Light Interaction is a training-free inference acceleration framework for interactive video world models that reduces computational costs via adaptive context management and hardware-aware sparse attention.</p>\n","updatedAt":"2026-06-01T02:25:49.322Z","author":{"_id":"6039478ab3ecf716b1a5fd4d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6039478ab3ecf716b1a5fd4d/_Thy4E7taiSYBLKxEKJbT.jpeg","fullname":"taesiri","name":"taesiri","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":309,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7991297841072083},"editors":["taesiri"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/6039478ab3ecf716b1a5fd4d/_Thy4E7taiSYBLKxEKJbT.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2605.31158","authors":[{"_id":"6a1ced9f808ddbc3c7d4345a","name":"Jiacheng Lu","hidden":false},{"_id":"6a1ced9f808ddbc3c7d4345b","name":"Haoyi Zhu","hidden":false},{"_id":"6a1ced9f808ddbc3c7d4345c","name":"Sipei Yi","hidden":false},{"_id":"6a1ced9f808ddbc3c7d4345d","name":"Enze Xie","hidden":false},{"_id":"6a1ced9f808ddbc3c7d4345e","name":"Yu Li","hidden":false},{"_id":"6a1ced9f808ddbc3c7d4345f","name":"Cheng Zhuo","hidden":false}],"publishedAt":"2026-05-29T00:00:00.000Z","submittedOnDailyAt":"2026-06-01T00:00:00.000Z","title":"Light Interaction: Training-Free Inference Acceleration for Interactive Video World Models","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":"Interactive video world models generate video chunk by chunk in response to user-controlled camera movements, enabling applications such as real-time game simulation, virtual scene navigation, and embodied AI training. However, scaling to long interactive trajectories is prohibitively expensive due to growing context memory, quadratic attention complexity, and repeated denoising steps. We present Light Interaction, a training-free inference acceleration framework for interactive video world models. Our key insight is that interaction naturally enables trajectory-dependent adaptive computation: retrieved spatial memory can be discarded during novel exploration, temporal context can be adjusted according to local latent dynamics, and early-step model outputs can be reused when the camera revisits familiar regions. Based on this insight, Light Interaction combines adaptive context management, denoising cache acceleration, and hardware-software co-designed 3D block sparse attention with fused Triton kernels. Evaluated on HY-WorldPlay and Matrix-Game-3.0, Light Interaction achieves up to 2.59x speedup without model retraining while maintaining competitive visual quality.","upvotes":1,"discussionId":"6a1ceda0808ddbc3c7d43460","projectPage":"https://2843721358l-del.github.io/Light-Interaction-Project/","ai_summary":"Light Interaction accelerates interactive video world models through adaptive computation strategies and optimized attention mechanisms without requiring model retraining.","ai_keywords":["video world models","interactive video","trajectory-dependent adaptive computation","spatial memory","temporal context","denoising cache acceleration","3D block sparse attention","Triton kernels"],"organization":{"_id":"60262b67268c201cdc8b7d43","name":"nvidia","fullname":"NVIDIA","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/65df9200dc3292a8983e5017/Vs5FPVCH-VZBipV3qKTuy.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"620783f24e28382272337ba4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/620783f24e28382272337ba4/zkUveQPNiDfYjgGhuFErj.jpeg","isPro":false,"fullname":"GuoLiangTang","user":"Tommy930","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"60262b67268c201cdc8b7d43","name":"nvidia","fullname":"NVIDIA","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/65df9200dc3292a8983e5017/Vs5FPVCH-VZBipV3qKTuy.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2605/2605.31158.md"}">

Get this paper in your agent:

Don't have the latest CLI?

Cite arxiv.org/abs/2605.31158 in a model README.md to link it from this page.

Cite arxiv.org/abs/2605.31158 in a dataset README.md to link it from this page.

Cite arxiv.org/abs/2605.31158 in a Space README.md to link it from this page.

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