Papers

Trending research and the full catalog - each paper linked to the benchmarks, methods, and models it introduces.

Filtered by domain: video-generationClear

RealtimeWAM: One-Step Asynchronous World Action Models

5 Oct 2026

World Action Models (WAMs) incorporate visual representations from video generation backbones to guide action prediction. Recent efficient WAMs adopt Mixture-of-Transformers (MoT) architectures and compute video representations once for reuse by the action expert.

Robotics Video generation World Models

3.0k0.1/h

Filtering here covers the 2,000 most recent papers, as much as one page can hold in memory. See the full index of 22,656 papers.