The authors built a world action model that maintains a sliding window of aligned video and action chunks at staggered noise levels.
Rolling predictions make robot replanning 4.5 times faster
The method reuses partially denoised video and action predictions across control cycles instead of regenerating the full planning horizon.
Big Tech
Yinghua Zhou · Junjie Ye · Yiqi Zhao · Hao Dong · Celina Shiyu Wang · Ruohai Ge · +5 more
University of Southern California · Brown University · Fudan University · Toyota Research Institute
Research Digest··2 min read
Zhou et al.
Why this paper
From Toyota Research Institute and 3 others · Part of World Model Planning for Agents, now 24 papers
In one line
Rolling-WAM distributes video-action denoising across replanning cycles to achieve 4.5x faster replanning without sacrificing manipulation performance.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks (3 benchmarks)
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§