GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch</p>\n","updatedAt":"2026-07-16T03:07:58.210Z","author":{"_id":"6426616ea5ec4a5cbc535634","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6426616ea5ec4a5cbc535634/5IfSFYd9QOxz8K9QmBCst.png","fullname":"JeffWang","name":"Jeff-Wang","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":8,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7362425327301025},"editors":["Jeff-Wang"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/6426616ea5ec4a5cbc535634/5IfSFYd9QOxz8K9QmBCst.png"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2607.13960","authors":[{"_id":"6a58460969aa0f8878bddb23","name":"GigaWorld Team","hidden":false},{"_id":"6a58460969aa0f8878bddb24","name":"Angen Ye","hidden":false},{"_id":"6a58460969aa0f8878bddb25","name":"Angyuan Ma","hidden":false},{"_id":"6a58460969aa0f8878bddb26","name":"Boyuan Wang","hidden":false},{"_id":"6a58460969aa0f8878bddb27","name":"Chaojun Ni","hidden":false},{"_id":"6a58460969aa0f8878bddb28","name":"Fangzheng Ye","hidden":false},{"_id":"6a58460969aa0f8878bddb29","name":"Guan Huang","hidden":false},{"_id":"6a58460969aa0f8878bddb2a","name":"Guo Li","hidden":false},{"_id":"6a58460969aa0f8878bddb2b","name":"Guosheng Zhao","hidden":false},{"_id":"6a58460969aa0f8878bddb2c","name":"Haodong Yan","hidden":false},{"_id":"6a58460969aa0f8878bddb2d","name":"Hengtao Li","hidden":false},{"_id":"6a58460969aa0f8878bddb2e","name":"Jiwen Lu","hidden":false},{"_id":"6a58460969aa0f8878bddb2f","name":"Kai Wang","hidden":false},{"_id":"6a58460969aa0f8878bddb30","name":"Mingming Yu","hidden":false},{"_id":"6a58460969aa0f8878bddb31","name":"Qitang Hu","hidden":false},{"_id":"6a58460969aa0f8878bddb32","name":"Qiuping Deng","hidden":false},{"_id":"6a58460969aa0f8878bddb33","name":"Songling Liu","hidden":false},{"_id":"6a58460969aa0f8878bddb34","name":"Xiaoyu Tian","hidden":false},{"_id":"6a58460969aa0f8878bddb35","name":"Xiaofeng Wang","hidden":false},{"_id":"6a58460969aa0f8878bddb36","name":"Xinyu Zhou","hidden":false},{"_id":"6a58460969aa0f8878bddb37","name":"Xiuwei Xu","hidden":false},{"_id":"6a58460969aa0f8878bddb38","name":"Xinze Chen","hidden":false},{"_id":"6a58460969aa0f8878bddb39","name":"Yang Wang","hidden":false},{"_id":"6a58460969aa0f8878bddb3a","name":"Yejun Zeng","hidden":false},{"_id":"6a58460969aa0f8878bddb3b","name":"Yifan Chang","hidden":false},{"_id":"6a58460969aa0f8878bddb3c","name":"Yun Ye","hidden":false},{"_id":"6a58460969aa0f8878bddb3d","name":"Zhenyu Wu","hidden":false},{"_id":"6a58460969aa0f8878bddb3e","name":"Zhanqian Wu","hidden":false},{"_id":"6a58460969aa0f8878bddb3f","name":"Zheng Zhu","hidden":false}],"publishedAt":"2026-07-15T00:00:00.000Z","submittedOnDailyAt":"2026-07-16T00:00:00.000Z","title":"GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch","submittedOnDailyBy":{"_id":"6426616ea5ec4a5cbc535634","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6426616ea5ec4a5cbc535634/5IfSFYd9QOxz8K9QmBCst.png","isPro":false,"fullname":"JeffWang","user":"Jeff-Wang","type":"user","name":"Jeff-Wang"},"summary":"World Action Models (WAMs) improve robot policy learning by jointly modeling actions and future visual observations, using future scene evolution as dense supervision for physically grounded action generation. However, a common design in existing WAMs is to explicitly generate future videos at inference time, incurring substantial computational overhead and hindering real-time closed-loop deployment. GigaWorld-Policy addresses this issue with an action-centered formulation, where future visual dynamics are used during training while action-only decoding is used at inference time. Building upon this framework, we present GigaWorld-Policy-0.5, an enhanced action-centered WAM designed for more efficient robot control. During pretraining, GigaWorld-Policy-0.5 adopts a mixed Action-Conditioned World Modeling (AC-WM) and WAM training strategy. This strengthens the coupling between visual dynamics and robot actions and improves the transferability of action representations for downstream policy learning. For efficient inference, GigaWorld-Policy-0.5 introduces a Mixture-of-Transformers architecture that separates visual dynamics modeling and action generation into specialized experts, reducing active computation during action-only inference and achieving 85 ms inference latency on a local RTX 4090 setup. In addition, we employ an agent-based AutoResearch pipeline to systematically search training configurations, enabling more efficient identification of optimal experimental setups while reducing the time and manual intervention required for hyperparameter tuning. Experiments and ablations show that GigaWorld-Policy-0.5 preserves the training benefits of future visual dynamics while improving inference efficiency for robot control.","upvotes":21,"discussionId":"6a58460a69aa0f8878bddb40","projectPage":"https://open-gigaai.github.io/giga-world-policy/","organization":{"_id":"68d6587936e2de9610d9f5f0","name":"open-gigaai","fullname":"GigaAI","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/68d6394328e169473e90e4a6/zUK7FKr_8XqrN0aFUgsD-.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"6426616ea5ec4a5cbc535634","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6426616ea5ec4a5cbc535634/5IfSFYd9QOxz8K9QmBCst.png","isPro":false,"fullname":"JeffWang","user":"Jeff-Wang","type":"user"},{"_id":"6909ce9b391d11cef04e17ee","avatarUrl":"/avatars/d3d4274c7610e2e66b0319075b34c7f4.svg","isPro":false,"fullname":"Daniel Harris","user":"codecodecode123","type":"user"},{"_id":"6440cffb3e0374802e1b5fc6","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6440cffb3e0374802e1b5fc6/ZFLIhn72CTeZ87lO-zAH-.jpeg","isPro":false,"fullname":"Zhenyuan Zhang","user":"liar-zzy","type":"user"},{"_id":"6910c494cf03b074db355000","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/2-ydVDpQPjHbj58K1eZ_X.png","isPro":false,"fullname":"Yk202","user":"HengtaoLi","type":"user"},{"_id":"6760e68767cc964d06af5439","avatarUrl":"/avatars/e23a8889eedd59d1d33e32fc95063107.svg","isPro":false,"fullname":"Keweijie","user":"WadeKe","type":"user"},{"_id":"6466e66314e059dde8bbf35c","avatarUrl":"/avatars/f2a27bb4e04749ec51f3a9fc36d87fb0.svg","isPro":false,"fullname":"I0u0I","user":"I0u0I","type":"user"},{"_id":"64fed9eb56243ce8cb66beec","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/_KVMINyIbVQFzreQBogct.png","isPro":false,"fullname":"BY.W","user":"chuanshuogushi","type":"user"},{"_id":"654c7f32386fc5525c1ebc12","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/654c7f32386fc5525c1ebc12/RIUS_nkbt9n5iu46lLQkb.jpeg","isPro":false,"fullname":"zhao guosheng","user":"f1yfish","type":"user"},{"_id":"686fc6d16ea5d5fb0a4a5b2d","avatarUrl":"/avatars/d7a793b03951c2a7682167e17deaf8db.svg","isPro":false,"fullname":"chong","user":"Phil1220","type":"user"},{"_id":"66af1e307f4db96a1021c7f5","avatarUrl":"/avatars/6b4bf963d90239e2f20d2193f602149f.svg","isPro":false,"fullname":"haodong123","user":"Haodong082399","type":"user"},{"_id":"6a4c6ce8d0dfffe1452e28cd","avatarUrl":"/avatars/a3eba21621ae792fc6ba9611fbc46409.svg","isPro":false,"fullname":"xiaoyu","user":"ZUANADAS","type":"user"},{"_id":"654babcef8853732606bab78","avatarUrl":"/avatars/d3e21586583ca684fba08fce2fb38bf1.svg","isPro":false,"fullname":"guo","user":"phoenix88","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"68d6587936e2de9610d9f5f0","name":"open-gigaai","fullname":"GigaAI","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/68d6394328e169473e90e4a6/zUK7FKr_8XqrN0aFUgsD-.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2607/2607.13960.md","query":{}}">

Get this paper in your agent:

Don't have the latest CLI?

Cite arxiv.org/abs/2607.13960 in a dataset README.md to link it from this page.

Cite arxiv.org/abs/2607.13960 in a Space README.md to link it from this page.