arXiv 2610.25666 · cs.CV · 2026-10-19
Frechet Forcing: Training Long-Horizon Streaming World Models from Short Clips
Yian Zhao, Yu Yan, Hongcan Guo, Ruochong Zheng, Jian Zhang, Jie Chen
机构待核实
在最新榜 #331 本站收录于 2026-10-24
一句话要点
Frechet Forcing 解决只用短片段训练的流式视频世界模型在长时间滚动时漂移的问题：不依赖对动作不敏感的外部教师模型，而是要求长滚动结果仍是本场景、遵循动作的真实延续来训练。
Frechet Forcing trains long-horizon streaming video world models from short clips: instead of distillation from an external teacher that ignores actions, it trains long rollouts to remain realistic, action-following continuations of their own scene, reducing drift beyond the training horizon.
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：机器人与具身
- Has GPT-6-Astra Achieved Embodied Intelligence? 2026-10-15 · ▲421
- In-Context Learning for Robots: Methods and Applications 2026-09-28 · ▲388
- GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives 2026-09-30 · ▲310
- HexaShell: A Thin Harness for Exploring the Limits of VLM Agents as Robot Coding Agents 2026-10-16 · ▲294
- EgoXperience: Learning World-Grounded Egocentric Representations from Human Experience 2026-10-19 · ▲189
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。