arXiv 2610.26811 · cs.CV · 2026-10-19
State World Models: Execute the Rules, Generate the Pixels
Chan Yan Ki, Yanran Zhang, Wenzhao Zheng, Xiaofeng Wang, Zheng Zhu, Lei Chen, Jie Zhou, Jiwen Lu
Tsinghua-IVG
在最新榜 #308 本站收录于 2026-10-25
一句话要点
清华的 Stateful Harness 把世界演化和视频渲染分开：按规则维护世界状态，用冻结的视频模型渲染每个事件，再以生成片段更新状态，让交互式世界模型遵守看不见的持久规则。
Tsinghua's Stateful Harness separates world evolution from rendering: it maintains a rule-governed world state, renders events with a frozen video model, and updates state from each clip, so world models obey persistent, invisible rules.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库 项目页
主题与学科
同主题：视觉生成
- StreamEval: Evaluating Interactive Streaming Video Generation Models ▲649
- MaLiang-Harness: A Programmable Path to Image and Video Generation ▲367
- Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation ▲364
- DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models ▲325
- Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation ▲200
同主题：智能体
- Raven: The Harness of Harnesses for Composable Agentic Intelligence 2026-09-27 · ▲748
- False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents 2026-09-30 · ▲642
- Omni-IO Skills: Harnessing Your Agent Omni-Native 2026-09-25 · ▲485
- BizAgentBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business 2026-10-14 · ▲388
- Player-1: Learning to Play from Synthetic Experience 2026-10-14 · ▲347
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-26。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。