robotics
A Sparse Skeleton Beat a Video World Model
SkeleWAM represents joints, object centers and interaction points instead of reconstructing full video.
Summary
SkeleWAM represents joints, object centers and interaction points instead of reconstructing full video.
SkeleWAM builds a sparse 3D skeleton online from RGB-D observations and robot proprioception, then uses it both for action generation and future-state prediction. On LIBERO-Plus, the 57.1-million-parameter system reported 85.9 percent overall success, 3.7 percentage points above Cosmos-Policy. The finding supports compact geometric state for the tested manipulation suite; it is not a general comparison across every visual world model or physical robot.
Why it matters
SkeleWAM represents joints, object centers and interaction points instead of reconstructing full video.
Limits and context
- The finding supports compact geometric state for the tested manipulation suite; it is not a general comparison across every visual world model or physical robot.
Key claims
SkeleWAM represents joints, object centers and interaction points instead of reconstructing full video.
Qualification: The finding supports compact geometric state for the tested manipulation suite; it is not a general comparison across every visual world model or physical robot.
Evidence: source-2026-10-03-007
Sources
- arXiv preprint 2610.02120arXiv · primary research
Corrections
No corrections have been recorded for this story.