arXiv 2610.31668 · cs.CV · 2026-10-22
Reading, Writing, Sharing, and Interacting with the World through Video
Shengqiong Wu, Meng Luo, Bobo Li, Ziwei Liu, Shuicheng Yan, Ming-Hsuan Yang, Philip Torr, Hao Fei
University of Oxford
一句话要点
论文从世界建模视角系统梳理了视频理解与生成的四大核心操作:阅读、写作、共享和交互,强调从片段识别转向对持久状态和因果一致性的建模。
This survey unifies video understanding and generation through world modeling, focusing on four operations: reading, writing, sharing, and interaction, shifting from clip-level recognition to persistent, causal state modeling.
要点
- 视频理解与生成长期缺乏对世界动态和因果关系的建模,难以实现稳定、可预测的状态演化。
- 提出以世界建模为统一框架,将视频视为对潜在世界状态的失真投影,划分阅读(推断世界属性)、写作(从条件合成视频)、共享(共用模型理解与生成)和交互(预测并更新状态)四大操作。
- 研究发现当前方法正逐步从片段级感知转向持久状态、可控演化和物理因果一致性,并通过交互行为进行评估,验证了模型在动态世界中的合理性。
- 该视角系统性整合了视频建模方向,推动研究向可解释、可交互的动态世界建模演进,但对长期状态一致性和真实物理规律的建模仍面临挑战。
English overview
This survey presents a unifying framework for video foundation models through world modeling, organizing the literature around four operations: reading, writing, sharing, and interacting. It highlights a shift from clip-level perception to persistent world states, controllable evolution, and causal validity, emphasizing evaluation via interaction and downstream decisions.
只根据 arXiv 官方摘要,由开源模型整理,经数字/专名自动核对(必须在摘要中出现),以论文原文为准。
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:评测与数据
- Spectral-Spatial Interpretation 2026-10-15 · ▲753
- Has GPT-6-Astra Achieved Embodied Intelligence? 2026-10-15 · ▲421
- BizAgentBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business 2026-10-14 · ▲388
- RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations 2026-10-01 · ▲287
- FDE-Gym: The Last Mile of AI Delivery 2026-10-15 · ▲270
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 2026-10-22。
要点由本站根据摘要自写,不转载摘要原文,请阅读原文。