Starting with four real videos of people carrying boxes, the authors used video-to-video generation to create 256 counterfactual clips.
Counterfactual videos teach humanoids to handle unfamiliar objects
PRISM expands four human demonstrations into 256 synthetic interactions, then converts them into physically plausible training trajectories for real-world deployment.
Big Tech
Zihan Wang · Zhen Wu · Pieter Abbeel · Rocky Duan · Jitendra Malik · Carmelo Sferrazza · +3 more
Amazon FAR · UC Berkeley · Carnegie Mellon University · Stanford
Research Digest··2 min read
The authors present PRISM, a real-to-sim-to-real pipeline for training humanoid robots from a small number of human interaction videos.
Why this paper
From Amazon FAR and 3 others
In one line
Counterfactual video generation turns a handful of real videos into a diverse training set that lets a humanoid pick up, carry, and drop novel objects zero-shot.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§