数据来源：HuggingFace Papers Latest Papers1. AlayaWorld: Long-Horizon and Playable Video World GenerationAbstract:Game worlds have traditionally been built through labor-intensive production pipelines, making them costly to develop, difficult to customization, and expensive to modify after deployment. Recent advances in video world models offer a fundamentally different paradigm. Rather than explicitly authoring every component of a virtual environment, these models autoregressively synthesize futu ...

数据来源：HuggingFace Papers Latest Papers1. Vidu S1: A Real-Time Interactive Video Generation ModelAbstract:We introduce Vidu S1, a real-time interactive video generation model supporting voice control of digital characters. Users can control video generation content at any moment through voice instructions. Vidu S1 supports infinite-length real-time video generation without blurring, drift, or visual distortion. Built with TurboDiffusion and TurboServe, Vidu S1 outputs 540p real-time videos at up ...

数据来源：HuggingFace Papers Latest Papers1. Vidu S1: A Real-Time Interactive Video Generation ModelAbstract:We introduce Vidu S1, a real-time interactive video generation model supporting voice control of digital characters. Users can control video generation content at any moment through voice instructions. Vidu S1 supports infinite-length real-time video generation without blurring, drift, or visual distortion. Built with TurboDiffusion and TurboServe, Vidu S1 outputs 540p real-time videos at up ...

数据来源：HuggingFace Papers Latest Papers1. Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based GradingAbstract:AI agents have become capable of autonomously completing short, well-specified tasks. However, existing terminal benchmarks largely focus on simple problems that finish within minutes and are evaluated only by their final outcome. This setup overlooks intermediate progress and partial solutions, yielding sparse reward signals a ...

数据来源：HuggingFace Papers Latest Papers1. Weak-to-Strong Generalization via Direct On-Policy DistillationAbstract:Reinforcement learning with verifiable rewards (RLVR) is a powerful recipe for improving language-model reasoning, but it is expensive to repeat on every new strong model because the target model must generate many rollouts during training. As models scale, post-training itself becomes a bottleneck. We study a weak-to-strong alternative: run RL on a smaller model where rollouts are c ...

数据来源：HuggingFace Papers Latest Papers1. SynthDocBench: Controlled Benchmark for Long-Context Visual Document UnderstandingAbstract:Vision language models (VLMs) have achieved strong performance on visual document understanding benchmarks such as DocVQA, ChartQA, and MMLongBench-Doc. However, real-world documents combine multiple factors such as length, layout complexity, modality, and question difficulty, which makes it difficult to attribute model failures to specific causes. We introduce Syn ...

数据来源：HuggingFace Papers Latest Papers1. Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and EditableAbstract:The capability of a modern AI agent depends not only on its foundation model but also on its harness, which constructs prompts, manages state, invokes tools, and coordinates execution. As models, APIs, environments, and requirements evolve, the harness must be continually modified. Before such a change can be made, a developer or coding agent must identify all code ...

数据来源：HuggingFace Papers Latest Papers1. VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video UnderstandingAbstract:Recent advances in video understanding have spanned motion, long video, and streaming interaction, driving this field toward real-world applications. Despite this progress, current open-source models remain limited in several ways. They often struggle to generalize across diverse video types, making them effective only in specific domains. High computational demand ...

数据来源：HuggingFace Papers Latest Papers1. RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal ResourcesAbstract:Skills are a useful abstraction for software agents, turning human and agent experience into reusable procedural knowledge. Yet existing skill libraries are mostly hand-written, text-centric, or derived from agent traces, leaving tutorial videos and other multimodal human resources largely underused. We present RESOURCE2SKILL, a framework that distills mult ...

数据来源：HuggingFace Papers Latest Papers1. Kimi K3: Open Frontier IntelligenceAbstract:We introduce Kimi K3, a 2.8T parameter Mixture-of-Experts model with 104 billion activated parameters, native vision capabilities, and a 1-million-token context window. Kimi K3 is built on Kimi Delta Attention and Attention Residuals, which improve information flow across sequence length and model depth. Together with Stable LatentMoE, which effectively activates 16 of 896 routed experts per token, and refined ...

数据来源：HuggingFace Papers Latest Papers1. HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data AloneAbstract:Learning deployable manipulation policies is bottlenecked by the scarcity of data that is both high-fidelity and scalable. Real-robot teleoperation is accurate but costly to scale; robot-free UMI capture scales readily, and current practice uses the resulting data mainly for pre-training, adding a small real-robot “anchor” at post-training. We ask whether raisin ...

数据来源：HuggingFace Papers Latest Papers1. TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAMAbstract:Vision-language-action (VLA) models commonly adopt an LLM-centric $V \to L \to A$ pathway, where visual observations are projected into the representation space of a large language model before being decoded into robot actions. Although effective, this design incurs substantial computation and memory overhead at every policy invocation. In this work, we in ...

数据来源：HuggingFace Papers Latest Papers1. LongDS-Bench: On the Failure of Long-Horizon Agentic Data AnalysisAbstract:Real-world data analysis is inherently iterative, yet existing benchmarks mostly evaluate isolated or short interactive tasks, leaving agents’ ability to track evolving analytical context over long horizons untested. We introduce LongDS, a benchmark for long-horizon, multi-turn data analysis where agents must maintain, update, restore, and compose evolving analytical states. LongD ...

数据来源：HuggingFace Papers Latest Papers1. Which Pretraining Paradigm Better Serves Spatial Intelligence? An Empirical Comparison of Vision-Language and Video Generation ModelsAbstract:Spatial intelligence requires visual representations that capture both semantic objects and geometric structure in the physical world. To support this, two major pre-training schemes are now widely used as foundation backbones: Vision-Language Models (VLMs), which use language supervision to align visual observatio ...

数据来源：HuggingFace Papers Latest Papers1. Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline MatchingAbstract:Wide-baseline matching (WBM) requires integrating geometric understanding, viewpoint changes, fine-grained perception, and occlusion reasoning, making it a challenging testbed for spatial reasoning in multimodal large language models (MLLMs) deployed in physical environments. However, current MLLMs lack systematic evaluation and training frameworks for these capabilities. ...