Deprecated: The each() function is deprecated. This message will be suppressed on further calls in /home/zhenxiangba/zhenxiangba.com/public_html/phproxy-improved-master/index.php on line 456 Paper page - Code2Worlds: Empowering Coding LLMs for 4D World Generation
https://aigeeksgroup.github.io/Code2Worlds\n","updatedAt":"2026-02-16T03:08:51.314Z","author":{"_id":"64ec877bb93654d4ca5c92e9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64ec877bb93654d4ca5c92e9/GvHk_KSdE9Rhnk_o-NaZX.jpeg","fullname":"Zeyu Zhang","name":"SteveZeyuZhang","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":4,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.3385085463523865},"editors":["SteveZeyuZhang"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/64ec877bb93654d4ca5c92e9/GvHk_KSdE9Rhnk_o-NaZX.jpeg"],"reactions":[],"isReport":false}},{"id":"6993c6d93883cdc4e0116cac","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":318,"isUserFollowing":false},"createdAt":"2026-02-17T01:39:37.000Z","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* [SceneReVis: A Self-Reflective Vision-Grounded Framework for 3D Indoor Scene Synthesis via Multi-turn RL](https://huggingface.co/papers/2602.09432) (2026)\n* [Code2World: A GUI World Model via Renderable Code Generation](https://huggingface.co/papers/2602.09856) (2026)\n* [V-CAGE: Context-Aware Generation and Verification for Scalable Long-Horizon Embodied Tasks](https://huggingface.co/papers/2601.15164) (2026)\n* [CoAgent: Collaborative Planning and Consistency Agent for Coherent Video Generation](https://huggingface.co/papers/2512.22536) (2025)\n* [Mind-Brush: Integrating Agentic Cognitive Search and Reasoning into Image Generation](https://huggingface.co/papers/2602.01756) (2026)\n* [Affordance-Graphed Task Worlds: Self-Evolving Task Generation for Scalable Embodied Learning](https://huggingface.co/papers/2602.12065) (2026)\n* [AGILE: Hand-Object Interaction Reconstruction from Video via Agentic Generation](https://huggingface.co/papers/2602.04672) (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":"
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
\n
The following papers were recommended by the Semantic Scholar API
Please give a thumbs up to this comment if you found it helpful!
\n
If you want recommendations for any Paper on Hugging Face checkout this Space
\n
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: \n\n@librarian-bot\n\t recommend
\n","updatedAt":"2026-02-17T01:39:37.192Z","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":318,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7274911403656006},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2602.11757","authors":[{"_id":"69928a0e50fb2c0be478390b","name":"Yi Zhang","hidden":false},{"_id":"69928a0e50fb2c0be478390c","name":"Yunshuang Wang","hidden":false},{"_id":"69928a0e50fb2c0be478390d","user":{"_id":"64ec877bb93654d4ca5c92e9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64ec877bb93654d4ca5c92e9/GvHk_KSdE9Rhnk_o-NaZX.jpeg","isPro":false,"fullname":"Zeyu Zhang","user":"SteveZeyuZhang","type":"user"},"name":"Zeyu Zhang","status":"claimed_verified","statusLastChangedAt":"2026-02-18T09:06:54.418Z","hidden":true},{"_id":"69928a0e50fb2c0be478390e","name":"Hao Tang","hidden":false}],"publishedAt":"2026-02-12T09:34:28.000Z","submittedOnDailyAt":"2026-02-16T00:38:51.304Z","title":"Code2Worlds: Empowering Coding LLMs for 4D World Generation","submittedOnDailyBy":{"_id":"64ec877bb93654d4ca5c92e9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64ec877bb93654d4ca5c92e9/GvHk_KSdE9Rhnk_o-NaZX.jpeg","isPro":false,"fullname":"Zeyu Zhang","user":"SteveZeyuZhang","type":"user"},"summary":"Achieving spatial intelligence requires moving beyond visual plausibility to build world simulators grounded in physical laws. While coding LLMs have advanced static 3D scene generation, extending this paradigm to 4D dynamics remains a critical frontier. This task presents two fundamental challenges: multi-scale context entanglement, where monolithic generation fails to balance local object structures with global environmental layouts; and a semantic-physical execution gap, where open-loop code generation leads to physical hallucinations lacking dynamic fidelity. We introduce Code2Worlds, a framework that formulates 4D generation as language-to-simulation code generation. First, we propose a dual-stream architecture that disentangles retrieval-augmented object generation from hierarchical environmental orchestration. Second, to ensure dynamic fidelity, we establish a physics-aware closed-loop mechanism in which a PostProcess Agent scripts dynamics, coupled with a VLM-Motion Critic that performs self-reflection to iteratively refine simulation code. Evaluations on the Code4D benchmark show Code2Worlds outperforms baselines with a 41% SGS gain and 49% higher Richness, while uniquely generating physics-aware dynamics absent in prior static methods. Code: https://github.com/AIGeeksGroup/Code2Worlds. Website: https://aigeeksgroup.github.io/Code2Worlds.","upvotes":3,"discussionId":"69928a0e50fb2c0be478390f","projectPage":"https://aigeeksgroup.github.io/Code2Worlds","githubRepo":"https://github.com/AIGeeksGroup/Code2Worlds","githubRepoAddedBy":"user","ai_summary":"Code2Worlds enables 4D dynamic scene generation by formulating it as language-to-simulation code generation with a dual-stream architecture and physics-aware closed-loop refinement.","ai_keywords":["language-to-simulation code generation","dual-stream architecture","retrieval-augmented object generation","hierarchical environmental orchestration","physics-aware closed-loop mechanism","PostProcess Agent","VLM-Motion Critic","self-reflection","simulation code"],"githubStars":30,"organization":{"_id":"61dcd8e344f59573371b5cb6","name":"PekingUniversity","fullname":"Peking University","avatar":"https://cdn-uploads.huggingface.co/production/uploads/noauth/vavgrBsnkSejriUF4lXDE.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"},{"_id":"656ee8008bb9f4f8d95bd8f7","avatarUrl":"/avatars/4069d70f1279d928da521211c495d638.svg","isPro":false,"fullname":"Hyeonho Jeong","user":"hyeonho-jeong-video","type":"user"},{"_id":"684d57f26e04c265777ead3f","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/cuOj-bQqukSZreXgUJlfm.png","isPro":false,"fullname":"Joakim Lee","user":"Reinforcement4All","type":"user"}],"acceptLanguages":["*"],"dailyPaperRank":0,"organization":{"_id":"61dcd8e344f59573371b5cb6","name":"PekingUniversity","fullname":"Peking University","avatar":"https://cdn-uploads.huggingface.co/production/uploads/noauth/vavgrBsnkSejriUF4lXDE.png"}}">
Code2Worlds enables 4D dynamic scene generation by formulating it as language-to-simulation code generation with a dual-stream architecture and physics-aware closed-loop refinement.
AI-generated summary
Achieving spatial intelligence requires moving beyond visual plausibility to build world simulators grounded in physical laws. While coding LLMs have advanced static 3D scene generation, extending this paradigm to 4D dynamics remains a critical frontier. This task presents two fundamental challenges: multi-scale context entanglement, where monolithic generation fails to balance local object structures with global environmental layouts; and a semantic-physical execution gap, where open-loop code generation leads to physical hallucinations lacking dynamic fidelity. We introduce Code2Worlds, a framework that formulates 4D generation as language-to-simulation code generation. First, we propose a dual-stream architecture that disentangles retrieval-augmented object generation from hierarchical environmental orchestration. Second, to ensure dynamic fidelity, we establish a physics-aware closed-loop mechanism in which a PostProcess Agent scripts dynamics, coupled with a VLM-Motion Critic that performs self-reflection to iteratively refine simulation code. Evaluations on the Code4D benchmark show Code2Worlds outperforms baselines with a 41% SGS gain and 49% higher Richness, while uniquely generating physics-aware dynamics absent in prior static methods. Code: https://github.com/AIGeeksGroup/Code2Worlds. Website: https://aigeeksgroup.github.io/Code2Worlds.