数据来源：HuggingFace Papers Latest Papers1. Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy DistillationAbstract:Policy-shift distillation reuses the difference between a teacher’s log probabilities before and after reinforcement learning (RL) as supervision on student-generated trajectories. However, this endpoint policy shift cannot reveal whether local action preferences evolved consistently during teacher training. The same endpoint shift can result from early and late ...

数据来源：HuggingFace Papers Latest Papers1. HexaShell: A Thin Harness for Exploring the Limits of VLM Agents as Robot Coding AgentsAbstract:Agents built on vision language models (VLMs) now compete with learned policies on robot manipulation leaderboards. We ask how far a coding agent can go when it controls a robot instead of a computer, and where it stops. Our system, HexaShell, keeps the harness thin: it only turns the agent’s commands into robot motion. The agent drives a robot with two arms t ...

数据来源：HuggingFace Papers Latest Papers1. EMBER: Predicting TCR—pMHC Binding Without a Docked ComplexAbstract:We propose EMBER, a structure-based framework for TCR—pMHC binding prediction that eliminates the need for a predicted docked complex, and with it the placement error that dominates such predictions. Traditional structure-based predictors utilize the co-folded complex structure of the receptor and the antigen and interpret binding from its contact surface. Consequently, every downstream ...

数据来源：HuggingFace Papers Latest Papers1. Focused Omni-Modal GUI AgentsAbstract:Graphical User Interface (GUI) agents increasingly act over streaming omni-modal observations spanning screenshots, audio, video, interaction history, and device states. However, exposing this complete context uniformly at every step ignores that relevance is transient and sparse: the signal determining one action can become clutter at the next. Because executed actions feed back into the context, these errors compou ...

数据来源：HuggingFace Papers Latest Papers1. StreamEval: Evaluating Interactive Streaming Video Generation ModelsAbstract:As streaming video generation advances, enabling real-time interaction with generated video is becoming increasingly important. We introduce StreamEval, a unified benchmark for interactive streaming video generation spanning five tasks: avatar dialogue, avatar performance, world generation, instruction editing, and reference editing. StreamEval comprises 300 scripted test cases ...

数据来源：HuggingFace Papers Latest Papers1. WeVisOne-VL: Unified Visual Perception from Objects to PixelsAbstract:Existing vision-language models (VLMs) remain unreliable for fine-grained visual perception. In this report, we present WeVisOne-VL (WeChat Vision All-in-One), a powerful VLM that unifies object-level and pixel-level perception through structured next-token prediction. It supports multiple visual tasks including object detection, referring localization, counting, OCR, segmentation, and ...

数据来源：HuggingFace Papers Latest Papers1. Omni-Woodpecker: Hallucination Correction via Evidence-Prior Rebalancing for Omni LLMsAbstract:Recent Omni LLMs (OLLMs) have demonstrated remarkable capabilities in joint audio-visual reasoning, yet cross-modal hallucinations remain a major challenge. Existing mitigation methods mainly operate at the output level, overlooking the entanglement of grounding evidence and learned priors within fused representations. To address this issue, we propose Omni-Woo ...

数据来源：HuggingFace Papers Latest Papers1. WorldCast: World-Consistent Character Video Generation with Large-Angle Camera ControlAbstract:Precise camera control is essential for cinematic character video generation, yet existing methods struggle to follow large-angle trajectories with combined rotation, translation, and radius variation from arbitrary initial azimuths. Such viewpoint changes also reveal character regions unseen in the initial frame, causing geometric distortions, appearance degra ...

数据来源：HuggingFace Papers Latest Papers1. Rollback: Experience Backtracking in World Models for Policy ImprovementAbstract:Action-conditioned world models offer a scalable alternative to costly real-world interaction for improving robot policies. However, existing world-model-based methods largely treat world models as forward-only surrogates of the physical environment, leaving untapped a capability no physical environment affords: rewinding to past decision points to explore counterfactual fut ...

数据来源：HuggingFace Papers Latest Papers1. DTCA: Denoising Token Credit Assignment for Reinforcement Learning in Diffusion Language ModelsAbstract:Diffusion language models (DLMs) generate text through iterative denoising, enabling bidirectional context modeling and parallel token refinement. Recent studies have applied reinforcement learning (RL) to DLMs and improved their reasoning performance. However, the iterative denoising process makes credit assignment more challenging, as final outcome r ...

数据来源：HuggingFace Papers Latest Papers1. WorkFactory: Turning Professional Intents into Executable Work for Scalable Agent TrainingAbstract:Scaling supervised training for working agents requires diverse professional tasks that yield reliable expert demonstrations. However, missing or inconsistent task information can obstruct teacher execution and weaken the resulting supervision. We propose WorkFactory, a scalable framework for constructing coherent and executable professional tasks. Starting ...

数据来源：HuggingFace Papers Latest Papers1. Intrinsic Distribution MatchingAbstract:One-step and few-step text-to-image generation must accurately render the details specified in the prompt despite limited opportunities for refinement. Distribution matching distillation (DMD) uses score differences to bring the generated distribution closer to a reference distribution. Following prior work, we estimate this difference with internal velocity branches, avoiding a separate fake-score network. We ask ...

数据来源：HuggingFace Papers Latest Papers1. Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMsAbstract:Diffusion vision-language models (DVLMs) process their entire input at every denoising step. Since visual tokens make up 89-97% of this input on the benchmarks we study, most of the decoding computation is spent repeatedly processing the same image. Visual token pruning methods partially relieve this burden by removing part of the visual tokens, but they lose th ...

数据来源：HuggingFace Papers Latest Papers1. HiFOR: Hierarchical Foresight with Action-Guided World Grounding for Vision-Language-Action ModelAbstract:Vision-Language-Action (VLA) models have demonstrated promising capabilities in robotic manipulation by integrating visual perception, language understanding, and action generation. Recent advances have further incorporated future prediction to enhance the understanding of environmental dynamics and task progression. However, existing methods often m ...

数据来源：HuggingFace Papers Latest Papers1. Video Generation Meets Agent Harness: Agentic Video Generation, Agentic World Modeling and Recursive Self-ImprovementAbstract:Video generation is shifting from end-to-end synthesis toward agentic generation, where planning, tool use, and feedback enable coherent, controllable multi-shot videos. In parallel, video world models provide action-conditioned observations and predicted futures, serving as interactive environments for agents. We study their inte ...