Computer Vision Papers of the Week

We present Pixel, a co-designed full-stack system for learning general-purpose mobile manipulation.

This report summarizes the observations and insights on multimodal understanding gained from successive generations of Kling.

We introduce VFlash, a method for fast, accurate visual planning through Flash Primitive Decoding.

We introduce NEO-VLA, a structurally encoder-free vision-language-action framework.

We introduce ReLift, an efficient feed-forward framework that recasts dense 3D tracking as geometric trajectory repair and completion.

We present Pixel-UMI, a pipeline for learning environment-aware whole-body policies from human data.

We propose TurnWise, a turn-level GRPO framework that aligns learning with individual streaming decisions.

We introduce EmoReward, a new self-evolving training mechanism that distills evidence reliability from reward traces collected during an actual training run to adaptively guide multi-reward weight allocation in subsequent training by determining which emotional evidence to trust and how much to weight it.

We propose Wave Forcing (WF), which co-designs generation, training, and execution for continuous video output with multi-step denoising.

We introduce DreamX, which repurposes a pretrained video diffusion model as a universal latent action learner.

In this work, we introduce Factorized MLLM Embeddings (FactEmbed), which decouples compositional query comprehension from building discriminative embeddings.

We show that harness design can be automated, offering a strong alternative to finetuning on a novel setup.

We present \textbf{WeLM-Image}, a unified image foundation model that integrates multimodal understanding into text-to-image generation, instruction-guided editing, and multi-reference synthesis.

In this work, we present Route Anything, a unified framework for studying model and policy routing across general-purpose AI systems.

For example, an agent that calls the VLA in the agentic loop can stall the fast execution, while a VLA that calls the agent on errors tends to re-trigger fallbacks repeatedly or completely miss silent failures. To address this, we propose REA (Routed Embodied Agent), a unified runtime where a deliberative System 2, an embodied router System 1 and reactive System 0 policies cooperate under a single golden rule - no running policy waits on the brain.

We attribute this failure to a fundamental modality mismatch: reasoning is performed in a discrete token space, whereas image generation operates in a continuous space. To bridge this gap, we introduce a Latent Reasoning framework in Continuous space (LARC), which alleviates the token-level bottleneck by reasoning over continuous hidden states.

We present EDGAR (Efficient Diffusion-Driven Gaussian Avatar Refinement), a conditional diffusion framework designed to enhance the quality of Gaussian avatars by correcting artifacts while preserving identity fidelity.

At the same time, similar ideas are often described using different terminology across these tasks, further complicating efforts to develop a systematic understanding of the field. In this report, we address these challenges through two contributions. First, we introduce a unified taxonomy for characterizing agentic systems across diverse computer graphics tasks.

Consequently, they provide limited supervision and evaluation for multimodal stateful interaction, which requires models to understand, maintain, update, and faithfully realize evolving dialogue states across turns. To address this gap, we introduce YANAMI, the first large-scale multimodal dialogue dataset and benchmark for stateful interaction, comprising YANAMI-400K and YANAMI-Bench.

We further introduce the normalized participation ratio (nPR) to characterize the channel-wise organization of the gates and find that, across REPA teachers, projector architectures, and radial-objective targets, broader gate participation accompanies better generation quality. Guided by this insight, we propose a simple teacher-free radial objective that promotes broader gate participation through feature-norm regularization, without pairwise feature comparisons.