Streaming Multi-Agent Autoregressive Diffusion Model with World State Registers
Ranking
Overall
87
Content
95
Popularity
69
Observed public metrics from 1 member.
Merged summary
TL;DR - WorldWeaver is a streaming multi-agent video diffusion model that maintains persistent shared and agent-specific state across generated views. Explicit state tracking improves logical consistency and video quality in two-agent Minecraft experiments.
- Uses dynamically updated learnable world-state registers alongside observation history.
- Supervises registers with agent status, global bird’s-eye views, and scene text.
- Separates world-state and visual-frame modeling weights through a Mixture-of-Transformers architecture.
- Targets consistent world evolution across multiple agents and viewpoints.
Sources (1)
Streaming Multi-Agent Autoregressive Diffusion Model with World State Registers
Public signals
Hugging Face upvotes 16
TL;DR - WorldWeaver is a streaming multi-agent video diffusion model that maintains persistent shared and agent-specific state across generated views. Explicit state tracking improves logical consistency and video quality in two-agent Minecraft experiments.
- Uses dynamically updated learnable world-state registers alongside observation history.
- Supervises registers with agent status, global bird’s-eye views, and scene text.
- Separates world-state and visual-frame modeling weights through a Mixture-of-Transformers architecture.
- Targets consistent world evolution across multiple agents and viewpoints.