<video src=\"https://cdn-uploads.huggingface.co/production/uploads/68a34b763d0ab4811c881195/M6Gt3ueffojoixIcI3xvF.webm\" controls=\"\" class=\"max-w-full!\"></video></p>\n","updatedAt":"2026-07-29T04:52:41.472Z","author":{"_id":"68a34b763d0ab4811c881195","avatarUrl":"/avatars/6d2e2957dcd54887881fdf028a2c21b3.svg","fullname":"alq","name":"somnvz","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.278155654668808},"editors":["somnvz"],"editorAvatarUrls":["/avatars/6d2e2957dcd54887881fdf028a2c21b3.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2607.26037","authors":[{"_id":"6a69618f9d3a1231d492b7b6","name":"Jiacong Xu","hidden":false},{"_id":"6a69618f9d3a1231d492b7b7","name":"Hanwen Jiang","hidden":false},{"_id":"6a69618f9d3a1231d492b7b8","name":"Zhixin Shu","hidden":false},{"_id":"6a69618f9d3a1231d492b7b9","name":"Kalyan Sunkavalli","hidden":false},{"_id":"6a69618f9d3a1231d492b7ba","name":"Vishal M. Patel","hidden":false},{"_id":"6a69618f9d3a1231d492b7bb","name":"Yiqun Mei","hidden":false}],"mediaUrls":["https://cdn-uploads.huggingface.co/production/uploads/6039478ab3ecf716b1a5fd4d/J4rEn3_UurIFAFXZfsiHd.mp4"],"publishedAt":"2026-07-28T00:00:00.000Z","submittedOnDailyAt":"2026-07-29T00:00:00.000Z","title":"Wonder: Video World Model Done Better","submittedOnDailyBy":{"_id":"6039478ab3ecf716b1a5fd4d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6039478ab3ecf716b1a5fd4d/_Thy4E7taiSYBLKxEKJbT.jpeg","isPro":true,"fullname":"taesiri","user":"taesiri","type":"user","name":"taesiri"},"summary":"We present Wonder, a general-purpose video world model for real-time, camera-controllable world exploration. Given an image or a conditional video, Wonder constructs a playable world where users can navigate interactively by moving the camera, discovering unseen regions, and revisiting previously observed areas in real time and over a long-term horizon. Achieving this capability requires a system-level co-design of control method, memory mechanism, and training strategy. We introduce a novel camera conditioning with a dense coordinate field whose renderings provide spatially aligned motion and orientation cues, allowing the model to interpret camera motion directly as visual evidence. To support fast and precise memory retrieval over a growing generation context, we propose an efficient sparse attention-based memory mechanism, enabling the model to selectively attend to a small set of relevant context tokens at inference time, regardless of actual context length. We further develop several techniques to rectify the self-forcing-style distillation pipeline, improving the student model's ability to respect control signals, as well as maintaining diverse generation modes and long-term memory from the teacher. Together, these components enable Wonder to synthesize diverse, minute-scale videos at 16 FPS while preserving coherent geometry, appearance, and dynamics across long rollouts. Beyond image-to-video generation, Wonder naturally supports video-conditioned generation, allowing existing dynamic scenes to be re-shot in real time.","upvotes":7,"discussionId":"6a69618f9d3a1231d492b7bc","projectPage":"https://wonder-world-model.github.io/","organization":{"_id":"61e5d14f77496de0a6d95c6b","name":"adobe","fullname":"Adobe","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/1645217431826-61e35e517ac6b6d06cfa8081.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"63ca8e060609f1def7e6548a","avatarUrl":"/avatars/1da7947840cb87d5f77c0af9ee11f9c2.svg","isPro":true,"fullname":"Yi Jung","user":"YJ-142150","type":"user"},{"_id":"67f5e63688b2c5303ab5be7a","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/67f5e63688b2c5303ab5be7a/QSH8-QZH6l3KradXqNxJT.png","isPro":false,"fullname":"Chengxuan Qian","user":"Raymond-Qiancx","type":"user"},{"_id":"647f01d3838ac3601fc6c17b","avatarUrl":"/avatars/9605767bdf8a896b9c99f974797715c5.svg","isPro":false,"fullname":"Wangjianxiong","user":"wjx138819","type":"user"},{"_id":"65ce020f8b4adee8718cbcff","avatarUrl":"/avatars/b82f2286fd4f335dbe4bf5fe86d39410.svg","isPro":false,"fullname":"yusong hu","user":"songsongh","type":"user"},{"_id":"620783f24e28382272337ba4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/620783f24e28382272337ba4/zkUveQPNiDfYjgGhuFErj.jpeg","isPro":false,"fullname":"GuoLiangTang","user":"Tommy930","type":"user"},{"_id":"65c4eb7cd1dcbd30d86febec","avatarUrl":"/avatars/001c8f02e8ce794b2c21883628b2da72.svg","isPro":false,"fullname":"free-bit","user":"free-bit","type":"user"},{"_id":"6848933f729cfa426d465951","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/IjRV2AW77lTJ3CZtyixfe.png","isPro":false,"fullname":"Maya","user":"Yamanjuinc","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"61e5d14f77496de0a6d95c6b","name":"adobe","fullname":"Adobe","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/1645217431826-61e35e517ac6b6d06cfa8081.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2607/2607.26037.md","query":{}}">

Get this paper in your agent:

Don't have the latest CLI?

Cite arxiv.org/abs/2607.26037 in a model README.md to link it from this page.

Cite arxiv.org/abs/2607.26037 in a dataset README.md to link it from this page.

Cite arxiv.org/abs/2607.26037 in a Space README.md to link it from this page.