Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players
- Published
- Source
- arXiv
- Paper number
- 254
- Field
- Computer Vision
- arXiv ID
- 2605.28816
Key points
- The hub token attends to all agent tokens and to other hub tokens.
- Bidirectional teacher training: the model is first trained as a standard diffusion model with access to the full temporal sequence. This teacher learns the full distribution of multi-agent interaction with high fidelity.
- Causal student training: to enable real-time rollouts, the student model is trained with a causal structure. Unlike the teacher, the student sees only the past and the present, and it uses a Sparse Hub Attention mask plus noise levels sampled independently for each frame block.
Paper links
External research summaries. These are not HDATF publications or measured product results.