Skip to content
AI News HubLIVE
Original source2 min read

Self-Distilling Future Video Representations for World Action Models

Summary

The paper introduces FRED, a framework that trains World Action Models (WAMs) to produce higher-quality future video representations from noise in a single denoising step via self-distillation with temporal context. Across real-world manipulation tasks, FRED outperforms competing WAMs, with large gains on long-horizon and zero-shot out-of-domain tasks, and boosts human-to-robot skill transfer success from 19.4% to 50.0%.

SourcearXiv RoboticsAuthor: Huiwon Jang, Suhyeok Jang, Hyeonmo Kang, Seungku Kim, Jinwoo Shin, Sihyun Yu
Self-Distilling Future Video Representations for World Action Models
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 21 Oct 2026]

Title:Self-Distilling Future Video Representations for World Action Models

View a PDF of the paper titled Self-Distilling Future Video Representations for World Action Models, by Huiwon Jang and 5 other authors

View PDF HTML (experimental)

Abstract: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.

Comments: 27 pages; Project page: this https URL

Subjects:

Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)

Cite as: arXiv:2610.30320 [cs.RO]

(or arXiv:2610.30320v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2610.30320

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Suhyeok Jang [view email] [v1] Wed, 21 Oct 2026 18:33:13 UTC (2,967 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Self-Distilling Future Video Representations for World Action Models, by Huiwon Jang and 5 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.RO

new | recent | 2026-10

Change to browse by:

cs cs.CV

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • FRED uses self-distillation to predict future representations from noise, targeting representations extracted from ground-truth future observations.
  • Conditioning the video model on historical observations supplies temporal context for better future representation prediction.
  • FRED consistently beats competing WAMs in diverse real-world manipulation scenarios, especially long-horizon and zero-shot out-of-domain tasks.
  • It reaches 50.0% task success on tasks shown only in human videos and absent from robot training data, versus 19.4% for the best baseline.

Highlights and analysis are generated automatically and may contain errors. Check the original source.

More recent stories on this topic · Research