WorldCast: Distributed Multiplayer World Models

Key points

• Multiplayer world models must generate independently controlled views with consistent representations of both players and their shared environment.1
• Shared scene state enables clients to reuse one another's generated observations to maintain consistent scene appearance across views.1
• Experiments on Counter-Strike 2 demonstrate WorldCast's consistency, real-time performance, and distributed scalability.1
• 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.1

Sources (1)

• [1]WorldCast: Distributed Multiplayer World Models
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 05:49 PM

  We present WorldCast, a distributed multiplayer world model in which each player runs a local client comprising a video generator and a state model.

  Multiplayer world models must generate independently controlled views with consistent representations of both players and their shared environment.

Extractive summary: sentences quoted from the sources.