FRED 框架通过自蒸馏和时序条件提升世界行动模型的未来视频表示能力

Published on Oct 21

Authors:

,

,

,

Abstract

FRED improves single-step future video representations in world action models through self-distillation and temporal conditioning, boosting robot policy performance on long-horizon and unseen tasks.

World Action Models (WAMs) have emerged as a promising approach to learning generalist robot policies using rich spatiotemporal priors from pre-trained video diffusion models. A recent line of WAMs improves inference efficiency by conditioning a separate action decoder on intermediate future video representations extracted from a single denoising step, avoiding costly iterative denoising required for video generation. This design makes action prediction depend directly on the quality of these future representations. In this paper, we introduce Future REpresentation learning via self-Distillation with temporal context (FRED), a framework that trains WAMs to improve the quality of future video representations from noise in a single denoising step. Specifically, FRED uses self-distillation to predict future representations from noise, using representations extracted from ground-truth future observations as targets. We further condition the video model on historical observations, providing temporal context for predicting future representations better. Across diverse real-world manipulation scenarios, FRED consistently outperforms competing WAMs. It achieves particularly large gains on long-horizon 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.

View arXiv page View PDF Project page GitHub 4 Add to collection

Get this paper in your agent:

hf papers read 2610.30320

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 3

FRED-AGI-LAB/fred-wan22-5b-droid

FRED-AGI-LAB/fred-wan21-14b-droid

FRED-AGI-LAB/fred-wan22-5b-robocasa-kitchen

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.30320 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.30320 in a Space README.md to link it from this page.

Collections including this paper 1