations. |
Wenqian Ye; Guangtao Zheng; Aidong Zhang; |
| 170 | Variable-Oriented Adaptive Singleton Consistency Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a variable-oriented adaptive singleton consistency, namely VOASC, that could be applied in general-purpose constraint solvers. |
Yaling Wu; Hongbo Li; Minghao Yin; |
| 171 | LoCo: Low-Rank Compositional Rotation Fine-Tuning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce Low-rank Compositional Orthogonal fine-tuning (LoCO), a novel PEFT method that constructs orthogonal transformations through low-rank skew-symmetric matrices and compositional rotation chains. |
An Nguyen; Jaesik Choi; Anh Tong; |
| 172 | SpecBridge: Spectral Structure Alignment and Transitive Bridging for 3D–2D–Text Pre-Training Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This work introduces SpecBridge, a 3D-2D-Text pre-training framework that leverages CLIP priors as a foundational bridge to connect three modalities by synergizing spectral graph theory with transitive semantic learning. |
Dong Wang; Jie Jiang; Weidong Min; Lixin Zhan; Xinpeng Zhao; Ze Zhang; |
| 173 | BioDisco: Multi-Agent Hypothesis Generation with Dual-Mode Evidence, Iterative Feedback and Temporal Evaluation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing automated methods often struggle to generate novel and evidence-grounded hypotheses, lack robust iterative refinement and rarely undergo rigorous temporal evaluation for future discovery potential. To address this, we propose BIODISCO, a multi-agent framework that draws upon language model-based reasoning and a dual-mode evidence system (biomedical knowledge graphs and automated literature retrieval) for grounded novelty, integrates an internal scoring and feedback loop for iterative refinement, and validates performance through pioneering temporal and human evaluations and a Bradley-Terry paired comparison model for statistical assessment. |
Yujing Ke; Kevin George; Kathan Pandya; Gerrit Großmann; David B. Blumenthal; Maximilian Sprang; David A. Selby; Sebastian Vollmer; |
| 174 | AMR-LLM: Knowledge-Enhanced Multi-Modal Automatic Modulation Recognition Via Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we propose a knowledge-enhanced multi-modal automatic modulation recognition framework based on large language model (AMR-LLM). |
Shen Hu; Yuhua Qian; Xinyan Liang; Zikun Jin; Jiaqian Zhang; Jiangfeng Zhang; |
| 175 | Sparsity in Federated Learning: A Survey Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this survey, we introduce a novel taxonomy of sparse FL methods that systematically organizes the existing literature according to their core objectives and methodological choices. |
Alessio Mora; Adriano Guastella; Lorenzo Sani; Paolo Bellavista; Nicholas D. Lane; |
| 176 | GenID: A Generalizable Physical-Layer Device Identification Method for Out-of-Distribution Environments Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, its deployment in modern full-duplex Ethernet networks faces two major challenges: (1) the presence of Out-of-Distribution (OOD) data caused by temporal distribution shift and diverse local transmitters, and (2) the difficulty of environment-agnostic device identification, where the unique features of target devices are often obscured in mixed signals. To address these challenges, we propose GenID, which consists of two core components. |
Yawei Zhang; Lanting Fang; Di Yao; Kaiyu Feng; Shuliang Wang; |
| 177 | Spatial Pattern Matching: A Survey Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Recent developments in Artificial Intelligence (AI) have led to new ways for users to search through vast information. However, users may have questions that are grounded in the … |
Nicole R. Schneider; Kent O’Sullivan; Hanan Samet; |
| 178 | Unsupervised Graph-Level Anomaly Detection Via Multi-granular Graph Structure Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose M-GLAD, an unsupervised GLAD method via multi-granular graph structure learning. |
Ge Zhang; Huimei Li; Guohao Sun; Xiu Fang; Xixun Lin; Xiaobao Wang; Pengfei Jiao; Liang Yang; |
| 179 | Neuro-Symbolic AI for Evidence-Based Renewable Energy Planning in Sub-Saharan Africa Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This information is dispersed as unstructured knowledge across scientific papers, making the task manually demanding for decision and policy makers. In this work, we combine the strength of Large Language Models (LLMs) and structured knowledge (Knowledge Graphs) in a neuro-symbolic framework to tackle this issue. |
Janice Anta Zebaze; Azanzi Jiomekong; Germaine Djuidje Kenmoe; Maria-Esther Vidal; |
| 180 | Learning PDE Solvers with Physics and Data: A Unifying View of Physics-Informed Neural Networks and Neural Operators Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we propose a unifying perspective that places two dominant paradigms, Physics-Informed Neural Networks (PINNs) and Neural Operators (NOs), within a shared design space. |
Yilong Dai; Shengyu Chen; Ziyi Wang; Xiaowei Jia; Yiqun Xie; Vipin Kumar; Runlong Yu; |
| 181 | PURE: Purging Unrelated Representations for Content-Agnostic Forgery Detection Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We observe that this failure is mainly caused by content shortcuts, where detectors spuriously couple forgery artifacts with semantic content, such as object categories or demographic attributes, learning content–label correlations instead of generalizable forgery patterns. To address this issue, we propose PURE (Purging Unrelated Representations for Content-Agnostic Forgery Detection), which achieves content-agnostic detection through two complementary components: a Causal Semantic Generative (CSG) mechanism that disentangles semantic representations from forgery-irrelevant nuisance factors, and a Gaussian Mixture Model (GMM)-based prototype alignment module that suppresses category-specific content bias. |
Xinyu Wu; Dong Li; Minglai Shao; Xintao Wu; Zhong Chen; Chen Zhao; |
| 182 | LiSA: Leveraging Link Recommender to Attack Graph Neural Networks Via Subgraph Injection (Extended Abstract) Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Specifically, the link recommender is mislead to propose links between targeted victim nodes and the subgraph, encouraging users to unintentionally establish connections and that would degrade the node classification accuracy, thereby facilitating a successful attack. To address this, we present the LiSA framework, which employs a dual surrogate model and bi-level optimization to simultaneously meet two adversarial objectives. |
Wenlun Zhang; Enyan Dai; Kentaro Yoshioka; |
| 183 | JointScaler: A Hierarchical Multi-Indicator Distribution Forecasting Approach for Uncertainty-Aware Joint Scaling in Cloud Services Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing approaches forecast service indicators in isolation, ignore forecasting uncertainty, and scale resource types independently, violating bundled resource constraints and degrading service quality. Therefore, we propose JointScaler, a learning-based framework for multi-indicator distribution forecasting and uncertainty-aware scaling. |
Yang Luo; Zhemeng Yu; Yikang Fu; Wei Lu; Lintao Ma; Xiaofeng Gao; Guihai Chen; |
| 184 | Multi-View Ensemble for Time Series Anomaly Detection Via Coupling Flows Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose FlowFuse, a multi-view ensemble framework with coupling flow-based score fusion for time series anomaly detection. |
Wanghui Qiu; Chenxi Liu; Shiyan Hu; Zhengyu Li; Chenjuan Guo; Bin Yang; |
| 185 | Adaptive TD-Lambda for Cooperative Multi-agent Reinforcement Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We apply the proposed method on two competitive baseline methods, QMIX for value-based algorithms, and MAPPO for AC-based algorithms, over SMAC benchmarks and Gfootball academy scenarios, and demonstrate consistently competitive or superior performance compared to other baseline approaches with static λ values. |
Yue Deng; Zirui Wang; Yin Zhang; |
| 186 | Unrestricted Targeted Deep Hashing Attack Via Contrastive Latent Diffusion Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose UTDHA, the first unrestricted targeted attack for deep hashing models using contrastive-guided latent diffusion. |
Fan Yang; Chuan Ma; Yuhui Zheng; Xiaobo Shen; Joey Tianyi Zhou; |
| 187 | PerFlow: Physics-Embedded Rectified Flow for Efficient Reconstruction and Uncertainty Quantification of Spatiotemporal Dynamics Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we propose PerFlow, a Physics-embedded rectified Flow for efficient sparse reconstruction and uncertainty quantification of spatiotemporal dynamics. |
Hao Zhou; Rui Zhang; Han Wan; Hao Sun; |
| 188 | DeepSTE: Deep Spectral Temporal Embeddings for Dynamic Graph Representation Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose DeepSTE, a deep spectral temporal embedding framework for dynamic graphs. |
Qiang Huang; Ke Liu; Renjie Gong; Sijing Zhang; Hao Wang; Shanshan Feng; Xiao Yan; Jiawei Jiang; |
| 189 | Parallelizing Multi-Objective A* Search (Extended Abstract) Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper presents a novel search framework that enables efficient parallelization of MOA* through different objective orderings and a unique upper-bounding strategy that, in certain cases, allows the problem dimensionality to be reduced to one. |
Saman Ahmadi; Nathan R. Sturtevant; Andrea Raith; Daniel Harabor; Mahdi Jalili; |
| 190 | Obstacle Avoidance and Trajectory Tracking of Redundant Manipulators with Unknown Physical Parameters Under Multiple Constraints Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Considering that quadratic programming (QP) can integrate desired behaviors with constraints into a unified optimization framework and can be solved online in real time, this paper formulates the collision-free trajectory tracking of redundant manipulators with uncertain structure as a QP problem, which describes the trajectory tracking, obstacle avoidance and joint motion limits simultaneously. |
Lei Jia; Hui Deng; |
| 191 | RegionCache: Semantic-Aware Region Reuse for Efficient Multi-Turn Image Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we propose RegionCache, a semantic-aware reuse framework for multi-turn image editing that selectively reuses diffusion states from unchanged regions. |
Peizheng Li; Xin Ai; Hanyuan Liu; Qiange Wang; Yanfeng Zhang; |
| 192 | Harmonizing Real-Time Constraints and Long-Horizon Reasoning: An Asynchronous Agentic Framework for Dynamic Scheduling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Although Large Language Models (LLMs) offer advanced reasoning capabilities to bridge this gap, their substantial inference latency is incompatible with the millisecond-level decision cycles of industrial control systems. To resolve this conflict, we introduce RACE-Sched, an asynchronous agent-based framework that decouples policy execution from logical reasoning via a dual-stream architecture. |
Shijie Cao; Yuan Yuan; Jing Liu; |
| 193 | A Hybrid Modeling Framework for Crop Prediction Tasks Via Dynamic Parameter Calibration and Multi-Task Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a hybrid modeling approach that uses a neural network to parameterize a differentiable biophysical model and leverages multi-task learning for efficient data sharing across crop cultivars in data limited settings. |
William Solow; Paola Pesantez-Cabrera; Markus Keller; Lav Khot; Sandhya Saisubramanian; Alan Fern; |
| 194 | A Survey on Value Alignment in Agentic AI Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Guided by this framework, we conduct an in-depth analysis along the technical stack: at the LLM level, we examine value injection mechanisms through pretraining and post-training; at the single-agent level, we focus on representation and injecting values to agents, Profiles and memory, and planning and action; at the multi-agent level, we summarize collaborative alignment methods such as communication strategy optimization and multi-objective reinforcement learning. |
Wei Zeng; Hengshu Zhu; Chuan Qin; Han Wu; Yihang Cheng; Yinuo Shen; Zhe Wang; Yuyang Wang; Sirui Zhang; Xiaowei Jin; Zhenxing Wang; Feimin Zhong; Hui Xiong; |
| 195 | From Diversity to Uniformity: Cross-modal Time Series Modeling with Dependent Channel Grouping Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a universal cross-modal Time series modeling method named TimeIG, featuring Tailored Temporal Imaging and Dependent Channel Grouping. |
Minjun Cao; Hao Miao; Wentao Zhang; Senzhang Wang; |
| 196 | NaVQA: Mitigating Silent Failures in Question Answering Over Virtual Knowledge Graph Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we study the VKG-QA task, which enables users to interact with the VKGs through a natural language (NL) interface by translating their questions into SPARQL queries. |
Guohui Xiao; Haohan Xue; Lin Ren; Yishuai Geng; Guilin Qi; Shenyu Zhang; DeHao Guo; Marco Di Panfilo; Davide Lanti; Linfang Ding; |
| 197 | Learning to Sparsify Stochastic Linear Bandits Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose an adaptively phased exploration and exploitation algorithmic framework, utilizing ordinary least squares for parameter learning and specialized subroutines for sparse action selection. |
Zhengmiao Wang; Ming Chi; Zhi-Wei Liu; Lintao Ye; Carla Fabiana Chiasserini; |
| 198 | QFlash: Bridging Quantization and Memory Efficiency in Vision Transformer Attention Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: FlashAttention improves efficiency through tiling, but its online softmax still relies on floating-point arithmetic for numerical stability, making full quantization difficult.We identify three main obstacles to integer-only FlashAttention: (1) scale explosion during tile-wise accumulation, (2) inefficient shift-based exponential operations on GPUs, and (3) quantization granularity constraints requiring uniform scales for integer comparison.To address these challenges, we propose QFlash, an end-to-end integer FlashAttention design that performs softmax entirely in the integer domain and runs as a single Triton kernel.On seven attention workloads from ViT, DeiT, and Swin models, QFlash achieves up to 6.73x speedup over I-ViT and up to 8.69x speedup on Swin, while reducing energy consumption by 18.8% compared to FP16 FlashAttention, without sacrificing Top-1 accuracy on ViT/DeiT and remaining competitive on Swin under per-tensor quantization.Our code is publicly available at https://github.com/EfficientCompLab/qflash. |
Sehyeon Oh; Yongin Kwon; Jemin Lee; |
| 199 | Implicit Identity Technologies for LLMs: Fingerprinting and Watermarking Across Datasets, Models, and Generated Content Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we present a comprehensive review of LLM identity techniques, focusing on fingerprinting and watermarking across the LLM lifecycle, including datasets, models, and generated content. |
Bing Liu; Shunping Wang; Yufan Zhu; Xinyi Yu; Jing Huang; Linkang Du; Hongbin Pei; Wei Luo; |
| 200 | Towards Generalized Action Recognition on Low-Resolutions with Domain-Invariant Representation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Its attractive viewpoint is mining domain-invariant representations of cross-domain/species features under rough spatial details to enhance recognition and generalization, overcoming the significant decline of existing methods. To address this, we propose a generalized Action recognition framework for Low-resolution conditions with Domain-invariant Representation learning, named ActLDR, designed to learn domain-invariant representations. |
Hao Li; Jinhui Xu; Dianlong You; |
| 201 | From Multimodal Perception to Strategic Reasoning: A Survey on AI-Generated Game Commentary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing studies remain fragmented, and a systematic survey that unifies prior efforts is still lacking. To bridge this gap, our survey introduces a unified framework that systematically organizes the AI-GGC landscape. |
Qirui Zheng; Xingbo Wang; Keyuan Cheng; Yunlong Lu; Muhammad Asif Ali; Lingfeng Li; Yongyi Wang; Wenxin Li; |
| 202 | DynaOD: Dynamic Origin-Destination Flow Generation with Discrete-to-Continuous Temporal Semantic Modeling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: A key challenge is to translate semantic temporal signals into temporally coherent OD patterns while preserving the inherent spatial heterogeneity of urban regions. We propose DynaOD, a semantic-driven framework that models temporal dynamics through two complementary perspectives: discrete directional trends that characterize qualitative shifts in urban activity patterns, and continuous temporal evolution that captures how such shifts unfold over time. |
Jie Zhao; Xianqi Dai; Jie Feng; Huandong Wang; Yong Li; |
| 203 | Detect, Attend and Extract: Keyword Guided Target Speaker Extraction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, in many practical scenarios, clean enrollment utterances are unavailable, limiting the applicability of existing approaches. In this work, we propose DAE-TSE, a keyword-guided TSE framework that specifies the target speaker through distinct keywords they utter. |
Haoyu Li; Yu Xi; Yidi Jiang; Shuai Wang; Kate Knill; Mark Gales; Haizhou Li; Kai Yu; |
| 204 | DaV-Gen: End-to-End Generative Retrieval Via Draft-and-Verify Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: During training, the model is concurrently optimized for both candidate drafting and fine-grained verification. This is achieved by a composite loss function that jointly trains the model on two distinct but related objectives: 1) a contrastive loss that structures the embedding space for efficient drafting, and 2) a fusion loss that combines generative likelihood with vector similarity to produce a superior verification score. |
Meng Zhao; Chunmei Liu; Qinyong Wang; |
| 205 | QiMeng-VPID: Verification-Grounded Port-Level Iterative Decomposition for Complex Verilog Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose VPID, a multi-agent framework for generating complex Verilog that achieves monotonic functional improvement. |
Hongguang Wang; Jiaming Guo; Rui Zhang; Zerun Li; Di Huang; Pengwei Jin; Zidong Du; Xing Hu; Qi Guo; Yunji Chen; |
| 206 | GMENet: Generative Mixture of Experts Network for Multi-Center Glioma Diagnosis with Incomplete Imaging Sequences Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, in clinical settings, divergent imaging protocols result in incomplete MRI sequences, leading to two primary challenges: forcing existing frameworks to discard a large portion of clinical data during training and consequently limiting their clinical applicability. To address these limitations, we propose GMENet, a Generative Mixture of Experts Network for multi-center glioma diagnosis with incomplete imaging sequences. |
Pengfei Song; Fangjin Liu; Wenwen Zeng; Yonghuang Wu; Chengqian Zhao; Feiyu Yin; Xuan Xie; Jinhua Yu; |
| 207 | Cross-Modal Dynamic Hypergraph Computation Via Functional-Structural Brain Network for Brain Disorder Diagnosis Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing methods have failed to fully exploit the complementary information between functional and structural brain networks, neglecting the guiding role of topology in the transmission of functional modal information, as well as the potential associations of cross-modal high-order information. To address these challenges, this paper proposes a cross-modal dynamic hypergraph computing (CDHGC) framework for brain disease diagnosis and an in-depth analysis of coupled functional-structural brain networks. |
Jingxi Feng; Heming Xu; Rundong Xue; Junhao Cai; Xudong Chen; Dong Zhang; Shaoyi Du; |
| 208 | QiMeng-EvoPartition: Rethinking The Impact of Partitioning for Automated Pipeline Design Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Thus, automated pipeline partitioning should jointly reduce CPI and improve clock frequency while ensuring functional correctness, resulting in a multi-objective optimization problem. To address this issue, we propose EvoPartition, an evolutionary partitioning framework for automated pipeline design. |
Qicheng Wang; Rui Zhang; Shuyao Cheng; Chongxiao Li; Pengwei Jin; Zidong Du; Xing Hu; Qi Guo; Yunji Chen; |
| 209 | GPD: Guided Progressive Distillation for Fast and High-Quality Video Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose Guided Progressive Distillation (GPD), a framework that accelerates the diffusion process for fast and high-quality video generation.GPD introduces a novel training strategy in which a teacher model progressively guides a student model to operate with larger step sizes. |
Xiao Liang; Yunzhu Zhang; Linchao Zhu; |
| 210 | Revisiting Hypernetwork in Model Heterogeneous Personalized Federated Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To further enhance the hypernetwork’s learning and generalization, we propose MH-pFedHNGD, which introduces a lightweight yet effective plug-in global model. |
Chen Zhang; Husheng Li; Xiang Liu; Linshan Jiang; Danxin Wang; |
| 211 | ITBoost: Information-Theoretic Trust for Robust Boosting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Instead of relying on instantaneous error, we examine the evolution of each sample’s residuals across iterations. Based on this insight, we propose Information-Theoretic Trust Boosting (ITBoost), which uses the Minimum Description Length principle to measure the complexity of residual trajectories. |
Ye Su; Longlong Zhao; Diego García-Gil; Jipeng Guo; Gangchun Zhang; Jinxin Chen; Jinsong Chen; |
| 212 | Fast and Generalizable AI-Generated Image Detection Via Model-Agnostic Feature Reconstruction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose General Feature Reconstruction Error (GFRE), a fast and generalizable detection paradigm that leverages reconstruction behavior in a general-purpose representation space. |
Qinghui He; Haifeng Zhang; Bo Liu; Yang Wei; |
| 213 | Trajectory-Consistent Denoising Diffusion Codebook Models for Zero-Shot High-Fidelity Image Compression at Ultra-Low Bitrates Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This discrepancy inevitably results in trajectory drift, necessitating massive codebooks to span the enlarged search space and extensive inference steps to gradually compensate for the deviation. In this paper, we propose the Trajectory-Consistent Diffusion Codebook Model (TC-DDCM) to address these inefficiencies. |
Fang Zhang; Linli Xu; |
| 214 | NEST: Tackling Dataset-Level Distribution Shifts Via Regime-Oriented Mixture-of-Experts Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While existing methods predominantly focus on local temporal shifts, they fail to explicitly model the global structural challenge where datasets are composites of distinct operational regimes. In this paper, we propose NEST, a specialized framework designed to model and recompose these evolving structures through a two-phase dense MoE architecture. |
Lanhao Li; Bingshu Xie; Lijun Sun; Xin Xue; Haoyi Zhou; Jianxin Li; |
| 215 | Joint Multi-Modal Multi-Interest Profiling and Preference-Grounded Reasoning for Explainable Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Most previous methods fail to effectively exploit visual information to provide reliable evidence and primarily rely on a single unified representation of user preferences, making it difficult to distinguish diverse user interests and generate faithful explanations. To fill this gap, we propose Joint Multi-Modal Multi-Interest Profiling and Preference-Grounded Reasoning (PRIME) for solving the MMER problem. |
Anqi Wang; Jianye Xie; Weiming Liu; Rong Jiang; Lianyong Qi; Haolong Xiang; Xiaolong Xu; Wenmin Lin; Yang Zhang; Xiaokang Zhou; |
| 216 | Counterfactual Estimation Via Temporal-Aware Intervention Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose Counterfactual Estimation via Temporal-Aware Intervention Networks (TAIN), a novel model that introduces an Intervention-aware Functional Convolution kernel to emphasize the role of treatments and capture complex temporal treatment interactions. |
Xin Wang; Chi Luo; Shengfei Lyu; Yi Wan; Xiren Zhou; Xiangyu Wang; Huanhuan Chen; |
| 217 | FossilWriter: Learning Hypergraph World Models with Latent Narratives for Creative Story Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: When characters hold incomplete knowledge and situations remain unresolved, the world structure itself accumulates seeds for story development. Based on this insight we present FossilWriter, a framework that learns hypergraph world models for creative story generation. |
Heng Zhang; Yihao Zhong; Lubin Gan; Zhihe Chen; Tianyi Zhang; Jing Liu; Jin Huang; |
| 218 | PhysioGMC: Generalizable Multi-modal Coordination for Physiological Signals Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To leverage complementary strengths of clinical and wearable physiological signals, we propose PhysioGMC, a Generalizable Multi-modal Coordination framework for Physiological signals that explicitly accounts for their strong inter-subject variability. |
Mudi Zhang; Anirudh Nakra; Min Wu; |
| 219 | Graph Label Denoising Via Neighborhood Agreement–Guided Expectation Maximization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To tackle the issue, we propose NAEM, a latent label estimation framework that models clean labels as latent variables by integrating neighborhood agreement into the Expectation-Maximization (EM) paradigm. |
Dezhi Liu; Richong Zhang; Junfan Chen; Fengbo Tian; Si Chen; |
| 220 | Bridge: A Cross-Modal Learning Framework for Unified Semantic Representation in Noisy Communication Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Multimodal semantic communication systems face a critical challenge in extracting and aligning semantic features across heterogeneous modalities within a unified representation space, particularly under noisy transmission conditions. To address this, we propose Bridge, a cross-modal learning framework that integrates video, audio, and text into a unified semantic space through feature disentanglement and contrastive alignment. |
Liang Chen; Yanze Huang; Limei Lin; Xiaoding Wang; Wei Lou; Jie Wu; Sun-Yuan Hsieh; |
| 221 | Learnable Data Augmentation and Contrastive Pre-training for Temporal Link Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, the data augmentation techniques on which they depend frequently lead to suboptimal augmentations, manifesting either as over-augmentation or under-augmentation. In light of these challenges, we explore the under-explored domain of contrastive learning of temporal graph transformers and propose a novel model, ContraTGT, which employs a dual-view graph transformer. |
Canghong Jin; Jiafeng Zhao; Feng Xu; Tongya Zheng; Zemin Liu; Lina Wei; Mingli Song; |
| 222 | Constant-Memory Strategies in Stochastic Games: A Theoretical and Empirical Study Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Stochastic games have become a prevalent framework for studying long-term multi-agent interactions, especially in the context of multi-agent reinforcement learning.In this work, we comprehensively investigate the concept of constant-memory strategies in stochastic games.We first establish some results on best responses and Nash equilibria for behavioral constant-memory strategies, followed by a discussion on the computational hardness of best responding to mixed constant-memory strategies.Those theoretic insights are later verified on several sequential decision-making testbeds, including the Iterated Prisoner’s Dilemma, the Iterated Traveler’s Dilemma, and the Pursuit domain.This work aims to enhance the understanding of theoretical issues in single-agent planning under multi-agent systems, and uncover the connection between decision models in single-agent and multi-agent contexts.The codebase and the full version of this paper is available at github.com/Fernadoo/Const-Mem. |
Fengming Zhu; Fangzhen Lin; |
| 223 | A Survey on Actionable Interpretability in Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This survey reviews LLM interpretability through the lens of actionability, presenting a taxonomy of attributional and mechanistic approaches, along with emerging methods tailored to vision–language models (VLMs). |
Jie Cai; Mafizur Rahman; James Enouen; Lijun Qian; Yan Liu; |
| 224 | Double-Calibration: Towards Reliable LLMs Via Calibrating Knowledge and Reasoning Confidence Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While augmenting LLMs with Knowledge Graphs (KGs) improves factual accuracy, existing KG-augmented methods fail to quantify epistemic uncertainty in both the retrieved evidence and LLMs’ reasoning. To bridge this gap, we introduce DoublyCal, a framework built on a novel double‑calibration principle. |
Yuyin Lu; Ziran Liang; Yanghui Rao; Wenqi Fan; Fu Lee Wang; Qing Li; |
| 225 | DSSG: Dual-Stream Semantic Guidance for Source-Fully-Free Adaptation of Vision-Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: These issues lead to a severe stability-plasticity dilemma, manifesting as semantic misalignment and class collapse. To address this, we propose DSSG (Dual-Stream Semantic Guidance), an end-to-end framework that reconciles fine-grained plasticity with global stability. |
Weiwei Xiang; Shun Peng; Guangyi Xiao; Hao Chen; Lei Yang; |
| 226 | Discrete Cosine Transform Based Decorrelated Attention for Vision Transformers Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose two complementary methods that leverage the Discrete Cosine Transform (DCT) to enhance the efficiency and performance of Vision Transformers. |
Hongyi Pan; Emadeldeen Hamdan; Xin Zhu; Ahmet Enis Cetin; Ulas Bagci; |
| 227 | X-FEMR: A Token-level Explainable Approach for Electronic Health Records Foundation Models Using Transformer-based Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Despite their effectiveness, FEMRs remain black-box models, raising concerns about bias, interpretability, and clinical trust. To address this, we propose the first token-level explainability approach for FEMRs. |
Jie Huang; Pengfei Yin; Zihan Xu; Daniel Capurro; Mike Conway; Ting Dang; |
| 228 | Efficient Time Series Clustering from Multiscale Reservoir Dynamics with Granular-Ball Anchoring Graph Optimization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose MSRGC-Net, an efficient time-seriesclustering framework that integrates multiscale reservoir computing, granular-ball-based anchoring graph construction, and consensus learning.MSRGC-Net adopts a training-free reservoir computing paradigm to extract multiscale temporal representations from raw time series withoutbackpropagation, significantly reducing computational overhead. |
Yifan Wang; Lifeng Shen; Shuyin Xia; Yi Wang; |
| 229 | Multiscale-adaptive and Size-adaptive PSO-based Feature Selection for Gene Expression Analysis Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: MASA-PSO adopts a multiscale-adaptive weighting framework to explore feature subsets that distinguish between-class sample distributions during search spaces changes, and theoretically proves it enables the collaborative evaluation of multiple metrics. |
Weihao Deng; Lingyun Zhao; Fei Han; |
| 230 | Multi-Agent Non-Discriminatory Contracts Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Such disparities among agents may be undesirable in practice, for example, in standardized public contracting or worker cooperatives where fairness concerns are essential. Motivated by these considerations, our objective is to quantify the tradeoff between maximizing the principal’s utility and equalizing payments among agents, which we call the price of non-discrimination. |
Ke Ding; Bo Li; Ankang Sun; |
| 231 | Learning Multi-Indicator Weights for Data Selection: A Joint Task-Model Adaptation Framework with Efficient Proxies Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a framework for learning multi-indicator weights that jointly adapts data selection to both the downstream task and the specific model. |
Jingze Song; Zihao Chen; Wenqing Chen; Zibin Zheng; |
| 232 | UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose UniSAGE, a unified framework for modeling data with both static and dynamic attributes. |
Taoran Fang; Yan Deng; Chunping Wang; Yang Wang; Lei Chen; Yang Yang; |
| 233 | CASE-Net: Deep Spatio-Temporal Representation Learning Via Causal Attention and Channel Recalibration for Multivariate Time Series Classification Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We identify two critical bottlenecks: temporal non-causality in standard encoders that induces temporal confounding in non-stationary dynamics, and the absence of explicit channel saliency mechanisms that allows noise to contaminate the latent space. To address these challenges, we propose the Causal Attention and Spatio-temporal Encoder Network (CASE-Net), an architecture designed for structural manifold pre-conditioning. |
Fan Zhang; Yating Cui; Hua Wang; |
| 234 | Multi-Semantic Aware Self-Supervised Learning for Multi-Label Node Classification Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we propose a Multi-semantic Aware Self-Supervised pretraining method (MASS) for multi-label graphs. |
Jiayu Zhang; Jitao Zhao; Dongxiao He; Cuiying Huo; Zhiyong Feng; |
| 235 | Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose Fin-PRM, a domain-specialized, trajectory-aware PRM for financial reasoning that jointly models step-level correctness and trajectory-level coherence, producing binary supervision signals for both local and global reasoning quality. |
Jie Zhu; Yuanchen Zhou; Shuo Jiang; Junhui Li; Lifan Guo; Feng Chen; Chi Zhang; |
| 236 | Weight-Aware Branch-and-Bound for Weighted Maximum Satisfiability Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While state-of-the-art heuristic and SAT-based solvers have successfully integrated weight-aware mechanisms, Branch-and-Bound (BnB) solvers, notably WMaxCDCL, largely treat weight information passively during search and pruning. In this paper, we bridge this gap by introducing two novel weight-aware strategies into the BnB framework. |
Jialu Zhang; Chu-Min Li; Sami Cherif; Shuolin Li; |
| 237 | Walking on Ice: Adaptive Gait Control of Humanoid Robots Based on Visual Prediction and Proprioceptive Estimation for Variable Friction Environments Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing approaches such as domain randomization or employing estimation struggle to handle low-friction gait control and fail to address variable friction conditions, making it difficult to ensure control robustness. To address these challenges, we propose Walking on Ice (WoI), a friction-aware locomotion framework that combines proactive prediction with reactive adaptation for varying surface friction. |
Yixuan Shen; Rongqiang Zhao; Ruonan Li; Jie Liu; |
| 238 | ARMOR: Adaptive Curriculum Meta-Learning for Noise-Robust RAG Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Accordingly, we propose ARMOR, an Adaptive Curriculum Meta-Learning for Noise-Robust RAG Reasoning. |
Yan Wang; Yuxin Zhang; Shenyu Zhang; Yongrui Chen; Sheng Bi; Guilin Qi; |
| 239 | An LLM-based Chain-of-Response Counter-Scam System Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose Counter-Scam, a unified LLM-based multi-agent framework that orchestrates end-to-end response from initial detection to crime investigation. |
Heedou Kim; Mogan Gim; Donghee Choi; Soonil Bae; Hoonick Lee; Mi-Young Kim; Jaewoo Kang; |
| 240 | Collateral Damage Constrained Backdoor Attacks on Graph Neural Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, these methods overlook a fundamental property of GNNs: trigger-induced malicious signals inevitably propagate through graph neighborhoods, causing unintended mispredictions on clean nodes, i.e., Collateral Damage. To address this issue, we propose the Collateral Damage Constrained Graph Backdoor Attack (CDCA), a novel framework that explicitly controls malicious diffusion. |
Di Jin; Zechuan Zhang; Bingdao Feng; Xiaobao Wang; Dongxiao He; Zhen Wang; |
| 241 | Speaking Numbers to LLMs: Multi-Wavelet Number Embeddings for Time Series Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose TempoWave, a plug-and-play temporal wavelet digit interface that maps each scalar observation into digit-wise embeddings constructed from multi-wavelet, multi-scale coefficients. |
Defu Cao; Zijie Lei; Muyan Weng; Jiao Sun; Yan Liu; |
| 242 | SeMi-LoRA: Enhancing Low-Rank Adaptation Via Separation and Mixing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose SeMi-LoRA (Separation and Mixing LoRA), a novel framework that enables complete high-rank updates while preserving mergeability. |
Zhenfei Yang; Beiming Yu; Peiqin Lin; Yongkang Liu; Deyi Xiong; |
| 243 | CDMIQA: A Cross-Domain Perceptual Method and Benchmark Dataset for Medical Image Quality Assessment Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In response, we construct a multi-domain and multi-organ dataset comprising 9,105 2D and 3D medical images across three imaging domains and 18 organs, annotated by radiologists. Building upon this, we propose a cross-domain universal medical IQA method termed CDMIQA, which integrates efficient feature extractors with Hierarchical Perceptual Encoding Modules to capture and refine multi-level perceptual features while mitigating interference from noise and artifacts. |
Leilei Huang; Yue Sun; Mingxiang Wu; Wei Ke; Siyi Xun; Muzhen He; Tao Tan; |
| 244 | HyLoVQA: Dynamic Hypernetwork-Generated Low-Rank Adaptation for Continual Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This often leads to cross-level task interference, hindering accurate adaptation to the current task and object. To address this limitation, we propose HyLoVQA. |
Yiran Wang; Chenyi Xiong; Ziyue Qin; Miao Zhang; Kui Xiao; Zhifei Li; |
| 245 | Safe and Efficient Control: A Subgraph-Augmented Hierarchical Reinforcement Learning Framework for Dynamically Reconfigurable Battery Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we propose a Subgraph-Augmented Hierarchical Reinforcement Learning (SAHRL) framework. |
Kai Xie; Jingwei Hu; Ri Huang; Xiaodong Li; Yanglin Zhou; Song Ci; Jun Cheng; Zhihong Zhang; |
| 246 | Learning to Remove Coupled Rain and Mist from Single Degradation Priors Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Consequently, both specialized deraining models and all-in-one models for multiple degradations are ineffective in rain-mist coexistence scenarios. To address these challenges, we propose a novel Rain-Mist Removal (RMR) framework. |
Yan Zhang; Yuxin Feng; Zhe Huang; Fan Zhou; Zhuo Su; |
| 247 | A Local-Rotation-Driven Global Consistency Framework with Dual-View Decoding for Semi-Supervised Medical Image Segmentation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose LR-GCF, a Local-Rotation-Driven Global Consistency Framework that couples strong local geometric perturbations with global consistency regularization in a dual-view architecture. |
Zhen Yang; Dongshuai Zhang; Yunliang Qi; Guidong Zhang; Shouliang Li; Shuai Wu; |
| 248 | Bootstrapping Video Interaction Generation with Synthetic State Transitions Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To address this, we introduce a framework to generate a scalable synthetic dataset of controllable interactions.Our pipeline leverages a structured taxonomy and state-of-the-art image editing models to create explicit `start’ and `end’ state images, which serve as visual anchors for the interaction. To generate a seamless video utilizing these anchors, we propose State-Guided Sampling (SGS), a novel sampling technique that mitigates artifacts common in naive conditional generation. |
Jiho Jang; Jin-Young Kim; Nojun Kwak; Kyungjune Baek; |
| 249 | Proportional Selection in Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We address the problem of selecting k representative nodes from a network, aiming to simultaneously achieve two objectives: identifying the most influential nodes and ensuring that the selection proportionally reflects the diversity within the network. We propose a general approach to accomplish this by combining ideas from network science and computational social choice. |
Georgios Papasotiropoulos; Oskar Skibski; Piotr Skowron; Tomasz Wąs; |
| 250 | MultiGeo: Predicting Drug-Target Affinity Via Adaptive Multi-Conformation Ensemble Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose MultiGeo, a DTA prediction framework that explicitly leverages multiple protein conformations rather than a single snapshot. |
Ruida Zeng; Cheng Guo; Yajie Meng; Xunkun Cheng; Zhiwei Xu; Xiangzheng Fu; Pan Zeng; Shuting Jin; Junlin Xu; |
| 251 | GeoSFLoRA: Geometry-Conditioned Spectral Flow Low-Rank Adaptation for 2D-to-3D Transfer in Medical Image Segmentation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose GeoSFLoRA, a geometry-constrained spectral-flow low-rank adaptation framework for efficient 2D-to-3D transfer learning. |
Qin Hao; Bonian Chen; Shengwei Tian; Long Yu; |
| 252 | Progressive Adversarial Multi-View Alignment for Unsupervised Embedded Feature Selection with Linear Complexity Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This challenge is exacerbated by the diverse signals inherent in complex samples, which tend to mask shared patterns, thus complicating the pursuit of an optimal trade-off. In this work, we propose a Progressive Adversarial Feature Selection (ProAd-FS) framework for large-scale multi-view learning, which formulates this static trade-off objective as a dynamic competitive process. |
Shixuan Zhou; Yi Xiang; Haoxiang Qin; Haining Wang; Yukuan Ma; Han Huang; |
| 253 | A Durable Machine Unlearning Framework to Nullify Recall of Sensitive Data on Incremental Training Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In realistic scenarios, ULMs always need to be incrementally trained with the newly collected data samples, which can lead to the consequences of recalling sensitive information if the new dataset contains similar or even the same unlearned samples. To address this issue, we devise a Durable Unlearning Enhancement (DUE) framework to avoid restoring unwanted sensitive information from incremental training data samples. |
Qingqing Cao; Liang Hu; Dora D. Liu; Jiaxing Miao; Jian Cao; Zhongyuan Lai; Wei Cao; |
| 254 | EMMS: Evidential Multi-Label Multi-Dimensional Selection Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Although numerous data reduction methods have been developed, existing approaches face two major limitations: 1) existing methods typically select features, instances, or labels independently, without considering how noise or redundancy in one dimension may negatively influence the selection of others; 2) there are very few feature and instance co-selection methods that commonly assume label annotations are free of noise, which is seldom true in practice. To address these issues, we propose Evidential Multi-Label Multi-Dimensional Selection (EMMS), which jointly performs feature, instance, and label selection on multi-label data. |
Li Yang; Yanyong Huang; Jinyuan Chang; Ou Zheng; Minbo Ma; Xiaoyi Jiang; |
| 255 | Info-Driven Zero-Cost Proxy: Rethinking Vision Transformer Architecture Evaluation Via Information Quantification Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose Info-NAS, a zero-cost proxy based on architectural information. |
Yue Yang; Jiacheng Wang; Zhenkai Yang; Menglan Hu; Gaoyang Liu; Bo Xu; Tianyue Zheng; Kai Peng; |
| 256 | A Review on Test-Time Scaling for Agentic Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To the best of our knowledge, this paper presents the first systematic review of TTS tailored for Agentic LLMs. |
Jiayu An; Zheng Chen; Yongcheng Jing; Dacheng Tao; Bo Li; |
| 257 | Towards An Early Warning System for Ocean Heat Extremes Through AI-Ocean Dynamics Synergy Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This project introduces a novel AI-Ocean Dynamics synergy designed to provide an integrated early warning system. |
Zheng Jiang; Wei Wang; Gaowei Zhang; Yifei Bao; Zengzhou Hao; Lingyu Xu; Suixiang Shi; Lei Wang; Yi Wang; |
| 258 | ScLLM-DSC: LLM-Knowledge Enhanced Cross-Modal Deep Structural Clustering for Single-Cell RNA Sequencing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While Large Language Models (LLMs) offer promising semantic capabilities, their direct adaptation to cell clustering is hindered by the structural mismatch between generative pre-training objectives and discriminative downstream tasks. To bridge this gap, we propose scLLM-DSC, a novel LLM-Knowledge Enhanced Cross-Modal Deep Structural Clustering framework. |
Ping Xu; Pengjiang Li; Tian Du; Zaitian Wang; Jiawei Gu; Zhiyuan Ning; Ziyue Qiao; Pengfei Wang; Yuanchun Zhou; |
| 259 | Empowering Precise Embodied Agents with Executable Analytic Concepts As Semantic-Physical Blueprints Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While Vision-Language Models (VLMs) enhance agent task planning, they often fail in problem classes requiring accurate alignment between functional geometry and physical constraints, such as articulated object manipulation or precision assembly. To address these challenges, we propose GRACE, an agent framework that adopts Executable Analytic Concepts (EAC) as a core knowledge annotation paradigm for object understanding. |
Mingyang Sun; Jiude Wei; Qichen He; Donglin Wang; Cewu Lu; Jianhua Sun; |
| 260 | Information-Needs-Guided Virtual Knowledge Graph Enrichment Via Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Virtual Knowledge Graphs (VKGs) provide an effective solution for data integration by mapping heterogeneous data sources to a unified ontology.However, existing VKG construction frameworks primarily focus on one-shot construction, which often results in partial data coverage and support for only initial information needs.After the VKG has been deployed, new information needs will inevitably arise over time.Therefore, enriching VKGs to support evolving information needs remains an expert-intensive iterative task.In this work, we formulate the task of Information-Needs-Guided VKG Enrichment (IN-VKGE), and propose an iterative framework that leverages large language models to assess whether information needs can be supported using SPARQL execution feedback and generate ontology and mapping enrichment proposals.Experiments on two real-world VKGs show that our approach outperforms existing paradigms, and produces enrichment proposals that receive high expert ratings for effectively resolving the identified information needs. |
Lin Ren; Guohui Xiao; Guilin Qi; Wenjie Du; Yishuai Geng; Haohan Xue; Zhiyan Yue; Mingxuan Li; Marco Di Panfilo; Davide Lanti; Kamal Hamaz; Linfang Ding; |
| 261 | Beyond Homophily: Spectrum-Based Graph Pre-Training and Cluster-Augmented Prompt Tuning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose SCA-GPPT, a spectrum-aware framework that unifies Spectrum-based Graph Pre-training and Cluster-Augmented Prompt Tuning. |
Tingting Li; Yonghao Li; Xiangkun Wang; Sixiang Chen; Boyang Fan; Lingfei Ren; Hao Yu; Xin Yang; |
| 262 | Mixture of Clustering Experts with Dual Consistency for Multi-View Clustering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: MoCE-DC decomposes complex semantic clusters into multiple collaborative sub-structures, significantly enhances the ability to model intricate intra-cluster diversity.To further ensure cross-view semantic consistency, we propose a dual-level alignment mechanism that enforces prediction consistency across views while guiding clustering assignments toward a more discriminative direction. |
Daidai Zhu; Yang Zhao; Dandan Ma; Ganchao Liu; Zhiyu Jiang; |
| 263 | A Novel SAM Coupling Mechanism for SAR Image Segmentation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, the quality of mask generation is limited by the difficulty of aligning the optimization direction between the backbone and the prompt, which is especially significant in non-natural domain images with low contrast and indistinct semantic edge structure features, especially in SAR images. Therefore, this paper proposes a coupling optimization mechanism that integrates the originally independent prompt generation process with the backbone into a closed loop through the Point Impact Decomposition (PID) module to guide the iterative optimization of the prompt. |
Yang Liu; Miao Fu; Yingqi Gao; Lin Lin; Jiarui Li; Rui Liu; |
| 264 | TCDA: Thread-Constrained Discourse-Aware Modeling for Conversational Sentiment Quadruple Analysis Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing methods usually employ simple Graph Convolutional Networks (GCN), which introduce structural noise and fail to consider the temporal sequence of the dialogues, or use standard RoPE, which implicitly captures relative distances in a flat sequence but cannot clearly separate the token-level syntactic order from the utterance-level progression, and may suffer from the Distance Dilution problem. To address these issues, we propose a new framework that combines Thread-Constrained Directed Acyclic Graph (TC-DAG) and Discourse-Aware Rotary Position Embedding (D-RoPE). |
Xinran Li; Xinze Che; Yifan Lyu; Zhiqi Huang; Xiujuan Xu; |
| 265 | Uncertainty-Guided Adaptive Conservative Offline Reinforcement Learning for Safer Mechanical Ventilation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Offline reinforcement learning (ORL) enables policy optimization from retrospective clinical data without unsafe online interaction, but existing methods are highly sensitive to distributional shift and out-of-distribution (OOD) actions, limiting their reliability in complex clinical settings. To address these challenges, We propose UBER-CQL (Uncertainty-Balanced Exploration and Robust Conservative Q-Learning), a robust ORL algorithm for safe decision-making under dataset shift. |
Huidong Liu; Hang Yu; Qiyang Zhang; Jiarui Dou; Xianlei Long; Jiantao Shi; Fuqiang Gu; |
| 266 | Disturbance-Aware Hybrid Learning for Robust and Adaptive UAV Flight in Extreme Winds Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Wind disturbances are nonlinear, time-varying, and difficult to model, causing traditional controllers to struggle with perception and compensation, especially under unseen wind distributions. To address these limitations, we introduce WA-TD3, a data-driven control framework that enables real-time wind disturbance perception and adaptive compensation without dedicated wind sensors. |
Huidong Liu; Jiarui Dou; Jiangshan Ai; Enwen Hu; Xianlei Long; Mingyan Li; Chao Chen; Fuqiang Gu; |
| 267 | FreSH: Frequency-Segmented Hierarchical Multi-Expert Framework for Multivariate Time Series Classification Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing approaches generally struggle to reconcile fine-grained representation learning, especially under class imbalance and real-world constraints. In this paper, we present FreSH, a Frequency-Segmented Hierarchical Multi-Expert Framework designed to address these challenges. |
Pingping Liu; Muyao Wang; Zijian Zhang; Tongshun Zhang; Hao Miao; Guorui Xie; Qingliang Li; Qiuzhan Zhou; |
| 268 | Privacy-Preserving Reinforcement Learning with One-Sided Feedback Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This setting introduces substantial challenges in both learning efficiency and privacy preservation. To address these challenges, we propose POOL, a novel privacy-preserving RL algorithm. |
Lin Cong; Guangyan Gan; Hanzhang Qin; Zhenzhen Yan; |
| 269 | PersuHMM: Iterative Learning The Hierarchical Meta-Strategy Memory for Persuasive Dialogue Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Persuasive dialogue aims to alter people’s attitudes or behaviors through conversation. While LLMs can generate emotional responses, they tend to use a uniform approach across … |
Yanyue Zhang; Zihao Wang; Xin Zhang; Deyu Zhou; |
| 270 | Graph Anomaly Detection Via Feature Selection with Local Topological Residuals Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While local inconsistency mining requires the incorporation of topological information, the use of Graph Neural Networks (GNNs) to introduce such information tends to homogenize connected nodes, thereby causing the loss of local anomalous signals. To address this challenge, we propose LTRGAD, a two-stage GAD framework that performs feature selection based on local feature-topological residuals (LTR). |
Yazheng Zhao; Nannan Wu; Haoran Yin; Yiming Zhao; |
| 271 | MoTRa: Motion-Aware Target Representation Learning for End-to-End Multi-Object Tracking Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present MoTRa, a Motion-aware Target Representation learning framework for end-to-end MOT that enriches target-level representations with adaptive motion cues. |
Yuanzhou Huang; Songwei Pei; Shuhuai Wang; Bingfeng Liu; Qian Li; Shangguang Wang; |
| 272 | Improving Code Translation with Syntax-Guided and Semantic-aware Preference Optimization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose CTO to improve code translation with syntax-guided and semantic-aware preference optimization. |
Yuhan Wu; Huan Zhang; Wei Cheng; Chen Shen; Jingyue Yang; Wei Hu; |
| 273 | Bi-CoG: Bi-Consistency-Guided Self-Training for Vision-Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing methods often suffer from model bias and hyperparameter sensitivity, due to reliance on prediction consistency or pre-defined confidence thresholds. To address these limitations, we propose a simple yet effective plug-and-play methodology named Bi-Consistency-Guided Self-Training (Bi-CoG), which assigns high-quality and low-bias pseudo-labels, by simultaneously exploiting inter-model and intra-model consistency, along with an error-aware dynamic pseudo-label assignment strategy. |
Rui Zhu; Song-Lin Lv; Zi-Kang Wang; Lan-Zhe Guo; |
| 274 | Emo-LiPO: Listwise Preference Optimization for Fine-Grained Emotion Intensity Control in LLM-based Text-to-Speech Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Large language model (LLM)-based text-to-speech (TTS) systems enable prompt-conditioned emotional control but struggle with fine-grained emotion intensity due to the semantic–acoustic gap between text and speech. To address this challenge, we formulate emotion intensity control in LLM-based TTS as a learning-to-rank problem and propose Emo-LiPO, a listwise preference optimization framework that aligns prompt-conditioned speech generation with relative emotion intensity expressed in text. |
Yihang Lin; Li Zhou; Congwei Cao; Dongchu Xie; Xiaoxue Gao; Chen Zhang; Haizhou Li; |
| 275 | The Sword, Shield, and Achilles’ Heel: Characterizing The Linguistic Inductive Bias of Large Language Models for Spatial Reasoning in Navigation Planning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, the linguistic structures of such text-based spatial representations and the choices of contextual features (e.g., topology, geometry) they contain are often treated as neutral engineering decisions rather than key factors that shape LLMs’ behavior. To address this gap, we propose a dual-interventional framework that disentangles linguistic structures from different contextual cues to evaluate the linguistic inductive bias of LLMs for navigation planning. |
Xudong Zhang; Jian Yang; Shengkai Wang; Jiangpeng Tian; Shaowen Chen; Xian Wei; Ke Li; Xiong You; |
| 276 | Disentangling Coarse and Fine Latent Dynamics for Probabilistic Time Series Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Therefore, disentangling temporally coarse and fine latent dynamics is essential for achieving sharper and more reliable probabilistic forecasting results. Building on this insight, we propose COFE (COarse And FinE latent dynamics disentanglement), a variational autoencoder–based framework that models the temporal distribution by disentangling and modeling the rapidly changing and slowly varying latent dynamics simultaneously. |
Changze Zhou; Ruichu Cai; Shengbin Nie; Juntao Fang; Jie Qiao; Zijian Li; |
| 277 | TPPMG: Temporal Planning-driven Progressive Motion Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Most text-to-motion models treat motion duration as a fixed hyperparameter rather than a variable inferred from semantics, inducing two systematic failure modes: duration trailing on short prompts and stage-wise semantic collapse on long, multi-stage prompts. To address this issue, we propose TPPMG (Temporal Planning-driven Progressive Motion Generation), which factorizes generation as semantics -> temporal structure -> motion realization. |
Ruoyu Wang; Can Deng; Xinyi Li; Zhuo Li; |
| 278 | Uni-RS: A Spatially Faithful Unified Understanding and Generation Model for Remote Sensing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Unified remote sensing multimodal models exhibit a pronounced spatial reversal curse: although they can accurately recognize and describe object locations in images, they often fail to faithfully execute the same spatial relations during text-to-image generation, where such relations constitute core semantic information in remote sensing. Motivated by this observation, we propose Uni-RS, the first unified multimodal model tailored for remote sensing, to explicitly address the spatial asymmetry between understanding and generation. |
Weiyu Zhang; Yuan Hu; Yong Li; Yu Liu; |
| 279 | BehaviorBench: A Psychologically Grounded Benchmark for Evaluating Personality in Large Language Models Through Realistic Behaviors Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, these methods assess introspective labels rather than observable behavior, despite the fact that LLMs are deployed to act in realistic contexts, not to reflect on their own traits. To bridge this gap, we introduce BehaviorBench, a new benchmark for evaluating LLM personality through concrete behaviors in everyday scenarios. |
Taowen Pu; Hexi Wang; Zeyang Liu; Dongsheng Guo; Chuan Zhao; |
| 280 | Directional Hallucinations: Ideological Drift in News-Grounded LLM Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a reproducible measurement framework that treats hallucinations, unsupported statements in document-grounded QA, as diagnostic signals of ideological drift. |
Chendi Wang; Liam Cunningham; Tom Yishay; Jieying Chen; |
| 281 | White-Hat Testing for The Ballot Box: A Framework for Election AI Auditing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose CivicAudit-Bench, a stakeholder-guided auditing framework to stress-test large language models for civic hallucinations, false confidence, jurisdiction-dependent failure, and asymmetric refusals/accuracy. |
Chendi Wang; Jieying Chen; |
| 282 | StreamTimer: Efficient Inference for Long-Context Time Series Transformers Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose an inference-only streaming autoregressive framework that replaces repeated full-context recomputation with a one-time context warmup and incremental decoding, enabling efficient long-history forecasting without retraining. |
Xiyu Meng; Yuhan Wu; Canran Xiao; Yabo Dong; Duanqing Xu; |
| 283 | Neural Projection Fusion for Sliced Wasserstein on The Hypersphere Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, its reliance on uniformly sampling a large number of projection directions from the unit hypersphere can lead to suboptimal performance, as many directions are weakly informative and fail to capture salient differences between distributions. We address this limitation through Fusion Stereographic Spherical Sliced Wasserstein (FS3W), a data-adaptive divergence that incorporates distribution-dependent information into projection selection. |
Hongliang Zhang; Jianjun Qian; Lei Luo; Jian Yang; |
| 284 | Dual Branch Mutual Teaching for Long-Tailed Partial Label Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, hard-to-distinguish tail samples can significantly hinder representation learning and, in turn, affect the quality of pseudo-labels. To address this, we propose a novel Distribution-aware Dual-branch Contrastive Learning framework, DEACON, that decouples representation of head and tail labels via a dual-branch mutual-teaching design, enabling disambiguation across different shot-level groups with tailored representations. |
Xiangyu Ren; Mingxuan Xia; Guangcheng Zhu; Gengyu Lyu; Haobo Wang; Peng Lu; |
| 285 | Dual-Channel Hybrid Graph Neural Network for Mobility Social Relationship Inference Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Meanwhile, many approaches still struggle to distinguish stable social gatherings from transient noisy co-occurrences. To address these challenges, we propose a novel Dual-Channel Hybrid Graph Neural Network (HyGNN) that jointly models temporal dynamics and high-order structural dependencies. |
Liangkun Chen; Xiang Li; Guiyuan Jiang; Zhongying Zhao; Junyu Dong; Yanwei Yu; |
| 286 | TransAlpha: Lightweight Design Empowers Stock Return Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose TransAlpha, a light-weight Transformer variant tailored for cross section data to advance end-to-end forecasting methods with three novel components (Cross-Sectional Denoising for signal purification, Temporal Attention Gating for trend weighting, and Smart Pooling to avoid information loss) along with a multi-component hybrid loss function. |
Xiao Yang; |
| 287 | Propagating Unsafe Actions in LLM Controlled Multi-Robot Collaboration Via Single Robot Compromise Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Prior work has studied such threats in single robot settings, while security risks in LLM controlled multi-robot collaboration, especially those propagated through inter robot communication, remain largely unexplored. To bridge this gap, we propose a novel attack paradigm for multi-robot system in which the adversary interacts with only a single entry robot. |
Zhen Huang; Zhihuang Liu; Mengxuan Luo; Weishang Wu; Zhiping Cai; |
| 288 | Modeling Liquid Democracy: A Survey of The (Computational) Social Choice Literature Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We provide a community-maintainable and systematic survey of (computational) social choice papers on liquid democracy, organized through a searchable taxonomy of core modeling features that have appeared in the literature. |
Davide Grossi; Andreas Nitsche; Georgios Papasotiropoulos; |
| 289 | InterLight: Leveraging Intrinsic Illumination Priors for Low-Light Image Enhancement Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing methods frequently suffer from over-enhancement or color distortion, and often assume uniform noise or ideal lighting. To address these limitations, we propose InterLight, a novel framework that systematically excavates and operationalizes intrinsic illumination priors for LLIE. |
Ziqi Wang; Xu Zhang; Laibin Chang; Shi Chen; Jiaqi Ma; Huan Zhang; |
| 290 | Mitigating Collaboration Degeneration in Multi-Agent Code Generation Via A Controllable Competitive Collaboration Approach Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We thus propose C3, a Controllable Competitive Collaboration framework featuring two novel mechanisms: Centralized Auction-Based Competition (CAB) for role allocation via bidding andDecentralized Communication-Aware Competition (DCC) for solution refinement through opponent-aware adaptation.Evaluated on 70 complex projects from extended SoftwareDev, C3 reduces collaboration degeneration from 32.4% to 12.8%, while enhancing code innovation and diversity. |
Shanzhi Gu; Mingyang Geng; Yihong Dong; Yunxin Mao; Zhaoyang Qu; Hao Zou; Ruochun Jin; Zhipeng Liu; Chuanfu Xu; Haotian Wang; |
| 291 | TaylorMoDe-GS: Taylor-Driven Gaussian Splatting Motion Model for Multi-View Dynamic Scene Deblurring Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To map 3D physical motion onto the 2D image plane, we propose a velocity splatting technique. |
Xiaofeng Quan; Junzhe Wan; Chao Cai; Yifan Zuo; Xiaoshui Huang; Yuming Fang; |
| 292 | Falsdo: Benchmarking Artifact-Controlled Multimodal Fake News Verification Via Failure-Aligned Auditing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce Falsdo, a diagnostic benchmark designed to make robustness and auditability identifiable. |
Bowen Chen; Jun Yin; Lele Cao; Zheyuan Zhan; Can Wang; |
| 293 | Active Arbitration: Decoupling Spatio-Temporal Duality for Efficient Traffic Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Constrained by passive coupling, existing architectures often employ indiscriminate spatial aggregation that fails to dynamically arbitrate interaction intensity based on traffic states, forcing models to rely on redundant deep stacking to approximate complex dynamics. We address this issue by introducing Time Arbitrated Spatial GNN (TAS-GNN), an efficient framework that arbitrates spatial interactions through time. |
JiaJun Yu; Fang Yuan; Guang-Yong Chen; Min Gan; |
| 294 | Concept Bottleneck Models for Explainable Decision Making: A Survey of Progress, Taxonomy, and Future Directions Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This survey provides a unified review of CBMs organized along four dimensions: concept acquisition, concept-based decision making, concept intervention, and concept evaluation. |
Chunjiang Wang; Fan Li; Wenbo Hu; Rui Yan; Kun Zhang; Shaohua Kevin Zhou; |
| 295 | MiniST: Unlocking Input Window Length in Traffic Flow Forecasting with Compact Parameters Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Mainstream models typically contain millions of parameters and struggle to handle long sequence historical data due to memory bottlenecks. To address these challenges, we present MiniST, a minimalist framework that decouples information content from sequence length by exploiting the intrinsic redundancy of traffic data. |
Sheng Huang; Guanjun Wang; Jiaming Ma; Binwu Wang; Yang Wang; |
| 296 | Visualizing Deep Agents in Long-Horizon Tasks: Towards Explainable and Trustworthy Agentic AI Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a general-purpose observability framework that decomposes agent execution into four distinct visualization dimensions: Temporal, Cognitive, Hierarchical, and Spatial. |
Amirkia Rafiei Oskooei; Mehmet S. Aktas; |
| 297 | SDFLoRA: Selective Decoupled Federated LoRA for Privacy-preserving Fine-tuning with Heterogeneous Clients Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Moreover, under differential privacy (DP), adding noise to such mixed updates could perturb client specific directions that should remain local, resulting in utility loss. To address these issues, we propose Selective Decoupled Federated LoRA (SDFLoRA), a structure aware LoRA framework that decouples each client update into a shared component for updating and a private component that preserves client specific semantics. |
Zhikang Shen; Jianrong Lu; Haiyuan Wan; Jianhai Chen; |
| 298 | LECDPR:LLM Enhancement and Concept-Document Interactive Modeling for Prerequisite Relation Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Moreover, previous methods based on graph structures may have failed to capture the complex interactions between concepts and documents, an information gap exists between the two approaches. Therefore, we propose an LLM Enhancement and Concept-Document Interactive Modeling for Prerequisite Relation Prediction (LECDPR) model. |
Kui Xiao; Lele Zheng; Xiaoxue He; Miao Zhang; Zhifang Huang; Yan Zhang; |
| 299 | Cooperative Multi-View Graph Learning Via High-Rank Tensor Specificity Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Although these methods have achieved promising performance, existing methods mainly focus on stacking consistency graphs with low-rank constraints, while overlooking high-order specificity within diversity graphs, and the exploration of fine-grained diversity information among different samples across views remains insufficient. To address these issues, we propose High-Rank Tensor Specificity Induced Cooperative Multi-ViewGraph Learning (HTS-CMGL). |
Ling Ma; Qiyu Zhong; Songxuan Shi; Hao Wei; Shunjie Yang; Junbo Lian; Qiuru Hai; Lianjin Yu; Xiangning Zeng; Yi Shan; Zhen Yang; Gengyu Lyu; |
| 300 | Optimality-preserving Logic-Based Benders Decomposition of Answer Set Programs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This technique has been extended to Logic-Based Bender Decomposition (LBBD), solving problems specified by logic-based languages and enabling a wider applicability. |
Carmine Dodaro; Antonio Ielo; Marco Maratea; Cinzia Marte; Alice Tarzariol; |
| 301 | A Versatile Framework for Formula-Based Enforcement and Synthesis in Abstract Argumentation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Enforcement aims to modify an argumentation framework to satisfy given acceptability conditions while minimizing change from the original framework. Motivated by the need to address both syntactic and semantic notions of change, we propose formula-based enforcement, a generic framework that strictly generalizes existing approaches, by additionally covering cases they cannot handle, including semantic change. |
Andreas Niskanen; Jean-Guy Mailly; Yannis Dimopoulos; Pavlos Moraitis; |
| 302 | Prior Knowledge-enhanced Spatio-temporal Epidemic Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Spatio-temporal epidemic forecasting is critical for public health management, yet existing methods often struggle with insensitivity to weak epidemic signals, over-simplified spatial relations, and unstable parameter estimation. To address these challenges, we propose the Spatio-Temporal priOr-aware Epidemic Predictor (STOEP), a novel hybrid framework that integrates implicit spatio-temporal priors and explicit expert priors. |
Sijie Ruan; Jinyu Li; Jia Wei; Zenghao Xu; Jie Bao; Junshi Xu; Junyang Qiu; Shuliang Wang; Xiaoxiao Wang; Hanning Yuan; |
| 303 | An Automated Maintenance Plant for Highways Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: The Digital Roads project at Cambridge University is leveraging digitalisation, automation, and low-carbon materials to build an Automated Maintenance Plant (AMP) for UK road networks, aimed at minimising repair times to reduce congestion, improving safety, and contributing to the UK’s net-zero goals through faster, more accurate, and efficient road maintenance. |
N’zebo Richard Anvo; Alwyn Mathew; Lavindra de Silva; Damian Palin; Jie Xu; Samuel Schaefer; Abir Al-Tabbaa; Fumiya Iida; Ioannis Brilakis; |
| 304 | Multi-view Regression Clustering Via Low-Rank Manifold Decomposition Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Similarity-graph-based multi-view clustering is effective in capturing non-Gaussian cluster structures, yet it suffers from an inherent conflict between scalability and … |
Xiaowei Zhao; Xinyu Kou; Yan Chen; Linrui Xie; Qiang Zhang; Liang Du; |
| 305 | Context-Aware Multi-Agent Coordination: Learning Correlated Equilibria Under Situational Constraints Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose Situational-Constrained Density-Based Correlated Equilibria (SC-DBCE), a novel concept in Markov Games that formalizes situational constraints as logic implications. |
Libo Zhang; Zhirui Zeng; Yang Chen; Jiamou Liu; |
| 306 | A Structural-Analysis-Based Information Fusion for Multi-Modal Cross-View Geo-Localization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing multi-modal CVGL methods lack a structured design in the fusion stage, limiting their ability to fully exploit the information from multiple modalities. To overcome this limitation, we propose a Structural-Analysis-Based fusion principle that guides the design of network architecture. |
Xu Yan; Xiaoran Zhang; Ziwei Shi; Yu Zang; Weiquan Liu; Cheng Wang; |
| 307 | SBSDM: A Style-aware Bidirectional Stream Diffusion Model for CT-to-PET Synthesis Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: CT-to-PET synthesis aims to synthesize PET images from the widely available and lower-cost CT scans to address the high cost and additional radiation exposure associated with PET … |
Jiahao Zheng; Yu Tang; Caiwen Jiang; Zhanjie Zhang; Yongcan Luo; Dapeng Wu; |
| 308 | LLM-Based Intelligent Tutoring Systems: A Survey Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Large Language Models (LLMs) are reshaping the design and capabilities of intelligent tutoring systems (ITS) by providing powerful generative, reasoning and interaction abilities, which surpass traditional rule-based approaches. This survey presents a structured overview of LLM-based ITS and analyzes how these models transform classical system components and architectures. |
Li Kong; Jianwen Sun; Junsheng Zhou; Vincent Ng; |
| 309 | Generalization Analysis for Adversarial Vision Transformer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Extensive experiments on benchmark datasets corroborate our theoretical insights, bridging the gap between ViTs architecture design and adversarial robustness. |
Ziwen Jiang; Chang Cao; Han Li; Hong Chen; Rushi Lan; |
| 310 | MP2D: Constrained Monte Carlo Tree-Guided Diffusion for Multi-Objective Protein Sequence Design Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose Multi-Property Protein Diffusion, (MP2D), a unified framework for multi-objective protein sequence optimization that integrates conditional discrete diffusion with constrained MCTS and global iterative refinement. |
Zitai Kong; Yifan Dong; Yixuan Wu; Zhaokang Liang; Jian Wu; Hongxia Xu; |
| 311 | MLLMs Get It Right, Then Get It Wrong: Tracing and Correcting Late-Layer Textual Bias Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose CALRD (Conflict-Aware Layer Reference Decoding), a training-free method that recovers overridden predictions at inference time. |
Xingming Li; Ao Cheng; Qiyao Sun; Xixiang He; Xuanyu Ji; Runke Huang; Qingyong Hu; |
| 312 | Toward Preference-aligned Large Language Models Via Residual-based Model Steering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce Preference alignment of Large Language Models via Residual Steering (PaLRS), a training-free method that exploits preference signals encoded in the residual streams of LLMs. |
Lucio La Cava; Andrea Tagarelli; |
| 313 | Dual-Process Distribution Calibration: Bridging Slow-Fast Thinking for Few-Shot Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Based on the “fast-slow thinking” dual-process theory, we propose a novel cognition-inspired few-shot learning framework. |
Yuchen Liu; Weining Weng; Lingxing Chen; Qianzhong Chen; Shiyang Li; Yuan Ma; Yang Gu; |
| 314 | Ensuring Logic in The Fog: Sound POMDP Synthesis with LTL Objectives Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While Linear Temporal Logic (LTL) provides a rigorous language for specifying such tasks, the inherent undecidability of qualitatively verifying LTL satisfaction in partially observable Markov decision processes renders quantitative synthesis difficult, especially when designing reliable reward signals for approximate solvers. In this paper, we bridge this gap with a novel, sound reward-shaping mechanism that dynamically generates belief-dependent rewards grounded in certified LTL satisfaction. |
Can Zhou; Yulong Gao; Pian Yu; |
| 315 | SpatialSV: Internalizing Interpretable 3D Spatial Awareness in MLLMs Via Task-Oriented Visual Supervision Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Prevailing approaches typically inject spatial priors via external tools, which impose significant inference overhead, or rely on latent feature distillation, which remains uninterpretable and lacks fine-grained geometric constraints. To address these issues, we propose SpatialSV, a framework designed to internalize robust 3D spatial awareness within MLLMs while simultaneously offering inherent interpretability. |
Jiayu Tang; Yuchen Zhou; Chao Gou; |
| 316 | LBA: Textual Hard-Label Adversarial Attack Under Low Query Budgets Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Ideally, an optimal adversarial sample would consider all possible position combinations in the text, but exhaustive search is computationally impractical. To address this challenge, we propose a sampling-based method called LBA, which constructs an approximate distribution of high-quality adversarial examples by integrating both prior and posterior knowledge, and utilizes this distribution for sampling. |
Shixin Guo; Ming Zhong; Xuhong Zhang; Dandan Zhao; Zhe Wang; Bo Zhang; Shouling Ji; Hao Peng; |
| 317 | Stability and Generalization for Decentralized Markov SGD Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we investigate the stability and generalization of decentralized stochastic gradient descent (SGD) and stochastic gradient descent ascent (SGDA) under Markov chain sampling. |
Jiahuan Wang; Ziqing Wen; Ping Luo; Dongsheng Li; Tao Sun; |
| 318 | TextGaze: Prompting Gaze Target Estimation with Textual Scene Cues Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: The former leads to a high annotation burden and hinders domain transfer, whereas the latter causes misalignment between predicted attention and actual gaze targets. To address this issue, we propose TextGaze, a unified cross-modal architecture that leverages a Large Vision-Language Model (LVLM) as scalable semantic guidance to balance the two design paradigms. |
Junhui She; Fei Wang; Kun Li; Yiqi Nie; Yuxin Liu; Zhangling Duan; Xun Yang; |
| 319 | Beyond Sequences: A Dynamic Hierarchical Heterogeneous Spatio-Temporal Graph for Irregular Multivariate Time Series Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a novel method DyH2-STGraph, Dynamic Hierarchical Heterogeneous Spatio-Temporal Graph, for IMTS forecasting. |
Xiaowei Yan; Zhuo Li; Junjie Zhang; Bing Li; Jun Yan; Buzhou Tang; |
| 320 | FedCARE: Federated Unlearning with Conflict-Aware Projection and Relearning-Resistant Recovery Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose FedCARE, a unified and low overhead FU framework that enables conflict-aware unlearning and relearning-resistant recovery. |
Yue Li; Mingmin Chu; Xilei Yang; Da Xiao; Ziqi Xu; Wei Shao; Qipeng Song; Hui Li; |
| 321 | Deterministic Implementation in Single-Item Auctions Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Deterministic auctions are attractive in practice due to their transparency, simplicity, and ease of implementation, motivating a sharper understanding of when they can attain the same outcomes as randomized mechanisms.We study deterministic implementation in single-item auctions under two notions of outcomes: (revenue, welfare) pairs and interim allocations.For (revenue, welfare) pairs, we show a separation in discrete settings: there exists a pair implementable by a deterministic Bayesian incentive-compatible (BIC) auction but not by any deterministic dominant-strategy incentive-compatible (DSIC) auction.For continuous atomless priors, we identify conditions under which deterministic DSIC auctions are equivalent to randomized BIC auctions in terms of achievable outcomes.For interim allocations, under a strict monotonicity condition, we establish a deterministic analogue of Border’s theorem for two bidders, providing a necessary and sufficient condition for deterministic DSIC implementability.Using this characterization, we exhibit an interim allocation implementable by a randomized BIC auction but not by any deterministic DSIC auction. |
Yan Liu; Zeyu Ren; Pingzhong Tang; Zihe Wang; Yulong Zeng; Jie Zhang; |
| 322 | BERM: Low-Overhead Prompt-Injection Detection Via In-Situ Benign Representation Modeling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce BERM, a lightweight framework that performs in-situ detection by modeling a host LLM’s internal representations extracted during prefill, adding negligible overhead. |
Maihao Guo; Chaoyang Zhao; Jinqiao Wang; |
| 323 | DataCube: A Video Retrieval Platform Via Natural Language Semantic Profiling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present DataCube, an intelligent platform for automatic video processing, multi-dimensional profiling, and query-driven retrieval. |
Yiming Ju; Hanyu Zhao; Quanyue Ma; Donglin Hao; Chenwei Wu; Ming Li; Songjing Wang; Tengfei Pan; |
| 324 | Understanding AI Trustworthiness: A Scoping Review of AIES & FAccT Articles Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose actionable measures for the AI ethics community to adopt holistic frameworks that genuinely address the complex interplay between AI systems and society, ultimately promoting responsible technological development that benefits all stakeholders. |
Siddharth Mehrotra; Jin Huang; Xuelong Fu; Roel Dobbe; Clara I. Sánchez; Maarten De Rijke; |
| 325 | PTF-Net: Pseudo-Temporal Feature Fusion Network for Bi-Temporal Semantic Change Detection Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Bi-temporal Semantic Change Detection (SCD) is a fundamental analytical framework for capturing state transitions across various domains, with remote sensing being a key application area in this work. |
Xin Li; Xin Dong; |
| 326 | When Vision Meets Graphs: A Survey on Graph Reasoning and Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our goal is to clarify what current methods can and cannot do, and to outline a path toward foundation models that perceive and reason about graphs as scientists do. |
Xinjian Zhao; Wei Pang; Zhixuan Yu; Xiangru Jian; Xiaozhuang Song; Yaoyao Xu; Zhongkai Xue; Dingshuo Chen; Shu Wu; Philip Torr; Tianshu Yu; |
| 327 | From Traits to Roles: Consensus-Guided Composition of Orthogonal Experts for Cooperative MARL Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Inspired by Trait Theory, we propose DEcompose and COnstruct Roles (DECOR), a framework that models agent roles as dynamic compositions of orthogonal behavioral traits. |
Yewei Zhou; Bin Zhang; Ying Zhou; Xuri Ge; Dapeng Li; Hangyu Mao; Pengjie Ren; Zhiwei Xu; |
| 328 | Price of Fairness in Short-Term and Long-Term Algorithmic Selections Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce notions of group fairness for both the short and long term and theoretically analyze the trade-off between fairness and utility via the Price of Fairness (PoF). |
Shahin Jabbari; Chen Wang; |
| 329 | A Parallel Framework for The Maximum Common Induced Subgraph Problem Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a parallel MCIS framework integrating a dynamic task decomposition method guided by search information and a novel pruning strategy based on shared information. |
Jieyu Wu; Quan Zhang; Yiyuan Wang; Shiwei Pan; Jian Gao; |
| 330 | Efficient and Exact Global Attention on Latent Summaries for Knowledge Graph Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we introduce LaGR, a novel approach for integrating global information in knowledge graph reasoning. |
Chenxiao Lin; Lei Wang; Yin Zhang; Wei Liu; Ye Luo; Qingqiang Wu; |
| 331 | Riemannian Graph Convolutional Network for Skeleton-Based Two-Person Interaction Recognition Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Specifically, we model high-order skeletal statistics via Gaussian embedding and propose a Riemannian network to capture inter-subject interactions and global correlations. |
Rui Wang; Zihao Bi; Chen Hu; Xiaoning Song; Xiao-Jun Wu; Nicu Sebe; Ziheng Chen; |
| 332 | LELA: An End-to-end LLM-based Entity Linking Framework with Zero-shot Domain Adaptation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we extend LELA, a modular and domain-agnostic LLM-based entity disambiguation method, into a practical Python library that integrates zero-shot Named Entity Recognition (NER) — thereby providing a complete end-to-end pipeline for entity-linking in real-world usage. |
Samy Haffoudhi; Nikola Dobričić; Fabian Suchanek; Nils Holzenberger; |
| 333 | Environment-Aware Multiscale Geometric Interaction for Equivariant Molecular Spectral Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce the Multiscale Geometric Interaction Layer (MGIL), which integrates global context by augmenting local features with centroid-referenced anchors, geometric moments, and virtual nodes. |
Haoran Li; Weiran Cui; Minghui Li; |
| 334 | Boosting Knowledge Transfer and Retention with Brain-inspired Multi-View Incremental Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Inspired by underlying neural processing mechanisms, we propose a novel view incremental learning framework named Hebbian View Orthogonal Projection (HVOP). |
Yuhong Chen; Zihan Fang; Huifeng Yin; Yujie Wu; Qi Xu; Lei Deng; Shiping Wang; Mingkun Xu; |
| 335 | IKnowFlow: Trustworthy RAG for Sensitive Domains Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: RAG systems ground LLM responses in external evidence, yet their trustworthiness remains underspecified. Retrieval, re-ranking, and generation are optimized independently with no … |
Yash Saxena; |
| 336 | DeepLog: A Software Framework for Modular Neurosymbolic AI Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: DeepLog is an operational neurosymbolic framework that unifies logic and deep learning within standard PyTorch workflows. While existing neurosymbolic systems focus on a … |
Robin Manhaeve; Stefano Colamonaco; Vincent Derkinderen; Rik Adriaensen; Lucas Van Praet; Luc De Raedt; Giuseppe Marra; |
| 337 | SCOPE: Safety-Constrained Online Preview Enforcement for Efficient Encirclement in Multi-UAV Pursuit-Evasion Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This is challenging since forward feasible safety under dense interactions requires online safety preview. To address this issue, we propose Safety-Constrained Online Preview Enforcement (SCOPE), a MARL-based algorithm that balances encirclement efficiency and safety by short-horizon preview and safety enforcement. |
Cheng Chen; Weiwei Yuan; Xiaozhen Lu; Yicong Li; Jiale Zhang; |
| 338 | Representation-Aware Modularity: Efficient Cross-Task Generalization for LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we propose RaMod, a Representation-Aware Modularity framework to extend the ReFT paradigm to CTG through two novel components: (i) Dual-Modular Representation & Parameter Fine-tuning, which manipulates only a strategically chosen subset of hidden representations with modular interventions to guide the model toward solving unseen tasks; and (ii) Asynchronous Orchestrator, which proactively allocates and releases GPU memory for selected interventions, thereby minimizing storage overhead. |
Zheng Gong; Ying Sun; Chao Wang; Xiaohui Huo; Ping Li; Yi Zheng; Zhefeng Wang; |
| 339 | Dual-Topology Learning with Adaptive Anchors for Multi-View Clustering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: As a prominent paradigm for large-scale unsupervised learning, anchor-based multi-view clustering aims to reveal the latent structures across heterogeneous data representations … |
Chenglong Zhang; Chao Zhang; Junhao Zhang; Junyi Guan; Xianzhong Zhou; Bo Wang; Huaxiong Li; |
| 340 | Progressive Reasoning with Primitive Correction for Compositional Zero-Shot Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose PRPC, a Progressive Reasoning framework with Primitive Correction, which explicitly models the bidirectional dependency between attributes and objects via step-wise inference. |
Ziyi Chen; Haoyan Shi; Sunhan Xu; Congyan Lang; |
| 341 | SAFformer: Improving Spiking Transformer Via Active Predictive Filtering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing Spiking Transformers largely adhere to a passive reactive paradigm, which struggles to focus on task-relevant information and incurs substantial computational overhead when processing redundant visual data. To overcome this fundamental yet underexplored limitation, we propose SAFformer, a novel Spiking Transformer architecture based on an active predictive filtering paradigm. |
Zequan Xie; Weiming Zeng; Yunhua Chen; Sichang Lin; Tongyang Chen; Jinsheng Xiao; |
| 342 | IdentityMask: A Robust Face-Centric Privacy Protection Against Unauthorized Personalization of Diffusion Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, we reveal that these methods fundamentally overlook the spatio-temporal dynamics of the personalization process, resulting in inefficient optimization that fails to sufficiently disrupt the core identity encoding mechanism. To mitigate these limitations, we propose IdentityMask, a robust protection framework that shifts the paradigm from arbitrary confusion to precise, targeted feature corruption. |
Weiwei Tan; Rui Wang; Lihua Jing; Yanjun Zhang; Runbo Li; Leo Yu Zhang; |
| 343 | AwakeForest: An Interactive Geospatial Platform for Large-Scale Forest Imagery Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present AwakeForest, an interactive end-to-end platform designed for large-scale forest imagery that integrates model-assisted inference, automatic annotation, and human-in-the-loop refinement within a single workflow. |
Suraj Prasai; Kangning Cui; Rongkun Zhu; Sarra Alqahtani; Ying Zhang; Victor Paúl Pauca; Miles R. Silman; Fan Yang; |
| 344 | Identification of Probabilities of Causation: From Recursive to Closed-Form Bounds Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper extends PoCs to multi-valued treatments and outcomes by deriving closed form bounds for a representative family of discrete PoCs within Structural Causal Models, using standard experimental and observational distributions. We introduce the notion of equivalence classes of PoCs, which reduces arbitrary discrete PoCs to this family, and establish a replaceability principle that transfers bounds across value permutations. |
Xin Shu; Shuai Wang; Ang Li; |
| 345 | Stay in Character, Stay Safe: Dual-Cycle Adversarial Self-Evolution for Role-Playing Agents Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: LLM-based role-playing has rapidly improved in fidelity, yet stronger adherence to persona constraints commonly increases vulnerability to jailbreak attacks, especially for risky … |
Mingyang Liao; Yichen Wan; Shuchen Wu; Chenxi Miao; Xin Shen; Weikang Li; Yang Li; Deguo Xia; Jizhou Huang; |
| 346 | Continuous Test-Time Adaptation Via Dual Alignment Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Recent advances in this field either minimize prediction entropy on streaming target samples, which is efficient but prone to error accumulation, or rely on teacher–student pseudo-labeling, which provides more stable predictions at the cost of high computational overhead. To alleviate these issues, in this paper, we propose Dual Alignment (D-Align), a method that jointly optimizes correlation alignment and masked consistency alignment for stable and efficient online adaptation. |
Boyuan Zhang; Jie Pan; Shuai Yang; Lichuan Gu; |
| 347 | VaryBalance: Detecting LLM-Generated Text Through Variation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a simple but effective and practical LLM-generated text detection method, VaryBalance. |
Xuecong Li; Xiaohong Li; Qiang Hu; Yao Zhang; Junjie Wang; |
| 348 | Reducing Bias and Variance: Generative Semantic Guidance and Bi-Layer Ensemble for Image Clustering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Moreover, these methods primarily focus on reducing bias to improve performance, frequently overlooking the importance of variance reduction. To address these limitations, we propose GSEC (Image Clustering based on Generative Semantic Guidance and Bi-Layer Ensemble), a framework designed to reduce bias through generative semantic guidance and mitigate variance via ensemble learning. |
Feijiang Li; Zhenxiong Li; Jieting Wang; Zizheng Jiu; Saixiong Liu; Liang Du; |
| 349 | Spatially Generalizable Mobile Manipulation Via Adaptive Experience Selection and Dynamic Imagination Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Despite recent progress, existing MM methods still face two key limitations: (i) low sample efficiency, due to ineffective use of redundant data generated during long-term MM interactions; and (ii) poor spatial generalization, as policies trained on specific tasks struggle to transfer to new spatial layouts without additional training. In this paper, we address these challenges through Adaptive Experience Selection (AES) and model-based dynamic imagination. |
Ping Zhong; Liangbai Liu; Bolei Chen; Tao Wu; Jiazhi Xia; Chaoxu Mu; Jianxin Wang; |
| 350 | Three Minds, One Student: Online Multi-Teacher Knowledge Distillation for Multimodal Recommenders Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This dominance affects the entire fusion process: early fusion often amplifies biases driven by identity, while late fusion struggles to extract preference-relevant signals from misaligned modalities, even with alignment regularization. To address these issues, we propose Multi-Teacher Single-Student Online Distillation for Multimodal Recommendation (MTS2-4MM), which reframes the multimodal recommendation task from direct fusion to controllable knowledge transfer. |
Hangtong Xu; Yuanbo Xu; En Wang; |
| 351 | DiffVec: Diffusion Model for Trajectory Vector Recovery Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing trajectory recovery methods are further limited by either information loss from coordinate discretization into location IDs, or the inefficiency of conventional diffusion models that require a lengthy denoising process from pure noise. To address these challenges, we propose DiffVec, a novel and efficient diffusion framework for free-space trajectory recovery that operates directly on continuous coordinate data. |
Jiaqi Duan; Shengwei Tian; Long Yu; Xiangfu Meng; Ya Zhang; |
| 352 | Endo-GSG: Endoscopic Gaussian Splatting with Geometry-Awareness for Dynamic Tissue Reconstruction Via Single-View Monocular Knowledge Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we propose Endo-GSG, a unified framework that couples dynamic Gaussian splatting with an SDF field for dynamic surface-aware tissue reconstruction. |
Chao He; Kuangji Chen; Bruce X.B. Yu; Bo Lu; |
| 353 | LURE: Latent Space Unblocking for Multi-Concept Reawakening in Diffusion Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we model the generation process as an implicit function to enable a comprehensive theoretical analysis of multiple factors, including textual conditions, model parameters, and latent states. |
Mengyu Sun; Ziyuan Yang; Andrew Beng Jin Teoh; Junxu Liu; Haibo Hu; Yi Zhang; |
| 354 | DART: Navigating Last-Mile Heterogeneity in Instant Delivery Via Distribution-Adaptive Splines Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Analyzing 1.27 million real-world trajectories, we attribute this bias to unique challenges in GNSS-denied scenarios: distributional heterogeneity, structural heterogeneity, and contextual uncertainty. To bridge this gap, we propose DART (Distribution-Adaptive Robust Timing). |
Hao Xiong; Yang Gao; Haiyong Luo; Fang Zhao; Dan Luo; |
| 355 | PDD-RRG: Posterior Diagnostic Decision for Study-level Radiology Report Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Although some works attempt to incorporate multi-view images and historical data, these additional inputs may sometimes lead to avoidable diagnostic errors on the contrary. To address these challenges, we introduce a decision-making stage after report generation for the first time and propose a Posterior Diagnostic Decision framework (PDD-RRG) to integrate potentially conflicting diagnoses. |
Yang Yu; Yiming Ji; Bin Dai; Dong Zhang; Zhiyong Zhou; Shoushan Li; Yakang Dai; |
| 356 | Graph Rewiring in GNNs to Mitigate Over-Squashing and Over-Smoothing: A Survey Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this survey, we examine graph rewiring techniques, a class of methods designed to modify the graph topology to enhance information propagation in GNNs. |
Hugo Attali; Nathalie Pernelle; Davide Buscaldi; Fragkiskos D. Malliaros; |
| 357 | LogicFusion: Differentiable Logical Rule Learning for Cancer Driver Gene Identification Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing multi-network methods typically fuse views at the feature level or enforce uniform representations, which obscures network-specific signals and limits interpretability. To address this, we propose LogicFusion, a novel differentiable framework that treats each biological network as an independent probabilistic evidence source and explicitly learns how to combine them using logical reasoning. |
Bang Chen; Lijun Guo; Wentao He; Guang Cao; Rong Zhang; |
| 358 | EvoThink: Evolving Thinking in Large Reasoning Models Via Self-Pruning and Aha-Moment Preference Optimization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To simultaneously improve reasoning efficiency and capability, we propose EvoThink, a framework that reduces redundant verification and encourages the exploration of new reasoning paths. |
Xinbang Dai; Zheyu Xin; Huikang Hu; Lin Ren; Rihui Jin; Guohui Xiao; Kuicai Dong; Zhaocheng Du; Yuyang Zhang; |
| 359 | When Evidence Falls Short: Router-Guided Fake News Detection with Pattern Augmentation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, due to LLMs’ lack of expertise in deception-specific patterns, realizing such effective collaboration remains challenging. To address these issues, we propose a Router-Guided Fake News Detection Framework with Pattern Augmentation (RGPA). |
Yujing Wang; Xiaobao Wang; Yiqi Dong; Yueheng Sun; Di Jin; Dongxiao He; |
| 360 | Mask-Guided Hybrid Triggers for Robust Clean-Label Backdoor Attacks Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing methods face a fundamental dilemma: sample-agnostic triggers are robust but easily detectable, while sample-specific triggers offer superior stealthiness but suffer from limited effectiveness due to feature suppression. To bridge this gap, we propose a new backdoor trigger framework called Mask-Guided Hybrid Trigger (MGHT). |
Shengye Pang; Xiangyu Ji; Jungang Yang; Song Yang; Guobing Zou; |
| 361 | PoemDirector: A Multi-Agent Context-Adaptive Instructional Mode Selection Framework for Chinese Classical Poetry Video Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose PoemDirector, a multi-agent framework developed with a national K-12 educational platform partner that unifies context-adaptive instructional mode selection, hierarchical explanation, and end-to-end video generation. |
Tengteng Cheng; Xiaoli Zeng; Jialu Huang; Mingliang Hou; Zitao Liu; Xiangyu Zhao; Weiqi Luo; |
| 362 | From Language to Segmentation: Collaborative Category-Guided Unsupervised Camouflaged Object Detection with SAM3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a novel UCOD framework that leverages SAM3 through category-level interaction with MLLMs, bypassing unreliable spatial prompts. |
Huafeng Chen; Yueming Lyu; Caifeng Shan; |
| 363 | Disentangled Knowledge Forgetting in Machine Unlearning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Based on theoretical analysis, we propose disentangled knowledge forgetting constrained by the reformulated MU loss, which disentangles knowledge with variational auto-encoder and refines knowledge with counterfactual inference. |
Yuhang Xia; Cheng Zhen; Yirui Wu; Lixin Yuan; Wenxiao Zhang; Jun Liu; |
| 364 | ThinFormer: Channel Sparse Transformer for Efficient HRW Object Detection Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose ThinFormer, a dynamic and efficient framework tailored for object detection in HRW shots. |
Wenxi Li; Kunpeng Liu; Moran Liu; Shuyang Liu; Chenyang Lyu; Haozhe Lin; Yuchen Guo; |
| 365 | DSSL-Hash: Dynamic Semantic Structure Learning for Unsupervised Cross-Modal Hashing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present DSSL-Hash, which turns semantic structure learning into an evolving process rather than a one-shot preprocessing step. |
Fan Yang; Tongxuan Pei; Yuanzhi Zhao; Yudong Zhao; |
| 366 | FunCineForge: A Unified Dataset Pipeline and Model for Zero-Shot Movie Dubbing in Diverse Cinematic Scenes Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing methods face two major limitations: (1) high-quality multimodal dubbing datasets are limited in scale, suffer from high word error rates, contain sparse annotations, rely on costly manual labeling, and are restricted to monologue scenes, all of which hinder effective model training; (2) existing dubbing models rely solely on the lip region to learn audio-visual alignment, which limits their applicability to complex live-action cinematic scenes, and exhibit suboptimal performance in lip sync, speech quality, and emotional expressiveness. To address these issues, we propose FunCineForge, which comprises an end-to-end production pipeline for large-scale dubbing datasets and an MLLM-based dubbing model designed for diverse cinematic scenes. |
Jiaxuan Liu; Yang Xiang; Han Zhao; Xiangang Li; Zhenhua Ling; |
| 367 | FairTCD: Dual-Teacher Temporal Contrastive Distillation for Twofold Fair Dynamic Graph Embedding Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Furthermore, the evolution of dynamic graphs causes shifts in bias distribution, leading to unstable optimization and exacerbating these conflicts. To address these issues, we propose FairTCD, a Fair Dual-Teacher Temporal Contrastive Distillation framework. |
Yuxuan Gu; Yicong Li; Weiwei Yuan; Tianzi Zang; Donghai Guan; Jason J. Jung; Jie Zhao; Yongbo Ma; |
| 368 | URFPert: Unrolled Regulatory Flow Networks for Out-of-Distribution Single-Cell Perturbation Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In response, we propose URFPert, an unrolled regulatory flow network tailored for single-cell perturbation prediction. |
Xiaoqi Sheng; Jiawen Liu; Yutong Li; Sankar Mondal; Jiaming Liang; Tinghe Zhang; Hongmin Cai; |
| 369 | History Doesn’t Repeat, But Its Patterns Echo: A Parallel Pairwise Negative-Sampling Framework for Temporal Link Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose ATNSF, a temporal graph learning framework with a hybrid negative sampling strategy that uses a portion of historical edges as hard negatives. |
Yongchun Jiang; Heng Zhang; Jian Gao; Xin Zheng; |
| 370 | Mitigating Entity Type Confusion in Cross-Domain NER Via Multidimensional Quantification and Reasoning Enhancement Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Experimental results demonstrate that our method achieves new state-of-the-art results on all domains of the CrossNER dataset. |
Jingyu Wang; Shijie Wu; Fusheng Jin; |
| 371 | Semantically Labelled Automata for Multi-Task Reinforcement Learning with LTL Instructions Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We consider tasks specified as linear temporal logic (LTL) formulae, which are commonly used in formal methods to specify properties of systems, and have recently been successfully adopted in RL. In this setting, we present a novel task embedding technique leveraging a new generation of semantic LTL-to-automata translations, originally developed for temporal synthesis. |
Alessandro Abate; Giuseppe De Giacomo; Mathias Jackermeier; Jan Křetínský; Maximilian Prokop; Christoph Weinhuber; |
| 372 | Sharp-Wave Ripples Learning: A Bio-Inspired Incremental Learning Method Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Recent neuroscience findings reveal that hippocampal sharp-wave ripples play critical roles in consolidating neocortex memory by internally triggering the reactivation of spontaneous neural circuits without external stimulus. Inspired by this biological mechanism, we propose an incremental learning method termed Sharp-Wave Ripples Learning (SWRL), a novel incremental learning framework composed of two functionally complementary modules: a neocortex-like network for long-term memory and a hippocampus-like model for rapid new-knowledge encoding. |
Yi Sun; Xiaochang Hu; Wenzhuo Zhang; Zhiwei Wang; Jiting Li; Jian Li; Xu Xin; jia jun; |
| 373 | Focus-LIME: Surgical Interpretation of Long-Context Large Language Models Via Proxy-Based Neighborhood Selection Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose Focus-LIME, a coarse-to-fine framework designed to restore the tractability of surgical interpretation. |
Junhao Liu; Haonan Yu; Zhenyu Yan; Xin Zhang; |
| 374 | Beyond Isolated Investor: Predicting Startup Success Via Roleplay-Based Collective Agents Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose SimVC-CAS, a collective agent system that simulates VC decisions as a multi-agent interaction process. |
Zhongyang Liu; Haoyu Pei; Xiangyi Xiao; Xiaocong Du; Yihui Li; Suting Hong; Kunpeng Zhang; Haipeng Zhang; |
| 375 | Connected EF1 Allocations Exist in Discrete Chore Cutting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we prove the existence of an envy-free up to one item (EF1) division for a discrete chore. |
Ankang Sun; Bo Li; |
| 376 | DyG-Seg: Unsupervised 3D Point Cloud Segmentation Via Geometric Manifold Rectification Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To address these, we propose DyG-Seg, a Dynamic Geometric-Semantic Alignment framework. |
Benyu Wu; Kun Zhou; Xulun Ye; |
| 377 | Mitigating Dynamic Graph Distribution Shifts Via Spectral Augmentation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a spectral-based graph augmentation framework designed to investigate and improve generalization behavior in dynamic graphs under distribution shifts. |
Qianyu Song; Chao Li; Zhongying Zhao; Hua Duan; Qingtian Zeng; |
| 378 | Unlocking More Granular Control of Memory-Efficient LLM Finetuning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we systematically investigate the impact of the projection unit on LoRP methods. |
Yezhen Wang; Zhouhao Yang; Fanyi Pu; Kenji Kawaguchi; |
| 379 | HieraMix: A Hierarchical MLP-Mixer for Large-Scale Traffic Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a novel framework, Spatio-Temporal Hierarchical Mixer (HieraMix), which leverages an all-MLP architecture for efficient and effective large-scale traffic forecasting. |
Yongyao Wang; Xie Yu; Jingyuan Wang; Jiahao Ji; Li Chao; |
| 380 | Soft Condorcet Optimization for Ranking of General Agents (Extended Abstract) Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this extended abstract, we describe a ranking scheme inspired by social choice frameworks, called Soft Condorcet Optimization (SCO), to compute the optimal ranking of agents: the one that makes the fewest mistakes in predicting the agent comparisons in the evaluation data. |
Marc Lanctot; Kate Larson; Michael Kaisers; Quentin Berthet; Ian Gemp; Manfred Diaz; Roberto-Rafael Maura-Rivero; Yoram Bachrach; Anna Koop; Doina Precup; |
| 381 | A Theory of Response Sampling in LLMs: Part Descriptive and Part Prescriptive (Extended Abstract) Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Large Language Models (LLMs) are often used in autonomous decision-making, where they have to sample options from vast action spaces.Here we present a summary of the work studying the heuristics that guide this sampling process and show it resembles that of human decision-making: comprising a descriptive component (reflecting statistical norm) and a prescriptive component (implicit ideal encoded in the LLM). |
Sarath Sivaprasad; Pramod Kaushik; Sahar Abdelnabi; Mario Fritz; |
| 382 | Dynamic Heterogeneous Graph Representation Learning: A Survey Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This survey presents the first systematic review of DHG representation learning methods. |
Huan Liu; Pengfei Jiao; Jie Yin; Hongjiang Chen; Zhidong Zhao; |
| 383 | S²-VLA: State-Space Guided Vision-Language-Action Models for Long-Horizon Manipulation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This limitation largely arises from static feature fusion mechanisms that rely on fixed weights to combine visual, language, and action representations, preventing the model from adapting to different phases of task execution. To address this limitation, we propose S²-VLA, a framework that introduces a State-Space Guided Adaptive Attention (SSGAA) mechanism. |
Zhipeng Xie; Zongyi Han; Xiangyi Wei; Shiliang Sun; Yang Li; Jing Zhao; |
| 384 | BehaviorGuard: Online Backdoor Defense for Deep Reinforcement Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we shift defense concerns to trigger-agnostic backdoor output behaviors and propose BehaviorGuard, an online behavior-based backdoor detection and mitigation framework for DRL. |
Yinbo Yu; Xueyu Yin; Jiadai Wang; Chunwei Tian; Sai Xu; Qi Zhu; Daoqiang Zhang; |
| 385 | Guard4D: Robust Watermarking for 4D Gaussian Splatting Via Decoupled Decoding Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose Guard4D, a decoupled watermarking framework for 4DGS. |
Yingying Shi; Zhong Zhou; Bin Zhou; |
| 386 | ADC-GNN: Adaptive Dual-level Collaborative Graph Neural Networks for Graph Classification Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Consequently, high-level structural semantics cannot effectively feed back to guide node representation learning, limiting the collaborative optimization between fine-grained features and macroscopic structural semantics. To address these limitations, we propose a novel Adaptive Dual-level Collaborative GNN (ADC-GNN) associated with an adaptive dual-level collaborative mechanism. |
Wan Tang; Lu Bai; Lixin Cui; Ming Li; Hangyuan Du; Jing Li; |
| 387 | GRASP: Hard-Label Black-Box Malware Evasion with Higher Success, Fewer Queries, and Smaller Perturbations Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Among these atomic perturbations, (i) those with highly combinatorial search spaces are difficult to explore effectively under hard-label feedback, leaving their potential untapped, and (ii) those relying on transplanting benign fragments are often laden with evasion-irrelevant bytes and exhibit highly variable adversarial utility. We propose Gradient-seeded Reinforcement Learning And Stealthy Pruning (GRASP), a three-stage framework that tackles these challenges. |
Yutong Liu; Jianting Ning; Qi Feng; Yanjun Zhang; Yujin Huang; Leo Yu Zhang; |
| 388 | Taming Treewidth DP with Modulators: A General Booster for Graph Heuristics Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Rather than applyingTDP as a standalone technique, we demonstrate that TDP can serve as abroadly applicable enhancer for a wide range of graph combinatorialoptimization algorithms. |
Jialiang Li; Aneta Neumann; Frank Neumann; Hung Nguyen; Mingyu Guo; |
| 389 | Addressing Overcommitment in The Reasoning of Gendered Economic Memes Under Multimodal Ambiguity Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we study gendered economic dependence in image-text memes through the lens of contextual sufficiency and identify epistemic overcommitment—inferring roles without adequate evidence—as a primary source of bias. |
Kushal Kanwar; Dushyant Singh Chauhan; Kapil Rana; Gopendra Vikram Singh; Nils Lukas; |
| 390 | PAR-AdvGAN: Improving Adversarial Attack Capability with Progressive Auto-Regression AdvGAN (Extended Abstract) Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose PAR-AdvGAN, a progressive auto-regressive GAN framework that iteratively refines adversarial perturbations. |
Jiayu Zhang; Zhiyu Zhu; Xinyi Wang; Silin Liao; Zhibo Jin; Flora Salim; Huaming Chen; |
| 391 | MeteGS：Meteorology-Guided Gaussian Splatting for Scene Rendering and Recovery in Adverse Weather Conditions Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We adopt a closed-loop dual-branch optimization where the rendering branch fits degraded observations to capture weather degradation patterns, and the restoration branch regularizes scene Gaussians toward a clean domain with multi-scale perceptual consistency, suppressing artifacts and improving cross-view detail fidelity. |
Sha Fan; Xinhua Shan; Mingyu Liang; Ningjie Bao; Wei Liu; Ying Fu; |
| 392 | Focus Like A Human: Efficient GUI Grounding Via Coarse-to-Fine Visual Attention and Parallel Verification Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In contrast, low-resolution inputs, which suppress high-frequency details while preserving global layout structure through downsampling, produce significantly more robust and coherent attention patterns that better guide the model toward relevant regions. Interestingly, this observation mirrors the human visual system, which first leverages low-resolution peripheral vision to identify salient areas before conducting a detailed examination via high-resolution foveal focus.Motivated by this insight, we propose a coarse-to-fine GUI grounding framework termed FastFocus. |
Zhenhua Yang; Xiachong Feng; Weihong Zhong; Lunjun Liu; Xiaocheng Feng; Bing Qin; |
| 393 | Self-Refine Learning in LLM Multi-Agent Systems for Legal Norm Cognition and Compliance Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Comparison with human cognition reveals alignment in moral reasoning but sharp divergence in risk perception and probability distortion. To address these deficits, we introduce four methods to improve LLM’s normative compliance. |
Rongxin Cheng; Jianhui Yang; Bohan Xiong; Ning Zheng; Yiran Hu; Qingjing Chen; Yan Liu; Huanghai Liu; Yun Liu; Weixing Shen; |
| 394 | Perturbation Matters in Time Series Forecasting: A Wave-attention-aware Transformer Method Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Accordingly, we propose a novel TSF method, namely Wave-Attention-aware TransformER (WATER). |
Yiming Wang; Yiqing Su; Ximing Li; Changchun Li; Bing Wang; |
| 395 | Guiding Team Objectives with Individual Policies: A Two-Stage Model Aggregation Framework for Partially Cooperative MARL Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Model aggregation (MA) is a promising solution due to its simplicity and efficiency, yet it suffers from instability caused by the volatility of individual policies trained with individual rewards and the non-asymptotic nature of aggregation updates. To address these challenges, we propose Two-Stage Model Aggregation (TSMA), a novel multi-policy MA framework for multi-agent reinforcement learning (MARL) that leverages individual policies to enhance team cooperation. |
Wanting Liu; Baoxi Wang; Pengyi Li; Lu Jiang; Chengwei Zhang; |
| 396 | LLM-Orchestrated Diagnose–Plan–Treat for Mixed-Degradation CT Reconstruction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our empirical study shows that decomposing CT reconstruction into a sequence of ordered steps effectively mitigates this conflict, with the execution order being a critical performance factor. Leveraging this insight, we propose AgenticCT, an LLM-orchestrated multi-agent framework designed to autonomously plan the optimal reconstruction trajectory. |
Yongqiang Huang; Yingyu Chen; Fengzhi Xu; Tao Wang; Wenjun Xia; Hongming Shan; Yi Zhang; |
| 397 | SCD-MVC: Stable Conditional Diffusion for Multi-view Clustering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose SCD-MVC, a Stable Conditional Diffusion-driven framework for Multi-View Clustering. |
Jinli Ma; Chenkai Guo; Renda Han; Renxiang Guan; Siwei Wang; Ke Liang; Xiaoyu Cui; Dayu Hu; |
| 398 | LLMs As Parametric Knowledge Sources for Knowledge Graph Completion Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing methods introduce substantial model complexity or rely on prompt-based solutions that inject priors at a shallow level, which do not exploit the factual knowledge inherently encoded in model parameters. To address these issues, we propose a novel framework that treats LLMs as parametric knowledge sources for KGC. |
Deyu Chen; Qiyuan Li; Jinguang Gu; Meiyi Xie; Hong Zhu; |
| 399 | McGcn: Learning Continuous Graph Dynamics for Multi-Channel Fusion Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: These models are typically confined to discrete message-passing mechanisms, which makes it difficult to characterize the continuous evolution of underlying system dynamics. To address these limitations, we propose a multi-channel Graph Continuous Network (mcGCN), a novel framework for multi-channel data fusion. |
Na Song; Zihan Fang; Weidong Zhang; Zehua Jia; Shiping Wang; |
| 400 | DiffLOB: Diffusion Models for Counterfactual Generation in Limit Order Books Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose DiffLOB, a regime-conditioned Diffusion model for controllable and counterfactual generation of LOB trajectories. |
Zhuohan Wang; Carmine Ventre; |
| 401 | PA-GMAE: A Position-Assigned Graph Masked Autoencoder for Point Cloud Representation Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, due to the unstructured nature of point clouds, existing methods struggle to effectively model both local geometric information and global topological features, while generally neglecting positional information, resulting in insufficient model representational capacity. To address these challenges, we propose a Position-Assigned Graph Masked Autoencoder (PA-GMAE) framework for point cloud representation learning. |
Haifeng Yang; Lupeng Fang; Jianghui Cai; Jie Wang; Guojiao An; Lihua Hu; |
| 402 | EnzyPGM: Pocket-conditioned Generative Model for Substrate-specific Enzyme Design Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Currently, generative models dominate functional protein design but cannot model pocket-substrate interactions, which limits enzyme generation with precise catalytic environments. To address this issue, we propose EnzyPGM, a unified framework that jointly generates enzymes and substrate-binding pockets conditioned on functional priors and substrates, with a particular focus on learning accurate pocket–substrate interactions. |
Zefeng Lin; Zhihang Zhang; Weirong Zhu; Tongchang Han; Xianyong Fang; Tianfan Fu; Xiaohua Xu; |
| 403 | GraphPerf-RT: Graph-Driven Performance Modeling with Calibrated Uncertainty for OpenMP Scheduling on Heterogeneous Embedded SoCs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce GraphPerf-RT, an AI technology achieving deep learning accuracy at heuristic speeds (2-7ms). |
Mohammad Pivezhandi; Mahdi Banisharif; Saeed Bakhshan; Abusayeed Saifullah; Ali Jannesari; |
| 404 | Med-StepBench: A Hierarchical Reasoning Framework for Evaluating Hallucinations in Medical Vision-Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce Med-StepBench, the first large-scale benchmark for step-wise hallucination detection in 3D oncological PET/CT, comprising over 12,000 images and more than 1,000,000 image–statement pairs across volumetric and multi-view 2D data, which decomposes clinical reasoning into four expert-designed diagnostic stages. |
Minh Khoi Nguyen; Dai Lam Le; Amir Reza Jafari; Tuan Dung Nguyen; Hong Son Mai; Huy Thong Mai; Quang Huy Nguyen; Thanh Trung Nguyen; Reza Farahbakhsh; Noel Crespi; Phi Le Nguyen; |
| 405 | DeTri: Debiasing General-Purpose LLMs for Zero-Shot Relation Triplet Extraction Via Structural Expert Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, LLMs often introduce biases such as entity shift, relation confusion, and over-prediction, which limit the reliability of the extracted triplets. In this paper, we introduce DETRI, a novel debiasing framework for ZSRTE that addresses these biases by leveraging a discriminative structural expert model. |
Zehan Li; Fu Zhang; Jiawei Li; Wenqing Zhang; Jingwei Cheng; |
| 406 | AC2-VLA: Action-Context-Aware Adaptive Computation in Vision-Language-Action Models for Efficient Robotic Manipulation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To train the adaptive policy, we introduce an action-guided self-distillation scheme that preserves the behavior of the dense VLA policy while enabling structured sparsification that transfers across tasks and settings. |
Wenda Yu; Tianshi Wang; Fengling Li; Jingjing Li; Lei Zhu; |
| 407 | A Truthful Multiunit Profit-Optimal Mechanism for Synthesizing Social Laws Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We derive a method to specify the problem succinctly, reduce payment determination to allocation determination, and design an integer linear programming (ILP)-based algorithm that further reduces allocation to a polynomial-time ILP formulation. |
Jun Wu; Jian Huang; Chongjun Wang; |
| 408 | HyperXRec: Unifying Preference Clusters and LLM Experts for Robust Explainable Recommendations Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Most LLM-based explainable recommenders incorporate collaborative signals through shallow prompting or lightweight adapters, which often yields generic explanations that are only loosely grounded in preference evidence, particularly when interactions are sparse. To address this gap, we propose HyperXRec, a novel framework that unifies preference modeling and explanation generation by integrating hyperspherical latent clustering with a cluster-guided mixture-of-experts (MoE) inside an LLM. |
Xue Han; Zhiwen Luo; Zhixiang Li; Nizar Bouguila; Weifeng Su; Wentao Fan; |
| 409 | LLMs Uncertainty Quantification Via Adaptive Conformal Semantic Entropy Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose Adaptive Conformal Semantic Entropy (ACSE), a method for estimating prompt-level uncertainty by adaptively measuring semantic dispersion in LLMs outputs. |
Hamed Karimi; Vaishali Meyappan; Reza Samavi; |
| 410 | Benchmarking Real-Time Question Answering Via Executable Code Workflows Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing benchmarks are predominantly static and therefore fail to capture the temporal dynamics of information and the continuously evolving nature of real world knowledge. To address this limitation, we propose RT-QA, a dynamic evaluation framework that leverages executable code workflows to retrieve current answers at evaluation time. |
Wenjie Zhou; Yuan Gao; Xin Zhou; Hao Fu; Zhongjian Miao; Wei Chen; Bo Chen; Xiaobing Zhao; |
| 411 | StressEval: Failure-Driven Dynamic Benchmarking for Knowledge-Intensive Reasoning in Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose StressEval, a failure-driven data synthesis framework that turns observed model failures into dynamic, challenging, and controlable test instances. |
Yongrui Chen; Yangyang Ma; Xiaoying Huang; Shenyu Zhang; Huajun Chen; Haofen Wang; Guilin Qi; |
| 412 | Robust Scheduling Against Machine Failures Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We study a robust scheduling problem on identical machines in which machines may fail after the initial assignment. |
Zhenwei Liu; Guochuan Zhang; Yifan Zhao; |
| 413 | Quantifying Semantic Inertia in Large Language Models Under Rapid Topic Switching Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose an operational definition and a causal-contrastive method that isolates semantic carryover from confounding factors like context length. |
Junxin Wang; Yuchao Wang; Hongkai Zhang; |
| 414 | M-LoRA: Efficient Serving for Concurrent LoRA Adapters with Memory-Aware Speculative Scheduler on Single GPU Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, most systems rely on first-come-first-serve (FCFS) scheduling, which can incur severe queuing delay and lead to excessive adapter memory usage, squeezing KV cache space and reducing concurrency and throughput. To address these challenges, we propose M-LoRA, a memory-aware multi-LoRA serving system that reduces queuing delay and improves throughput through efficient request scheduling guided by fine-grained memory modeling. |
Shaolong Li; Xiang Yang; Qi Qi; Haifeng Sun; Zirui Zhuang; Bo He; Wanyi Ning; Jingyu Wang; |
| 415 | D2MDM2: A Brain-Inspired Deep Network Based on DDM Decision-Making Mechanism for Remote Sensing Change Detection Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, conventional one-step modeling suffers from performance degradation caused by imaging temporal differences (e.g., illumination disturbances, seasonal variations). To address this issue, we formulate the problem as an “adversarial attack and defense” paradigm. |
Kang Zhao; Ye Zhang; Bin Wang; Jianchao Zeng; |
| 416 | RODIS: Robust Diffusion Solver to Dataset Quality in Combinatorial Optimization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To enhance the robustness of diffusion solvers to dataset quality, we propose a robust diffusion solver for combinatorial optimization capable of learning from sub-optimally labeled instances follows a two-stage generate-then-decode framework, integrating an objective-guided diffusion model, further reinforced by classifier-free guidance, to produce solutions that surpass the optimality of the training dataset.Experiments demonstrate the improved robustness in \myalg compared to the diffusion-based solver baseline, in a range of combinatorial optimization benchmark tasks such as TSP (Traveling Salesman Problem) and MIS (Maximum Independent Set). |
Hui Yuan; Zhigang Hua; Zihao Li; Qi Xu; Weilin Cong; Yan Xie; Taihui Li; Rong Jin; Shuang Yang; Bo Long; |
| 417 | Shot-Conditioned Vision-Language Adaptation for Effective Harmful Content Detection from Online Short Videos Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Moreover, existing Vision-Language Model-based approaches typically rely on rigid instance selection mechanisms that fail to adapt to the unpredictable duration of anomalies in such unconstrained videos. To address these issues, we propose SVLA, a Shot-conditioned Vision-Language Adaptation framework, for effectively detecting harmful contents from online short videos. |
Shuai Xu; Zao Qiu; Xuelin Zhu; Yicong Li; |
| 418 | Procedural Fairness in Machine Learning Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Our experimental studies have revealed the relationship between procedural and distributive fairness of ML models. |
Ziming Wang; Changwu Huang; Ke Tang; Xin Yao; |
| 419 | CrossRefine: A Microservice for Cross-Domain Spatial Super-Resolution Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present CrossRefine, a deployable microservice for cross-domain spatial super-resolution that enhances multi-channel spatial tiles without modifying upstream models. |
Daniil Sukhorukov; Andrei Zakharov; Ilya Makarov; |
| 420 | A Unified Spectral-Spatial Framework for GNNs: Balancing Over-Smoothing and Over-Squashing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we adopt polynomial spectral filters as an analytical tool to establish a unified spectral-spatial framework for graph convolution and systematically characterize the effect of the polynomial order k on information propagation in GNNs. |
Xinya Qin; Lu Bai; Lixin Cui; Ming Li; Hangyuan Du; Jing Li; |
| 421 | Accelerating Masked Diffusion Large Language Models: A Survey of Efficient Inference Techniques Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, rigorous comparisons remain difficult, as end-to-end latency stems from intricate trade-offs between algorithmic, architectural, and system-level factors that are often conflated in existing benchmarks. In this survey, we introduce a unified latency decomposition framework for dLLMs to disentangle these factors and analyze their impact on inference speed in real deployments. |
Daehoon Gwak; Minhyung Lee; Junwoo Park; Jaegul Choo; |
| 422 | An Emotion-Preserving Conditional Information Bottleneck for Domain-Generalizable Speech Emotion Recognition Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, these strategies often confine generalization to predefined domains, limiting robustness under diverse real-world speech variations. To address these challenges, this paper proposes an emotion-preserving conditional information bottleneck framework (EP-CIB) for domain-free DG-SER. |
Zhichen Yuan; C. L. Philip Chen; Shuzhen Li; Tong Zhang; |
| 423 | ReSyn: A Generalized Recursive Regular Expression Synthesis Framework Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing Programming-By-Example (PBE) systems often rely on simplified benchmarks that fail to capture the high structural complexity of real-world regexes, such as deeper nesting and frequent use of union operations.To overcome the resulting performance drop, we propose ReSyn, a synthesizer-agnostic divide-and-conquer framework that decomposes complex synthesis problem into manageable sub-problems. |
Seongmin Kim; Hyunjoon Cheon; Su-Hyeon Kim; Yo-Sub Han; Sang-Ki Ko; |
| 424 | Domain-Informed Graph Neural Networks for Climate Factor Forecasting to Support Sustainable Crop Management Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Inspired by agronomic knowledge, We propose DoIGNN, a Domain-Informed Graph Neural Network that injects a domain-structured graph constraint built from Agro-Climatic Homogeneous Zones (ACHZs). |
Ziyue Sun; Zixin Jiang; Chenkai Xu; Xinggao Liu; |
| 425 | Cross-Sensor Domain Generalization for Non-Contact Sleep Staging Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While contactless radio-frequency (RF) sensing offers an unobtrusive alternative to Polysomnography (PSG), existing methods often struggle with generalization across diverse devices and environments due to the scarcity of annotated RF data. To overcome this limitation, we propose XSensorSleep, a cross-sensor domain generalization framework. |
Jie Deng; Zhi Lu; Fang Zhou; Yu Pu; Zhi Wu; Beilei Wang; Yang Hu; Yan Chen; |
| 426 | D2ACE: Multi-Label Batch Selection Guided By Dual Dynamics and Adaptive Correlation Enhancement Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In addition, the method that explicitly exploits label correlations is largely affected by abundant irrelevant labels and insensitive to local label distributions. To address these issues, we propose D2ACE, a novel multi-label batch selection method guided by Dual Dynamics and Adaptive Correlation Enhancement. |
Bin Liu; Haoyu Peng; Zhijia Wei; Jiajing Zhang; Grigorios Tsoumakas; |
| 427 | Bridging The Data Scarcity in Venous Thromboembolism Detection: A Deep Learning Framework for Large-scale Irregular Clinical Time Series Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Unlike many benchmarks, CliTsVTE reflects real-world clinical settings and presents unique challenges in continuous irregular time-series modeling with long-term irregularity and varying data granularity, which makes missingness significantly consequential. To tackle this, we propose a deep learning framework integrating multiple sequential backbones with an adversarially regularized autoencoder (ARAE) that learns latent representations to eliminate missingness. |
Can Xu; Runze Yang; Xinni Xiang; Yongtao Wu; Yaqin Huang; Haike Lei; Jie Yang; |
| 428 | Cybersecurity in AI-Enabled Digital Ecosystems: Evolutionary Game-Theoretic Modelling and Multi-Agent Defence Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Through theoretical modelling and controlled multi-agent experiments, my research proposes mechanisms that reduce attack success and strengthen defensive resilience. |
Adeela Bashir; |
| 429 | SpatialV2A: Visual-Guided High-fidelity Spatial Audio Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This limitation stems largely from current models’ reliance on mono audio datasets, which lack the binaural spatial information needed to learn visual-to-spatial audio mappings. To address this gap, we introduce two key contributions: we construct BinauralVGGSound, the first large-scale video-binaural audio dataset designed to support spatially aware video-to-audio generation; and we propose an end-to-end spatial audio generation framework guided by visual cues that explicitly models spatial features. |
Yanan Wang; Linjie Ren; Zihao Li; Junyi Wang; Tian Gan; |
| 430 | Towards Vision-Spatiotemporal Fusion in Traffic Forecasting: A Survey on Cross-Modal Alignment Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: The fusion of the two modalities is critical for building models that comprehend complex traffic scenarios. |
Anna Wang; Chao Zhang; Mingwei Lin; Junbo Zhang; Zeshui Xu; Wentao Li; Pengfei Zhang; Oscar Castillo; |
| 431 | ReDi-FM: Frozen Foundation Model for Continual Test-Time Adaptation in Medical Image Segmentation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, most existing CTTA methods rely on pseudo-labeling and self-supervised objectives, which inevitably yield noisy supervision under domain shifts. To mitigate this limitation, we introduce off-the-shelf Vision Foundation Models (VFMs) as external knowledge sources. |
Jianhang Ji; Zhiming Cheng; Jianxiang Zhao; Tingyu Wang; Bingtao Ma; Yuhan Gao; Zuobin Ying; Shuai Wang; |
| 432 | BotVA: Combating Social Bots Via Variational Feature Augmentation and Adversarial Graph Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present BotVA, a unified framework addressing both challenges through variational feature augmentation and adversarial graph learning. |
Longlong Zhang; Xi Wang; Hongyi Nie; Zeqing Zhang; Huixiang Zhang; Hongping Wang; Yang Liu; |
| 433 | 4DVarGen: A 4D Variational-Inspired Generative Model for Eddy-Resolving Surface Ocean Reconstruction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose 4DVarGen, a 4DVar-inspired generative framework for reconstructing sea surface variable fields at eddy-resolving scales from sparse remote-sensing observations. |
Junpeng Huang; Wuxin Wang; Xiaoyong Li; Juan Zhao; Senliang Bao; Di Zhang; Difu Sun; |
| 434 | ChemKGL: Bridging Knowledge Graphs and Large Language Models for Chemical Multi-Step Reaction Pathway Inference Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Despite the achieved progress, LLMs are still far from satisfactory when dealing with complex chemical multi-step reaction pathway inference task due to the lack of domain knowledge and limited ability to maintain consistent multi-step reasoning. To address these challenges, we propose ChemKGL, a novel multi-step reasoning framework enhanced by knowledge graph retrieval. |
Fan Yang; Feiyang Xu; Kun Zhang; Huadong Liang; Pengyang Shao; Xin Li; Le Wu; |
| 435 | JURIS: Bringing The Jury System to Multi-Agent Summarization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Inspired by the U.S. jury system, we propose JURIS, a judicial-decision-inspired multi-agent collaborative framework. |
Ziling Li; Junwei Zhang; Yixuan Yang; Yuqiang Han; Xiaolin Li; |
| 436 | Multi-View Alignment and Denoising Via Center-Guided Spectral Diffusion Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This means that noise may propagate or even amplify during the alignment stage, ultimately leading to suboptimal solutions. To address this issue, we propose center-guided spectral diffusion, which replaces traditional alignment with generative modeling. |
Jiayuan Wang; Jie Lian; Yongquan Shi; Jielong Lu; Zhiyuan Lai; Shiping Wang; |
| 437 | Provably Sub-Linear Two-Timescale NeuroEvolution with Online Plasticity Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper gives the first regret analysis for a general NeuroEvolutionary Online Learning (NEOL) framework, which decouples learning into two timescales: an outer loop for architecture search and an inner loop for online weight adaptation via reward-modulated plasticity. |
Shishen Lin; Yixin Chen; |
| 438 | Attributed Hypergraph Generation with Realistic Interplay Between Structure and Attributes (Extended Abstract) Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: As a result, they fail to capture the interactions between structure and node attributes. To address this issue, we propose NoAH, a stochastic hypergraph generative model for attributed hypergraphs. |
Jaewan Chun; Seokbum Yoon; Minyoung Choe; Geon Lee; Kijung Shin; |
| 439 | Manifold-Aware Point Cloud Completion Via Geodesic-Attentive Hierarchical Feature Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present a manifold-aware point cloud completion framework that explicitly incorporates nonlinear geometry information throughout the feature learning pipeline. |
Jianan Sun; Dongzhihan Wang; Zhangqi Huang; Mingyu Fan; |
| 440 | LLM-Summarized Interest Distillation for Multimedia Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Furthermore, the sparse interactions provide incomplete interest patterns, leading to biased recommendations. To address these issues, this work proposes an LLM-summarized interest distillation (SID) model to enrich interactions by interest summarization and retrieval augmentation. |
Meng Jian; Zhuoyang Xia; Haolun Fan; Lifang Wu; |
| 441 | Lookahead Branching for Neural Network Verification Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we investigate the effect of lookahead branching strategies in neural network verification. |
Liam Davis; Duo Zhou; Huan Zhang; Guy Katz; Clark Barrett; Haoze Wu; |
| 442 | One-Turn Knockout: Traceable and Editable Proxy Unlearning Under Asymmetric Access Constraints Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: The MP provides the model, while the SO can only access the model via APIs when handling unlearning requests. Under such an asymmetric access constraint, we propose One-Turn Knockout (OTK), a novel traceable and editable MUL framework based on a model-agnostic and editable proxy. |
Ziluowen Luo; Jun Yin; Hao Yan; Ruochen Liu; Ming Cheng; Senzhang Wang; |
| 443 | G-SalAlignMamba: Geometry-Aware Vision Mamba for Dual-Modal Salient Object Detection Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, they are still constrained by three inherent limitations: first, Mamba’s strict reliance on sequential ordering makes it sensitive to cross-modal geometric misalignment, where spatial shifts disrupt token correspondence; second, general indiscriminate scanning treating all tokens equally may lead to signal dilution, where sparse foreground features are overwhelmed by background noise; third, conventional decoders rely on implicit upsampling, causing boundary degradation during resolution recovery. To address these challenges, we propose G-SalAlignMamba, a geometry-aware framework tailored for dual-modal SOD. |
Haixiao Gao; Yimin Zheng; Mengke Song; Linyou Xiao; Tian-Tian Zhang; Zhi-Ri Tang; |
| 444 | Sufficient Decision Proxies for Decision-Focused Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper investigates for the first time problem properties that justify using a certain decision proxy. Using this, we present alternative decision proxies for DFL, with little or no compromise on the complexity of the learning task. |
Noah Schutte; Grigorii Veviurko; Krzysztof Postek; Neil Yorke-Smith; |
| 445 | Agreement, Diversity, and Polarization Indices for Approval Elections Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: The latter means that if two elections differ by the fraction of candidates approved by an average voter, but otherwise are of similar nature, then they should have similar index values. We propose several indices, analyze their properties, and use them to derive a new map of approval elections, and compare various real-life elections from Pabulib, Preflib and other sources. |
Piotr Faliszewski; Jitka Mertlová; Krzysztof Sornat; Stanisław Szufa; Tomasz Wąs; |
| 446 | HighFM: Towards A Foundation Model for Learning Representations from High-Frequency Earth Observation Data Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we present HighFM, a first cut approach towards a FM for high-temporal-resolution, multispectral EO data. |
Stella Girtsou; Konstantinos Alexis; Giorgos Giannopoulos; Charalambos Kontoes; |
| 447 | ConDyGNet: Constraint-Guided Dynamic Graph Networks for Multivariate Time Series Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing methods either use a single global static structure, resulting in insufficient sensitivity to temporal changes, or use local statistical correlations to construct dependencies, but local correlations are prone to introducing noise, which may further amplify the impact of noise during propagation. To address these issues, we propose a Constraint-Guided Dynamic Graph Network (ConDyGNet), whose core idea is "global basis, dynamic weights". |
Zhenzhou Li; Xiang Li; Zhibin Niu; |
| 448 | ASTPKEFormer: Adaptive Spatiotemporal Prior Knowledge Embedding-Induced Transformers for Traffic Data Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Although existing prediction models are able to achieve certain results on this task, existing Transformer-based models usually rely on simple embedding strategies and do not fully utilize the prior knowledge embedded in traffic patterns and network topology. To address these limitations, we propose ASTPKEformer, a prior knowledge-guided Transformer framework for traffic prediction. |
Wenfeng Zhou; Xiaoyun Xia; Xiangjie Kong; Guojiang Shen; Bin Chen; Fei Wu; Binbin Guo; |
| 449 | VERA: Identifying and Leveraging Visual Evidence Retrieval Heads in Long-Context Understanding Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we dissect the internal mechanisms governing long-context processing in VLMs to understand their performance bottlenecks. |
Rongcan Pei; Huan Li; Fang Guo; Qi Zhu; |
| 450 | A Unified Knowledge Embedded Reinforcement Learning-based Framework for Generalized Capacitated Vehicle Routing Problems Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: The Capacitated Vehicle Routing Problem (CVRP) is a fundamental NP-hard problem with broad applications in logistics and transportation. Real-world CVRPs often involve diverse objectives and complex constraints, such as time windows or backhaul requirements, motivating the development of a unified solution framework.Recent reinforcement learning (RL) approaches have shown promise in combinatorial optimization, yet they rely on end-to-end learning and lack explicit problem-solving knowledge, limiting solution quality.In this paper, we propose a knowledge-embedded framework inspired by the Route-First Cluster-Second heuristics. |
Wen Wang; Xiangchen Wu; Liang Wang; Hao Hu; Xianping Tao; |
| 451 | H²SCAN: Adaptive Time Series Representation Learning Via Heterogeneous Hypergraph Structure-aware Contrasts Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In addition, most static representation learning frameworks struggle to cope with the non-stationary nature of real-world time series. To address these issues, we propose Heterogeneous Hypergraph Structure-aware Contrastive Adaptive Network (H²SCAN), a novel augmentation-free framework that derives contrastive supervision directly from graph topology. |
Biao Chen; Zijie Tang; Junhua Fang; Feng Lu; Lang Zhang; Pengpeng Zhao; |
| 452 | Perturbation-Resilient Autonomous Navigation with Distributionally Robust Reinforcement Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To address the problem, we propose DRIQN to integrate DistributionallyRobust Optimization (DRO) with implicit quantile networks to optimize worst-case performance under natural environmental conditions. |
Zhaofan Zhang; Minghao Yang; Sihong Xie; Hui Xiong; |
| 453 | Cross-Paradigm Graph Backdoor Attacks with Promptable Subgraph Triggers Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Graph Neural Networks (GNNs) are vulnerable to backdoor attacks, where adversaries implant malicious triggers to manipulate model predictions. Existing trigger generators are often simplistic in structure and overly reliant on specific features, confining them to a single graph learning paradigm, such as graph supervised learning, graph contrastive learning, or graph prompt learning.Such paradigm-specific designs lead to poor transferability across different learning frameworks, limiting attack success rates in general testing scenarios.To bridge this gap, we propose Cross-Paradigm Graph Backdoor Attacks with Promptable Subgraph Triggers (CP-GBA), which employs Graph Prompt Learning (GPL) to synthesize transferable subgraph triggers. |
Dongyi Liu; Jiangtong Li; |
| 454 | MindTracker: Unveiling Implicit Emotions in Long-Horizon Dialogues Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing models struggle to disentangle internal emotional states from external expressions, and fail to capture the emotional inconsistency that emerges across long-horizon dialogues. To address this limitation, we introduce Emotional Inconsistency Analysis (EIA), a novel task that aims to identify and reason about discrepancies between implicit and explicit emotions over long-term conversational contexts. |
Zhiqiang Gao; Jing Han; Zhuochu Wang; Shihao Gao; Cheng Zhu; Kehan Wang; Huan Zhao; Zixing Zhang; |
| 455 | Predicting Context-Aware Transcriptional Responses to Unseen Genetic Perturbation Subject to Interactome Distance Constraints Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Based on the fact that a genetic perturbation is a molecular stimulus acting through functional connectivity to reconfigure cellular expression profiles, we propose PertDCR, a framework for context-aware Perturbation response prediction via Distance-Constrained Refinement. |
Feiyu Ma; Yunfei Zhang; Hau-San Wong; Si Wu; |
| 456 | Bridging The Semantic Gap: Leveraging LLMs for Hierarchical Interest Evolution in Sequential Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While Large Language Models (LLMs) offer rich semantic understanding to bridge this gap, their direct application faces two main challenges: modality misalignment between continuous semantic representations and discrete item IDs, and prohibitive computational costs that make them unsuitable for real-time inference. To address these issues, we propose the Hierarchical Semantic Interest Evolution Network (HSIEN), a novel generative-discriminative framework. |
Yifan Cao; Rui Wu; Xiang Wang; Wei Peng; Wei Xu; Caihong Sun; Jian Zeng; |
| 457 | Beyond Scaling: A Survey of Data-Efficient Learning for LLM Agents Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This survey develops an agent-centric view of data-efficient learning. |
Yaqing Wang; Zhenlin Luo; Peiyao Zhao; Yunfeng Cai; Quanming Yao; |
| 458 | STAR: Spatio-Temporal Attention Rebalancing for Eco-Friendly Autonomous Mobility-on-Demand Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Moreover, existing Deep Reinforcement Learning (DRL)-based approaches fail to address the instability of cooperative learning in environments with highly variable rewards, such as carbon emissions. To address these issues, we propose the Spatio-Temporal Attention Rebalancing (STAR) framework, leveraging an encoder-decoder architecture. |
Jungeun Lee; Seungjae Baek; Seongjae Lee; Sunhwi Kim; Jeong hwan Jeon; |
| 459 | TriHAI: A Combination Enhanced Tri-Mode Deferral for Human-AI Team Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To address the challenges, we propose TriHAI, a tri-mode deferral method that routes samples to suitable modes based on normalized confidence scores obtained through a discriminative gating network, and enhances combination mode by fusing model predictions refined by human-guided Conformal Prediction and human predictions via Bayesian theory. |
Minhui Zhang; Xuehan Zhao; Xin Zhang; Jiaqi Liu; Zhiwen Yu; Bin Guo; |
| 460 | STAR-Net: Physics Inspired Spectral Topology Aware Reconstruction Network for Single-View Fluorescence Molecular Tomography Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While single-view FMT offers distinct advantages in data acquisition efficiency and cost-effectiveness, the scarcity of projection views severely exacerbates photon scattering-induced depth ambiguity, rendering 3D volumetric recovery a highly ill-posed inverse problem. To address these challenges, we propose a physics-inspired spectral topology aware reconstruction network (STAR-Net). |
Xiangzheng Li; Jian Zhang; Mengxiang Chu; Xiaoli Luo; Hongbo Guo; Xiaowei He; |
| 461 | NeuroDALEC: A Differentiable and Interpretable Mass-Conserving Framework for Terrestrial Ecosystem Carbon Cycle Dynamics Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose NeuroDALEC, an interpretable framework that embeds the DALEC carbon-cycle model within a neural network, enabling differentiable computation of ecological processes. |
Meng Wan; Tiantian Liu; Zhixin Xia; Ningming Nie; Jue Wang; Rongqiang Cao; Honglin He; Xiaoli Ren; Peng Shi; Yangang Wang; |
| 462 | Adversarial Attack Framework Against Vision-Language Model Unlearning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose SISA, a novel attack framework for crafting adversarial inputs to manipulate generation towards the forgotten target, which only requires access to a surrogate, pre-trained VLM. |
Yimin Liu; Peng Jiang; Yajie Wang; |
| 463 | UniPocket: Physics-Aware Geometric Graph Learning with Manifold Completeness for Ligand-Specific Binding Site Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose UniPocket, a novel E(3)-equivariant surface graph neural network. |
Kangxin Chen; Jieyu Zhao; Jinli Hu; Min Xie; |
| 464 | MindCopilot: Towards Formalizing and Evaluating Granular Human-LLM Co-Writing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To address this gap, we adopt a sequential, behavior-centered view of interactive writing and formalize co-writing as a Human-in-the-Loop Markov Decision Process, modeling writing as an interaction shaped by user acceptance and editing decisions. Based on this formulation, we introduce the Co-Writing Fidelity Suite, an interaction-aware metric suite that captures both user–assistant alignment and cognitive editing effort, including Hierarchical Acceptance Rate and Knowledge-aware Editing Distance. |
Youqing Fang; Yinhao Tang; Yanan Sun; Jiangning Liu; Ziyi Wang; Xun Zhao; Bin Liu; Weiming Zhang; Kuikun Liu; Wenwei Zhang; Kai Chen; |
| 465 | Policy-Embedded Graph Expansion: Networked HIV Testing with Diffusion-Driven Network Samples Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Here, we study sequential testing on incrementally revealed disease networks and introduce Policy-Embedded Graph Expansion (PEGE), a novel framework that directly embeds a generative distribution over graph expansions into the decision-making policy rather than attempting explicit topological reconstruction. |
Akseli Kangaslahti; Davin Choo; Lingkai Kong; Milind Tambe; Alastair van Heerden; Cheryl Johnson; |
| 466 | StructureBench: A Unified Benchmark Suite for Multi-Scenario Structured Generation Tasks with On-Device Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce StructureBench, a comprehensive benchmark for structured generation on edge devices, covering JSON and tool-call generation, code synthesis, mathematics, science, and domain-specific languages, and evaluating over 11 on-device language and vision–language models spanning 0.5B–8B parameters. |
Xiaokun Xiong; Zhengjie Xu; Junyi Chen; Shihao Bai; Ruihao Gong; Xianglong Liu; |
| 467 | Relation-Aware Graph Learning with Mixture-of-Experts Prediction for Cognitive Diagnosis Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Fully leveraging heterogeneous relations and modeling large mastery-difficulty variations remain challenging, especially with a single predictor. To address these challenges, we propose RMCD, a unified cognitive diagnosis model that integrates relation-aware graph learning with Mixture-of-Experts (MoE) prediction. |
Jingwei Qu; Mingze Zhang; Pingshun Zhang; Li Tao; Ying Wang; Zhaofang Yang; Haibin Ling; |
| 468 | Interactive System for Reducing Error Propagation in Multi-Stage Ancient Egyptian Text Analysis Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce a web tool that puts the full image-to-text pipeline for Ancient Egyptian hieroglyphs inside a single annotation workspace. |
Maksim Golyadkin; Innokentiy Humonen; Ilya Makarov; |
| 469 | When Can We Trust Fairness Audits? Identifying Reliability Boundaries of Third-party Audit Conclusions Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Answering this question is challenging, as the actual deployment distribution is typically inaccessible or unobservable. To tackle this, we introduce the Consistency Radius, a metric that quantifies the maximum distribution shift under which an audit conclusion based on third-party dataset remain consistent. |
Yuanhao Liu; Qi Cao; Huawei Shen; |
| 470 | Speeding Up The NSGA-II Via Dynamic Population Sizes Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This slows down the algorithm and renders the choice of the population size a crucial design decision. In this work, we aim to overcome these difficulties by proposing the dynamic NSGA-II, a variant of the well-known NSGA-II that starts with a small initial population and doubles it after a user-specified number ? |
Benjamin Doerr; Martin S. Krejca; Simon Wietheger; |
| 471 | Disentangled Hypergraph Network with Implicit Structure Learning for Mobility Social Relationship Inference Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Third, the intrinsic characteristics of the users themselves are frequently ignored. To address these challenges, we propose a Disentangled Hypergraph Network with Implicit Structure Learning for mobility social relationship inference, named DHISL. |
Jingjing Zhu; Xiang Li; Dongliang Chen; Haobing Liu; Yuan Cao; Yanwei Yu; |
| 472 | PDFlow: Popularity-Debiased Flow Matching for Sequential Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Current debiasing methods struggle to enforce consistent step-wise constraints, rendering them ineffective for the multi-step process of generative recommendation. To address this challenge, we propose a method called Popularity-Debiased Flow Matching for sequential recommendation (PDFlow). |
Zican Yang; Zeyu Li; Cong He; Xiaotao Wu; Guanfeng Liu; Pengpeng Zhao; |
| 473 | Physically Guided Visual Mass Estimation from A Single RGB Image Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Consequently, mass prediction from pixels is ill-posed and therefore benefits from physically meaningful representations to constrain the space of plausible solutions. We propose a physically structured framework for single-image mass estimation that addresses this ambiguity by aligning visual cues with the physical factors governing mass. |
Sungjae Lee; Junhan Jeong; Yeonjoo Hong; Kwang In Kim; |
| 474 | Learning Quantitative Automata Modulo Theories Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce QUINTIC, a general algorithm for actively learning quantitative automata from preferences. |
Eric Hsiung; Nathan Tsoi; Swarat Chaudhuri; Joydeep Biswas; |
| 475 | Parameterized and Streaming Algorithms for Euclidean Fair K-Center Clustering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: By incorporating this algorithm as a post-processing stage into a one-pass streaming framework for large-scale data, we obtain an approximation ratio of 4.464. |
Zeyu Lin; Chaoqi Jia; Longkun Guo; Chao Chen; |
| 476 | When and How to Adapt: Subject Shifts Detection and Prototype-Guided Correction for Online EEG Decoding Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Meanwhile, some online EEG decoding methods that utilize detected shifts as soft boundaries are ill-suited for unsupervised scenarios and lack effective distribution alignment strategies. To address these issues, we propose a novel Prototype-driven online EEG Decoding framework (PRED). |
Shaoqi Zhang; Xiyuan Jin; Xiaojun Ning; Yilin Chen; Jing Wang; |
| 477 | NPRIP: Nucleus-to-Periphery Retrieval-Iterative Prompting for Improved Abstractive Summarization in Low-Resource Mongolian Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: For traditional Mongolian, a typical low-resource agglutinative language, this paper proposes a Nucleus-to-Periphery Retrieval-Iterative Prompting (NPRIP). |
Menghan Li; Nier Wu; Yang Liu; Yatu Ji; Shuo Sun; |
| 478 | Object-Centric Alignment and Anchor Distillation for Weakly Supervised Referring Expression Comprehension Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our key insight is thatdifferent self-attention heads in DINOv2 naturallyattend to distinct semantic regions, effectively capturing object-level information. |
Yi Tian; Cheng Yang; Qingbao Huang; |
| 479 | Vector-Quantized Discrete Latent Factors Meet Financial Priors: Dynamic Cross-Sectional Stock Ranking Prediction for Portfolio Construction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Classical factor models offer interpretability but limited flexibility, while deep learning models achieve strong performance yet often underutilize financial priors. We address this gap with PRISM-VQ (PRior-Informed Stock Model with Vector Quantization), a dynamic factor framework that integrates expert prior factors, vector-quantized discrete latent factors learned from cross-sectional structure, and a structure-conditioned Mixture-of-Experts to generate time-varying factor loadings. |
Namhyoung Kim; Jae Wook Song; |
| 480 | Adversarial Masked Graph Modeling for Robust Graph Autoencoders Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: As a result, existing GMAEs tend to overfit these perturbed inputs, leading to poor robustness. Motivated by this, we propose an adversarial masked graph modeling for robust graph autoencoders, named ArmorGAE. |
Qiqi Zhang; Chuanjin Liu; Gen Liu; Chao Li; Zhongying Zhao; |
| 481 | SeGO: Sensitivity-Aware Golden Optimization for Large-Scale VLM Quantization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we categorize the Transformer linear layers into Expansion Space (responsible for feature expansion) and Projection Space (responsible for feature aggregation) and reveal a cross-modal structural sensitivity asymmetry in VLMs: The Expansion Space is more sensitive to quantization accuracy than the Projection Space in both LLM and ViT encoders. |
Tianqi Zhao; Xinrui Cheng; Yang Su; Weiyi Lu; Zhaodong Zhang; Zhongjie Wang; Ruihan Hu; |
| 482 | Text-Graph Synergy: A Bidirectional Verification and Completion Framework for RAG Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose TGS-RAG, a unified framework for Text-Graph Synergistic enhancement. |
Jiarui Zhong; Hong Cai Chen; |
| 483 | PRIME: A Decoupled Multi-agent Actor-Critic for Multi-view Clustering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Deep multi-view clustering draws plentiful attention in various domains, owing to remarkable performance in learning patterns from complementary information of multi-view data. … |
Jing Gao; Xinxin Liu; Peng Li; Jianing Zhang; Meng Liu; Qingchen Zhang; |
| 484 | Bridging The Objective Gap: A Unified Pre-Training Framework for Few-Shot Medical Image Segmentation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce a Drift-Gap diagnostic to quantify intrinsic dense-matching misalignment and adaptation-induced feature drift. |
Shoupeng Chen; Yiming Miao; Limei Peng; Pin-Han Ho; |
| 485 | Multimodal Emotion Recognition with Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To systematically review existing research and guide future exploration, this paper categorizes prior works according to their focus on addressing these challenges into three directions: Affective Data Augmentation, Multimodal Affective Representation, and Multimodal Affective Reasoning. By thoroughly tracing the development, emerging trends, and remaining issues within each direction, this paper aims to provide a clear academic map of the MER-with-LLMs paradigm and foster its structured advancement. |
Hongrui Zhang; Daiqing Wu; Yangyang Li; Kuien Liu; Yuhui Wang; Yu Zhou; Sicheng Zhao; |
| 486 | BetaEdit: Null-Space Constrained Sequential Model Editing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we first expose the knowledge leakage inherent in existing null-space approaches and then analyze why history-aware updates effectively preserve both editing performance and general capabilities during long-horizon editing. Building on these insights, we propose BetaEdit, a refined framework that effectively controls the knowledge leakage and integrates history-aware updates into the null-space paradigm. |
Bingqing Liu; Wei Liu; Yuhua Li; |
| 487 | CoFL: Consensus Driven Human-AI Collaborative Federated Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose CoFL, a novel consensus driven human-AI collaborative FL method, which utilizes the complementarity between humans and AI models to produce more reliable labels. |
Zeyuan Cai; Yao Zhang; Zhiwen Yu; Jiaqi Liu; Yuchang Sun; Chenhao Ma; Yilin Zhao; |
| 488 | HFFN-ID: A Hierarchical Feature Fusion Network with Bi-Phase Subject ID Modulation for EEG Mel-Spectrogram Reconstruction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To alleviate both issues, this paper proposes a Hierarchical Feature Fusion Network with bi-phase subject IDentifier modulation (HFFN-ID) for reconstructing mel-spectrograms from EEG signals. |
Chi Huang; Zhaohu Liu; Yong Peng; Wanzeng Kong; |
| 489 | AlgoSimBench: Identifying Algorithmically Similar Problems for Competitive Programming Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce AlgoSimBench, a benchmark of 402 multiple-choice questions curated in an adversarial setting: each given reference problem is paired with one algorithmically similar problem and three distractors that are semantically close but algorithmically dissimilar. |
Jierui Li; Raymond Mooney; |
| 490 | Deep Identification of Propagation Trees in Graph Diffusion Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce DIPT (Deep Identification of Propagation Trees), a probabilistic framework that infers propagation trees from final observed node diffusion states, without knowledge of the underlying diffusion mechanism. |
Zeeshan Memon; Chen Ling; Ruochen Kong; Vishwanath Seshagiri; Andreas Züfle; Liang Zhao; |
| 491 | Toward Trustworthy Foundation Models: Mitigating OOD Failure in Adaptation and Deployment Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: The nature of this vulnerability is two-fold: first, a reliance on spurious background cues during inference, and second, dimensional collapse in the representation space during fine-tuning. This research aims to mitigate these failures by developing mechanistic insights and algorithmic solutions during foundation model adaptation and deployment phases of the lifecycle. |
Ping Song; |
| 492 | MemoVAD: Resource-Efficient Video Anomaly Detection Via Dynamic Semantic Memory in Edge Computing Scenarios Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To address the challenge, we propose MemoVAD, an edge–cloud collaborative framework that selectively incorporates VLM semantics into streaming VAD. |
Guo Li; Jiandian Zeng; Yang Li; Zihao Peng; Ke Chen; Tian Wang; |
| 493 | VLM-AR3L: Vision-Language Models for Absolute and Relative Rewards in Reinforcement Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we present VLM-AR3L, a framework that leverages Vision-Language Models (VLMs) to provide both absolute and relative rewards for RL. |
Kuan-Chen Chen; Winston Chen; Wei-Fang Sun; Min-Chun Hu; |
| 494 | Frequency-Aware Augmentation and Alignment for Time Series Contrastive Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Such augmentations can unpredictably disrupt the natural frequency structure of signals, leading to representations failing to capture crucial patterns in the data. To address this, we propose a framework of Frequency-Aware Augmentation and Alignment for Time Series Contrastive Learning (FACL), which comprises two key innovations. |
Yusen Liu; Zhichen Lai; Hua Lu; Xu Cheng; Xiufeng Liu; Huan Huo; |
| 495 | FediLoRA: Practical Federated Fine-Tuning of Foundation Models Under Missing-Modality Constraints Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To the best of our knowledge, no prior work has addressed these two challenges simultaneously in federated VLLMs. To tackle these issues, we propose FediLoRA, a lightweight federated LoRA aggregation framework that effectively mitigates the impact of missing modalities in heterogeneous environment. |
Lishan Yang; Wei Emma Zhang; Nam Kha Nguyen; Po Hu; Yanjun Shu; Weitong Chen; Sim Mong Yuan; |
| 496 | TabKD: Tabular Knowledge Distillation Through Interaction Diversity of Learned Feature Bins Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We identify interaction diversity, systematic coverage of feature combinations, as an important factor for effective tabular model distillation. To operationalize this insight, we propose TabKD, which learns adaptive feature bins aligned with teacher decision boundaries, then generates synthetic queries that ensure uniform pairwise interaction coverage. |
Shovon Niverd Pereira; Krishna Khadka; Yu Lei; |
| 497 | A Unified Prompt for Enhancing Heterogeneous Graph Pre-training Via Edge-based Message Passing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing heterogeneous prompt methods primarily focus on holistic framework design, causing prompts to heavily depend on specific pre-trained models and thus limiting generalization. To address this, we focus on the common encoder module shared across pre-trained models and the multi-relational edge structure unique to heterogeneous graphs, proposing a novel heterogeneous graph prompt-tuning method named HGMRP. |
Fengyu Yan; Xiaobao Wang; Qianhua Tang; Dongxiao He; Di Jin; |
| 498 | Raise One and Infer Three: Toward Reasoning- and Memory-Augmented Diffusion Policy Generalization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we propose "raise one and infer three" diffusion policy (ROITDP), a novel approach that introduces two complementary mechanisms. |
Yihang Zhu; Yuxuan Wang; Tong Li; Jiexi Yan; Xu Yang; Cheng Deng; |
| 499 | Music Atelier: Exploring The Knowing–Doing Gap in LLM Creativity Via Symbolic Music Composition Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a realizational process theory that formalizes creative generation and localizes the knowing–doing gap at the realization stage. |
Zhejing Hu; Yan Liu; Zhi Zhang; Sean Fontaine; Gong Chen; |
| 500 | PhysTrans: A Physics-Aware Transferable Framework for Global Cold-Start Photovoltaic Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose PhysTrans, a physics-aware transferable framework for cold-start PV forecasting. |
Meng Wan; Kaipeng Gao; Jue Wang; Siyan Fang; Xue Miao; Pufen Zhang; Sijie Chang; Peng Shi; Yangang Wang; Zhenbing Zhao; |
This table only includes 500 papers selected by our daily digest algorithm. To continue with the full list (~1,000 papers), please visit Paper Digest: IJCAI-2026 (Full List).