τ0 -WM: A Unified Video-Action World Model for Robotic Manipulation</p>\n<p>largest open-source robotic world model</p>\n","updatedAt":"2026-06-02T14:35:49.021Z","author":{"_id":"64f8cb8ed04a890f5380d9a4","avatarUrl":"/avatars/d6fdfdbb0c10141aa3b4c832d928121b.svg","fullname":"Jianlan Luo","name":"jianlanluo","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":10,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.6399581432342529},"editors":["jianlanluo"],"editorAvatarUrls":["/avatars/d6fdfdbb0c10141aa3b4c832d928121b.svg"],"reactions":[],"isReport":false}},{"id":"6a1f8ab8acced0adcf949658","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":360,"isUserFollowing":false},"createdAt":"2026-06-03T02:00:24.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"This is an automated message from the [Librarian Bot](https://huggingface.co/librarian-bots). I found the following papers similar to this paper. \n\nThe following papers were recommended by the Semantic Scholar API \n\n* [Being-H0.7: A Latent World-Action Model from Egocentric Videos](https://huggingface.co/papers/2605.00078) (2026)\n* [MotuBrain: An Advanced World Action Model for Robot Control](https://huggingface.co/papers/2604.27792) (2026)\n* [AIM: Intent-Aware Unified world action Modeling with Spatial Value Maps](https://huggingface.co/papers/2604.11135) (2026)\n* [Learning Human-Intention Priors from Large-Scale Human Demonstrations for Robotic Manipulation](https://huggingface.co/papers/2604.24681) (2026)\n* [Action Images: End-to-End Policy Learning via Multiview Video Generation](https://huggingface.co/papers/2604.06168) (2026)\n* [Point Tracking Improves World Action Models](https://huggingface.co/papers/2605.23856) (2026)\n* [Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments](https://huggingface.co/papers/2605.30280) (2026)\n\n\n Please give a thumbs up to this comment if you found it helpful!\n\n If you want recommendations for any Paper on Hugging Face checkout [this](https://huggingface.co/spaces/librarian-bots/recommend_similar_papers) Space\n\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: `@librarian-bot recommend`","html":"<p>This is an automated message from the <a href=\"https://huggingface.co/librarian-bots\">Librarian Bot</a>. I found the following papers similar to this paper. </p>\n<p>The following papers were recommended by the Semantic Scholar API </p>\n<ul>\n<li><a href=\"https://huggingface.co/papers/2605.00078\">Being-H0.7: A Latent World-Action Model from Egocentric Videos</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2604.27792\">MotuBrain: An Advanced World Action Model for Robot Control</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2604.11135\">AIM: Intent-Aware Unified world action Modeling with Spatial Value Maps</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2604.24681\">Learning Human-Intention Priors from Large-Scale Human Demonstrations for Robotic Manipulation</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2604.06168\">Action Images: End-to-End Policy Learning via Multiview Video Generation</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2605.23856\">Point Tracking Improves World Action Models</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2605.30280\">Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments</a> (2026)</li>\n</ul>\n<p> Please give a thumbs up to this comment if you found it helpful!</p>\n<p> If you want recommendations for any Paper on Hugging Face checkout <a href=\"https://huggingface.co/spaces/librarian-bots/recommend_similar_papers\">this</a> Space</p>\n<p> You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: <code><span class=\"SVELTE_PARTIAL_HYDRATER contents\" data-target=\"UserMention\" data-props=\"{&quot;user&quot;:&quot;librarian-bot&quot;}\"><span class=\"inline-block\"><span class=\"contents\"><a href=\"/librarian-bot\">@<span class=\"underline\">librarian-bot</span></a></span> </span></span> recommend</code></p>\n","updatedAt":"2026-06-03T02:00:24.691Z","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":360,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.6863659620285034},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2606.01027","authors":[{"_id":"6a1eea2ce292c1c78ecb10bb","name":"Pengfei Zhou","hidden":false},{"_id":"6a1eea2ce292c1c78ecb10bc","name":"Shengcong Chen","hidden":false},{"_id":"6a1eea2ce292c1c78ecb10bd","name":"Di Chen","hidden":false},{"_id":"6a1eea2ce292c1c78ecb10be","name":"Jiaxu Wang","hidden":false},{"_id":"6a1eea2ce292c1c78ecb10bf","name":"Rongjun Jin","hidden":false},{"_id":"6a1eea2ce292c1c78ecb10c0","name":"Bingwen Zhu","hidden":false},{"_id":"6a1eea2ce292c1c78ecb10c1","name":"Yike Pan","hidden":false},{"_id":"6a1eea2ce292c1c78ecb10c2","name":"Songen Gu","hidden":false},{"_id":"6a1eea2ce292c1c78ecb10c3","name":"Kuanning Wang","hidden":false},{"_id":"6a1eea2ce292c1c78ecb10c4","name":"Shufeng Nan","hidden":false},{"_id":"6a1eea2ce292c1c78ecb10c5","name":"Xingyu Qiu","hidden":false},{"_id":"6a1eea2ce292c1c78ecb10c6","name":"Chenhao Qiu","hidden":false},{"_id":"6a1eea2ce292c1c78ecb10c7","name":"Pu Yang","hidden":false},{"_id":"6a1eea2ce292c1c78ecb10c8","name":"Yunuo Cai","hidden":false},{"_id":"6a1eea2ce292c1c78ecb10c9","name":"Jianxiong Gao","hidden":false},{"_id":"6a1eea2ce292c1c78ecb10ca","name":"Yifan Li","hidden":false},{"_id":"6a1eea2ce292c1c78ecb10cb","name":"Yanwei Fu","hidden":false},{"_id":"6a1eea2ce292c1c78ecb10cc","name":"Xiangyu Yue","hidden":false},{"_id":"6a1eea2ce292c1c78ecb10cd","name":"Zhi Chen","hidden":false},{"_id":"6a1eea2ce292c1c78ecb10ce","name":"Jianlan Luo","hidden":false}],"publishedAt":"2026-05-31T00:00:00.000Z","submittedOnDailyAt":"2026-06-02T00:00:00.000Z","title":"τ_0-WM: A Unified Video-Action World Model for Robotic Manipulation","submittedOnDailyBy":{"_id":"64f8cb8ed04a890f5380d9a4","avatarUrl":"/avatars/d6fdfdbb0c10141aa3b4c832d928121b.svg","isPro":false,"fullname":"Jianlan Luo","user":"jianlanluo","type":"user","name":"jianlanluo"},"summary":"Robotic manipulation requires models that generate executable actions while anticipating and evaluating their future consequences before physical execution. We present τ_0-World Model (τ_0-WM), a unified video-action world model that integrates policy learning, video prediction, and action evaluation within a single future-predictive framework. Built on a shared video diffusion backbone, τ_0-WM provides two complementary interfaces. First, a video action model jointly predicts future visual latents and continuous action chunks from multi-view observations, language instructions, and robot state. Second, an action-conditioned video simulator rolls out candidate action chunks into multi-view futures and predicts dense task-progress scores. The model is trained on approximately 27{,}300 hours of real-robot teleoperation, UMI-style interaction, egocentric human videos, and rollout or failure trajectories using modality-specific supervision masks. At inference time, τ_0-WM uses test-time computation to sample action candidates, rank them with re-denoising consistency, and invoke simulator-based rectification for low-quality candidates. On challenging long-horizon and fine-grained robotic manipulation tasks, τ_0-WM shows superior performance over other relevant baselines.","upvotes":0,"discussionId":"6a1eea2ce292c1c78ecb10cf","ai_summary":"A unified video-action world model integrates policy learning, video prediction, and action evaluation using a shared video diffusion backbone for robotic manipulation tasks.","ai_keywords":["video diffusion backbone","video action model","action-conditioned video simulator","test-time computation","re-denoising consistency","robotic manipulation","video prediction","policy learning","action evaluation"],"ai_summary_model":"Qwen/Qwen2.5-Coder-32B-Instruct"},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[],"acceptLanguages":["en"],"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2606/2606.01027.md"}">

Get this paper in your agent:

Don't have the latest CLI?

Cite arxiv.org/abs/2606.01027 in a model README.md to link it from this page.

Cite arxiv.org/abs/2606.01027 in a dataset README.md to link it from this page.

Cite arxiv.org/abs/2606.01027 in a Space README.md to link it from this page.