Hugging Face Daily Papers · · 2 min read

WorldDiT: A Unified Diffusion Architecture for World and Action Modeling

Mirrored from Hugging Face Daily Papers for archival readability. Support the source by reading on the original site.

Tweet: <a href=\"https://x.com/bidhan/status/2082098687464046684\" rel=\"nofollow\">https://x.com/bidhan/status/2082098687464046684</a></p>\n","updatedAt":"2026-07-28T15:13:18.590Z","author":{"_id":"5f1158120c833276f61f1a84","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1608042047613-5f1158120c833276f61f1a84.jpeg","fullname":"Niels Rogge","name":"nielsr","type":"user","isPro":false,"isHf":true,"isHfAdmin":false,"isMod":false,"followerCount":1262,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.5650634169578552},"editors":["nielsr"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1608042047613-5f1158120c833276f61f1a84.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2607.23909","authors":[{"_id":"6a68bc0c5dad3683ba934909","name":"Sen Wang","hidden":false},{"_id":"6a68bc0c5dad3683ba93490a","name":"R. Gnana Praveen","hidden":false},{"_id":"6a68bc0c5dad3683ba93490b","name":"Bidhan Roy","hidden":false},{"_id":"6a68bc0c5dad3683ba93490c","name":"Marcos Villagra","hidden":false}],"publishedAt":"2026-07-27T00:00:00.000Z","submittedOnDailyAt":"2026-07-28T00:00:00.000Z","title":"WorldDiT: A Unified Diffusion Architecture for World and Action Modeling","submittedOnDailyBy":{"_id":"5f1158120c833276f61f1a84","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1608042047613-5f1158120c833276f61f1a84.jpeg","isPro":false,"fullname":"Niels Rogge","user":"nielsr","type":"user","name":"nielsr"},"summary":"Many recent robot policies pursue stronger control by using large pretrained vision-language models (VLMs) as the action backbone. We introduce WorldDiT, a unified diffusion transformer architecture that couples action generation with visual world modeling and achieves strong performance without a large pretrained VLM action backbone. During training, a single diffusion transformer generates continuous action chunks and predicts normalized RGB patch targets from future camera frames. Across four LIBERO simulation suites, WorldDiT lies on the reported Pareto frontier for total model parameters and mean success among methods reporting all four suites. These results provide a strong sub-billion-parameter baseline for future scaling studies.","upvotes":0,"discussionId":"6a68bc0c5dad3683ba93490d","organization":{"_id":"69404a2d504d98ba21c52be1","name":"bageldotcom","fullname":"Bagel Labs","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/6862a65dd478e0d9d375be70/5cu7w3liwUf0OgcntR_rp.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[],"acceptLanguages":["en"],"organization":{"_id":"69404a2d504d98ba21c52be1","name":"bageldotcom","fullname":"Bagel Labs","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/6862a65dd478e0d9d375be70/5cu7w3liwUf0OgcntR_rp.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2607/2607.23909.md","query":{}}">
Papers
arxiv:2607.23909

WorldDiT: A Unified Diffusion Architecture for World and Action Modeling

Published on Jul 27
· Submitted by
Niels Rogge
on Jul 28
Authors:
,

Abstract

Many recent robot policies pursue stronger control by using large pretrained vision-language models (VLMs) as the action backbone. We introduce WorldDiT, a unified diffusion transformer architecture that couples action generation with visual world modeling and achieves strong performance without a large pretrained VLM action backbone. During training, a single diffusion transformer generates continuous action chunks and predicts normalized RGB patch targets from future camera frames. Across four LIBERO simulation suites, WorldDiT lies on the reported Pareto frontier for total model parameters and mean success among methods reporting all four suites. These results provide a strong sub-billion-parameter baseline for future scaling studies.

Community

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images

· Sign up or log in to comment

Get this paper in your agent:

hf papers read 2607.23909
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper

Datasets citing this paper

No dataset linking this paper

Cite arxiv.org/abs/2607.23909 in a dataset README.md to link it from this page.

Spaces citing this paper

No Space linking this paper

Cite arxiv.org/abs/2607.23909 in a Space README.md to link it from this page.

Collections including this paper

No Collection including this paper

Add this paper to a collection to link it from this page.

Discussion (0)

Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.

Sign in →

No comments yet. Sign in and be the first to say something.

More from Hugging Face Daily Papers