Hugging Face Daily Papers · · 6 min read

NeuROK: Generative 4D Neural Object Kinematics

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

NeuROK provides a data-driven kinematic state parameterization for object-centric systems, enabling the efficient generation of simulative 4D object dynamics without explicit physical models or prior inductive bias.</p>\n","updatedAt":"2026-05-29T02:56:57.656Z","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":307,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.6570383310317993},"editors":["taesiri"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/6039478ab3ecf716b1a5fd4d/_Thy4E7taiSYBLKxEKJbT.jpeg"],"reactions":[],"isReport":false}},{"id":"6a1a41ad1061848fe7ebf26e","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":359,"isUserFollowing":false},"createdAt":"2026-05-30T01:47:25.000Z","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* [Velox: Learning Representations of 4D Geometry and Appearance](https://huggingface.co/papers/2605.04527) (2026)\n* [ClothTransformer: Unified Latent-Space Transformers for Scalable Cloth Simulation](https://huggingface.co/papers/2605.27852) (2026)\n* [MatPhys: Learning Material-Aware Physics Parameters for Deformable Object Simulation from Videos](https://huggingface.co/papers/2605.19386) (2026)\n* [HO-Flow: Generalizable Hand-Object Interaction Generation with Latent Flow Matching](https://huggingface.co/papers/2604.10836) (2026)\n* [ViPS: Video-informed Pose Spaces for Auto-Rigged Meshes](https://huggingface.co/papers/2604.17623) (2026)\n* [RigidFormer: Learning Rigid Dynamics using Transformers](https://huggingface.co/papers/2605.09196) (2026)\n* [CausalGS: Learning Physical Causality of 3D Dynamic Scenes with Gaussian Representations](https://huggingface.co/papers/2605.10586) (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/2605.04527\">Velox: Learning Representations of 4D Geometry and Appearance</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2605.27852\">ClothTransformer: Unified Latent-Space Transformers for Scalable Cloth Simulation</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2605.19386\">MatPhys: Learning Material-Aware Physics Parameters for Deformable Object Simulation from Videos</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2604.10836\">HO-Flow: Generalizable Hand-Object Interaction Generation with Latent Flow Matching</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2604.17623\">ViPS: Video-informed Pose Spaces for Auto-Rigged Meshes</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2605.09196\">RigidFormer: Learning Rigid Dynamics using Transformers</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2605.10586\">CausalGS: Learning Physical Causality of 3D Dynamic Scenes with Gaussian Representations</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":"2026-05-30T01:47:25.376Z","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":359,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.6987528204917908},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2605.30347","authors":[{"_id":"6a19006556b4bb14ec65cf48","name":"Chen Geng","hidden":false},{"_id":"6a19006556b4bb14ec65cf49","name":"Guangzhao He","hidden":false},{"_id":"6a19006556b4bb14ec65cf4a","name":"Yue Gao","hidden":false},{"_id":"6a19006556b4bb14ec65cf4b","name":"Yunzhi Zhang","hidden":false},{"_id":"6a19006556b4bb14ec65cf4c","name":"Shangzhe Wu","hidden":false},{"_id":"6a19006556b4bb14ec65cf4d","name":"Jiajun Wu","hidden":false}],"mediaUrls":["https://cdn-uploads.huggingface.co/production/uploads/6039478ab3ecf716b1a5fd4d/JL9c0Ty8JyzISvE8CDF7f.mp4"],"publishedAt":"2026-05-28T00:00:00.000Z","submittedOnDailyAt":"2026-05-29T00:00:00.000Z","title":"NeuROK: Generative 4D Neural Object Kinematics","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":"Data-driven approaches have revolutionized 3D vision, enabling transformers to effectively reconstruct and generate static 3D objects. However, generating simulative 4D dynamics -- realistic temporal deformations of static objects under various physical conditions -- remains challenging and often ad hoc, despite its importance in building comprehensive 3D world models. Most existing methods assume a predefined physical model and use system identification to estimate parameters, restricting these methods to specific categories and small-scale datasets. We propose that these restrictions can be overcome by learning a data-driven kinematic state parameterization for object-centric physical systems. Specifically, we learn both a latent space representing all possible states of the object and a decoder that maps any sampled latent to a plausibly deformed shape of the object. We refer to this parameterization as Neural Object Kinematics (NeuROK), and learn a transformer-based encoder-decoder model on a curated large-scale 4D dataset. This formulation and the learned model significantly simplify the generation of simulative dynamics since we only need to consider the dynamics within a low-dimensional latent space from the Lagrangian mechanics' perspective in classical physics. We demonstrate the effectiveness and generality of this neural simulation framework across diverse dynamic object types, showing clear advantages over prior works. Project page: https://chen-geng.com/neurok","upvotes":4,"discussionId":"6a19006656b4bb14ec65cf4e","projectPage":"https://chen-geng.com/neurok","ai_summary":"Neural Object Kinematics learns a data-driven parameterization for 4D dynamic object simulation by combining latent space representation with transformer-based encoding-decoding, enabling realistic temporal deformations across diverse object types.","ai_keywords":["transformer-based encoder-decoder model","latent space","decoder","neural simulation framework","4D dynamics","object-centric physical systems","Lagrangian mechanics","temporal deformations","curated large-scale 4D dataset"]},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"6305b64699870e13d3e1cb50","avatarUrl":"/avatars/e38fc1ad7b147036b98cd5ac6cd37516.svg","isPro":false,"fullname":"Chen Geng","user":"MrMorning","type":"user"},{"_id":"6350ed6ba8822aadf570c8ea","avatarUrl":"/avatars/bffe710752df05cab25896a0bd40c5f6.svg","isPro":false,"fullname":"Seunggyu Chang","user":"itswyri","type":"user"},{"_id":"659765e22235d4056ba80c0a","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/659765e22235d4056ba80c0a/dATESmijLO3CpD1sCMezg.jpeg","isPro":true,"fullname":"Gao Sensen","user":"Sensen02","type":"user"},{"_id":"648961d150c003881f1a10c3","avatarUrl":"/avatars/1eb3784c39f7ced2e952d11a410933ae.svg","isPro":false,"fullname":"Harshita Sharma","user":"hdsharma","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2605/2605.30347.md"}">
Papers
arxiv:2605.30347

NeuROK: Generative 4D Neural Object Kinematics

Published on May 28
· Submitted by
taesiri
on May 29
Authors:
,
,
,
,
,

Abstract

Neural Object Kinematics learns a data-driven parameterization for 4D dynamic object simulation by combining latent space representation with transformer-based encoding-decoding, enabling realistic temporal deformations across diverse object types.

AI-generated summary

Data-driven approaches have revolutionized 3D vision, enabling transformers to effectively reconstruct and generate static 3D objects. However, generating simulative 4D dynamics -- realistic temporal deformations of static objects under various physical conditions -- remains challenging and often ad hoc, despite its importance in building comprehensive 3D world models. Most existing methods assume a predefined physical model and use system identification to estimate parameters, restricting these methods to specific categories and small-scale datasets. We propose that these restrictions can be overcome by learning a data-driven kinematic state parameterization for object-centric physical systems. Specifically, we learn both a latent space representing all possible states of the object and a decoder that maps any sampled latent to a plausibly deformed shape of the object. We refer to this parameterization as Neural Object Kinematics (NeuROK), and learn a transformer-based encoder-decoder model on a curated large-scale 4D dataset. This formulation and the learned model significantly simplify the generation of simulative dynamics since we only need to consider the dynamics within a low-dimensional latent space from the Lagrangian mechanics' perspective in classical physics. We demonstrate the effectiveness and generality of this neural simulation framework across diverse dynamic object types, showing clear advantages over prior works. Project page: https://chen-geng.com/neurok

Community

Paper submitter 1 day ago

NeuROK provides a data-driven kinematic state parameterization for object-centric systems, enabling the efficient generation of simulative 4D object dynamics without explicit physical models or prior inductive bias.

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend

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 2605.30347
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2605.30347 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2605.30347 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2605.30347 in a Space README.md to link it from this page.

Collections including this paper 0

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