Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation

Hugging Face Daily Papers Papers

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。

Long-form agentic video generation must turn a screenplay into shots that remain spatially and temporally consistent across nonconsecutive requests. Passing prompts or recent frames between shots does not provide a shared spatial frame for revisiting a scene or a time-indexed record for replaying an earlier event. We present Any Time, Any Space (ATAS), which compiles a screenplay into shot requests with explicit location, camera, and event-time references. Before generation, it retrieves relevant evidence from a scene memory of registered static geometry and an event memory of dynamic observations indexed by scene, event, and time. After generation, ATAS reconstructs and registers the clip. It updates memory only when review and state checks accept the observation, while film delivery remains independent of memory admission. Across four video generators, ATAS improves all reported cross-shot consistency measures and achieves the highest aggregate benchmark score for each backbone. It also outperforms the compared agents and 3D-guided methods on target-image spatial revisit, leads three event-recapture criteria, and receives the highest human ratings on all six criteria. The video results and code are available on our project page: https://lhmd.top/atas/.
Original Article
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

Video-Arena: A Scalable Agentic Video Benchmark for Spatiotemporal Capability

Hugging Face Daily Papers

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

Hugging Face Daily Papers

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。

Temporal Specification Guidance for Text-to-Video Generation

arXiv cs.AI

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。