Paper summary
Paper summary: Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players
Gamma-World is a generative world model for interactive video with many simultaneously controlled agents, using a parameter-free simplex rotary agent encoding and hub-token attention, distilled for real-time 24 FPS generation.
- Each agent gets a distinct rotary phase as a vertex of a regular simplex, so identities are distinct but interchangeable, with no learned per-slot IDs.
- Hub tokens mediate interaction between agents, making cross-agent attention linear rather than quadratic in the number of agents.