Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation
Summary
提出 Any Time, Any Space (ATAS) 框架,将剧本编译为带显式位置、相机和事件时间引用的镜头请求,通过场景记忆和事件记忆实现长时程 agentic 视频生成的跨镜头时空一致性,在四种视频生成器上均提升一致性指标并取得最佳综合评分。
View Cached Full Text
Cached at: 10/15/26, 02:55 AM
Paper page - Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation
Source: https://huggingface.co/papers/2610.20571
Abstract
Long-formagenticvideogenerationmustturnascreenplayintoshotsthatremainspatiallyandtemporallyconsistentacrossnonconsecutiverequests.Passingpromptsorrecentframesbetweenshotsdoesnotprovideasharedspatialframeforrevisitingasceneoratime-indexedrecordforreplayinganearlierevent.WepresentAnyTime,AnySpace(ATAS),whichcompilesascreenplayintoshotrequestswithexplicitlocation,camera,andevent-timereferences.Beforegeneration,itretrievesrelevantevidencefromascenememoryofregisteredstaticgeometryandaneventmemoryofdynamicobservationsindexedbyscene,event,andtime.Aftergeneration,ATASreconstructsandregisterstheclip.Itupdatesmemoryonlywhenreviewandstatechecksaccepttheobservation,whilefilmdeliveryremainsindependentofmemoryadmission.Acrossfourvideogenerators,ATASimprovesallreportedcross-shotconsistencymeasuresandachievesthehighestaggregatebenchmarkscoreforeachbackbone.Italsooutperformsthecomparedagentsand3D-guidedmethodsontarget-imagespatialrevisit,leadsthreeevent-recapturecriteria,andreceivesthehighesthumanratingsonallsixcriteria.Thevideoresultsandcodeareavailableonourprojectpage:https://lhmd.top/atas/.
View arXiv pageView PDFProject pageGitHubAdd to collection
Get this paper in your agent:
hf papers read 2610\.20571
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2610.20571 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2610.20571 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2610.20571 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
FrameMorrow: Future-guided Frame Selection with Prospective Tokens for Long-Horizon Video Generation
FrameMorrow 提出一种面向长时序视频生成的前瞻性帧选择方法,通过预测代表未来信息需求的紧凑 prospective tokens 来从历史中挑选相关帧,实现跨生成器的即插即用集成,并在五个基准、11 个生成模型上取得一致提升。
Video-Arena: A Scalable Agentic Video Benchmark for Spatiotemporal Capability
Video-Arena introduces a scalable benchmark that turns competitive games into verifiable tests of spatiotemporal world-state understanding and tracking in videos, evaluating models under native and tool-assisted agentic protocols and finding that both still struggle with state updates over time.
CausalAlign: Causal Alignment of Video Generation Models for Consistent Ego-Motion
CausalAlign 论文提出一种因果对齐框架,通过将扩散视频生成模型的内部表征与 3D 基础模型在 delta-token 空间中对齐,改善长时程相机自运动的一致性,在几何一致性上提升超过 20%,并提升了具身操作任务中世界动作模型的成功率。
Video Generation Meets Agent Harness: Agentic Video Generation, Agentic World Modeling and Recursive Self-Improvement
A report examining the intersection of video generation and agent harnesses, covering agentic video generation, agentic world modeling, and recursive self-improvement for autonomous multi-shot video production.
Temporal Specification Guidance for Text-to-Video Generation
Toyota Research与宾大提出Temporal Specification Guidance (TSG),一种免训练的推理时框架,将时序逻辑规格转化为可微目标,通过梯度引导注意力偏置来改善文本到视频模型对顺序、时序与持续性约束的遵循,在五个模型上比CFG提升9.5–20个百分点的规格满足率。