Self-Distilling Future Video Representations for World Action Models
Self-Distilling Future Video Representations for World Action Models
This research presents FRED, a framework that enhances World Action Models by using self-distillation to predict future video representations from noise in a single denoising step. By conditioning on historical observations and using ground-truth future representations as targets, FRED improves action prediction quality. It demonstrates significant gains in long-horizon and out-of-domain tasks under zero-shot generalization, achieving 50.0% task success on tasks absent from robot training data but demonstrated in human videos, compared to 19.4% for the best competing World Action Model.
The paper introduces FRED, a self-distillation framework for World Action Models that improves future video representation quality from noise in a single denoising step using ground-truth targets and historical context, achieving 50.0% task success on zero-shot out-of-domain tasks compared to 19.4% for the best competing model.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
izon and out-of-domain tasks under zero-shot environment generalization, and substantially improves human-to-robot skill transfer, reaching 50.0% task success on tasks absent from robot training data and demonstrated only in human videos, compared with 19.4% for the best competing WAM.
Open source S5
Source：arXiv Robotics — research abstracts · arxiv.org