WorldCast: Distributed Multiplayer World Models

Hugging Face Daily Papers Papers
world-models multiplayer video-generation distributed-systems real-time-inference

Summary

WorldCast 提出了一种分布式多人世界模型，每个玩家本地运行视频生成器与状态模型，通过交换玩家状态和共享场景状态实现一致、可扩展的实时多人生成，在 Counter-Strike 2 上验证了其一致性与可扩展性。

Multiplayer world models must generate independently controlled views with consistent representations of both players and their shared environment. Most existing approaches coordinate multiple players through joint multi-view generation, whose cost grows with each additional player. We present WorldCast, a distributed multiplayer world model in which each player runs a local client comprising a video generator and a state model. Using recorded player positions and map geometry during training, the state model estimates the player's position from generated video and control inputs. Clients exchange player states and project them into camera-aligned player state fields that guide where and how other players are rendered. Shared scene state enables clients to reuse one another's generated observations to maintain consistent scene appearance across views. Experiments on Counter-Strike 2 demonstrate WorldCast's consistency, real-time performance, and distributed scalability. The camera-aligned player state field improves player rendering rates by over an order of magnitude over joint-generation methods, while shared scene state improves visual consistency over whole rounds. Each client runs in real time and exchanges only player and scene states, enabling scalable multiplayer generation without a centralized computational bottleneck. Image quality remains stable over hour-long rollouts.
Original Article
View Cached Full Text

Cached at: 10/14/26, 02:52 PM

Paper page - WorldCast: Distributed Multiplayer World Models

Source: https://huggingface.co/papers/2610.12412 Published on Oct 8

·

Submitted byhttps://huggingface.co/ZiyangYe

Ziyangon Oct 14

Authors:

,

,

,

,

,

,

,

,

,

,

Abstract

Multiplayerworldmodelsmustgenerateindependentlycontrolledviewswithconsistentrepresentationsofbothplayersandtheirsharedenvironment.Mostexistingapproachescoordinatemultipleplayersthroughjointmulti-viewgeneration,whosecostgrowswitheachadditionalplayer.WepresentWorldCast,adistributedmultiplayerworldmodelinwhicheachplayerrunsalocalclientcomprisingavideogeneratorandastatemodel.Usingrecordedplayerpositionsandmapgeometryduringtraining,thestatemodelestimatestheplayer’spositionfromgeneratedvideoandcontrolinputs.Clientsexchangeplayerstatesandprojectthemintocamera-alignedplayerstatefieldsthatguidewhereandhowotherplayersarerendered.Sharedscenestateenablesclientstoreuseoneanother’sgeneratedobservationstomaintainconsistentsceneappearanceacrossviews.ExperimentsonCounter-Strike2demonstrateWorldCast’sconsistency,real-timeperformance,anddistributedscalability.Thecamera-alignedplayerstatefieldimprovesplayerrenderingratesbyoveranorderofmagnitudeoverjoint-generationmethods,whilesharedscenestateimprovesvisualconsistencyoverwholerounds.Eachclientrunsinrealtimeandexchangesonlyplayerandscenestates,enablingscalablemultiplayergenerationwithoutacentralizedcomputationalbottleneck.Imagequalityremainsstableoverhour-longrollouts.

View arXiv pageView PDFProject pageGitHub34Add to collection

Models citing this paper1

#### ZiyangYe/WorldCast Image-to-Video• Updated4 days ago • 37 • 3

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2610.12412 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2610.12412 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

MASS: Multiplayer World Models with Authoritative Shared State

Hugging Face Daily Papers

This paper introduces MASS, a method for multiplayer world models that disentangles world dynamics from view rendering using an authoritative shared state, enabling scalable and consistent multi-agent simulation with up to 1,024 concurrent players.

MultiWorld: Scalable Multi-Agent Multi-View Video World Models

Hugging Face Daily Papers

MultiWorld is a unified framework for multi-agent multi-view video world modeling that achieves accurate control of multiple agents while maintaining multi-view consistency through a Multi-Agent Condition Module and Global State Encoder.

Matrix-Game: Interactive World Foundation Model

Papers with Code Trending

Matrix-Game 是一个 17B 参数的交互式世界基础模型，通过两阶段训练（大规模无标注预训练 + 动作标注训练）实现可控的 Minecraft 游戏世界生成，在动作可控性与物理一致性上超越 Oasis 和 MineWorld 等开源模型，并将开源权重与 GameWorld Score 基准。