{"id":33346038,"url":"https://github.com/knightnemo/Awesome-World-Models","last_synced_at":"2025-11-27T02:00:37.776Z","repository":{"id":321807444,"uuid":"1087207313","full_name":"knightnemo/Awesome-World-Models","owner":"knightnemo","description":"A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts Interested in World Modeling.","archived":false,"fork":false,"pushed_at":"2025-11-23T15:55:10.000Z","size":2347,"stargazers_count":849,"open_issues_count":0,"forks_count":25,"subscribers_count":13,"default_branch":"main","last_synced_at":"2025-11-23T17:29:56.036Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-3-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/knightnemo.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-10-31T14:38:53.000Z","updated_at":"2025-11-23T15:55:13.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/knightnemo/Awesome-World-Models","commit_stats":null,"previous_names":["knightnemo/awesome-world-models"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/knightnemo/Awesome-World-Models","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/knightnemo%2FAwesome-World-Models","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/knightnemo%2FAwesome-World-Models/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/knightnemo%2FAwesome-World-Models/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/knightnemo%2FAwesome-World-Models/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/knightnemo","download_url":"https://codeload.github.com/knightnemo/Awesome-World-Models/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/knightnemo%2FAwesome-World-Models/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286079811,"owners_count":27282121,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-11-27T02:00:05.795Z","response_time":58,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-11-22T06:00:35.714Z","updated_at":"2025-11-27T02:00:37.766Z","avatar_url":"https://github.com/knightnemo.png","language":null,"funding_links":[],"categories":["Other Lists","Related Works","🙏 Acknowledgements","Others","🔗 Related Awesome Lists","Acknowledgements"],"sub_categories":["TeX Lists","Research Labs \u0026 Initiatives","2022","🧪 Frontier Labs and Teams","🚫 Excluded (RL)"],"readme":"\u003cdiv align=\"center\"\u003e\n\n# 🌍 Awesome World Models\n\n\n[![Awesome](https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg)](https://github.com/sindresorhus/awesome) [![GitHub stars](https://img.shields.io/github/stars/knightnemo/Awesome-World-Models?style=social)](https://github.com/knightnemo/Awesome-World-Models/stargazers) [![License](https://img.shields.io/badge/License-CC0_1.0-blue.svg)](LICENSE.txt) [![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](CONTRIBUTING.md)\n\n**📜 A Curated List of Amazing Works in World Modeling, spanning applications in Embodied AI, Autonomous Driving, Natural Language Processing and Agents.** \u003c/br\u003e\n*Based on [Awesome-World-Model-for-Autonomous-Driving](https://github.com/LMD0311/Awesome-World-Model) and [Awesome-World-Model-for-Robotics](https://github.com/leofan90/Awesome-World-Models)*.\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"assets/main.png\" alt=\"Awesome World Models\" width=\"100%\" style=\"border-radius: 15px; box-shadow: 0 4px 24px rgba(0,0,0,.1); margin: 5px 0;\"\u003e\n\u003c/p\u003e\n\n*Photo Credit: [Gemini-Nano-Banana🍌](https://aistudio.google.com/models/gemini-2-5-flash-image)*.\n\u003c/div\u003e\n\n---\n\n## 🚩 News \u0026 Updates\n_Major updates and announcements are shown below. Scroll for full timeline._\n\n🗺️ **[2025-10] Enhanced Visual Navigation** — Introduced badge system for papers! All entries now display [![arXiv](https://img.shields.io/badge/arXiv-Paper-b31b1b.svg)](#) [![Website](https://img.shields.io/badge/Website-Link-blue)](#) [![Code](https://img.shields.io/badge/Code-GitHub-green)](#) for quick access to resources.\n\n🔥 **[2025-10] Repository Launch** — Awesome World Models is now live! We're building a comprehensive collection spanning Embodied AI, Autonomous Driving, NLP, and more. See [CONTRIBUTING.md](CONTRIBUTING.md) for how to contribute.\n\n💡 **[Ongoing] Community Contributions Welcome** — Help us maintain the most up-to-date world models resource! Submit papers via PR or contact us at [email](mailto:siqiaohuang981@gmail.com).\n\n⭐ **[Ongoing] Support This Project** — If you find this useful, please [cite](#citation) our work and give us a star. Share with your research community!\n\n\n---\n## Overview\n\n  - 🎯 [Aim of the project](#aim-of-the-project)\n  - 📚 [Definition of World Models](#definition-of-world-models)\n  - 📖 [Surveys of World Models](#surveys-of-world-models)\n  - 🎮 [World Models for Game Simulation](#world-models-for-game-simulation)\n  - 🚗 [World Models for Autonomous Driving](#world-models-for-autonomous-driving)\n  - 🤖 [World Models for Embodied AI](#world-models-for-embodied-ai)\n  - 🔬 [World Models for Science](#world-models-for-science)\n  - 💭 [Positions on World Models](#positions-on-world-models)\n  - 📐 [Theory \u0026 World Models Explainability](#theory--world-models-explainability)\n  - 🛠️ [General Approaches to World Models](#general-approaches-to-world-models)\n  - 📊 [Evaluating World Models](#evaluating-world-models)\n  - 🙏 [Acknowledgements](#acknowledgements)\n  - 📝 [Citation](#citation)\n\n---\n\n## Aim of the Project\n\nWorld Models have become a hot topic in both research and industry, attracting unprecedented attention from the AI community and beyond. However, due to the **interdisciplinary nature** of the field (_and because the term \"world model\" simply sounds amazing_), the concept has been used with varying definitions across different domains.\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"assets/image.png\" alt=\"Awesome World Models\" width=\"50%\" style=\"border-radius: 15px; box-shadow: 0 4px 24px rgba(0,0,0,.1); margin: 20px 0;\"\u003e\n\u003c/p\u003e\n\nThis repository aims to:\n\n- 🔍 **Organize** the rapidly growing body of world model research across multiple application domains\n- 🗺️ **Provide** a minimalist map of how world models are utilized in different fields (Embodied AI, Autonomous Driving, NLP, etc.)\n- 🤝 **Bridge** the gap between different communities working on world models with varying perspectives\n- 📚 **Serve** as a one-stop resource for researchers, practitioners, and enthusiasts interested in world modeling\n- 🚀 **Track** the latest developments and breakthroughs in this exciting field\n\nWhether you're a researcher looking for related work, a practitioner seeking implementation references, or simply curious about world models, we hope this curated list helps you navigate the landscape! \n\n---\n\n## Definition of World Models\nWhile world models' outreach has been expanded again and again, it is widely adopted that the original sources of world models come from these two papers:\n* [⭐️] **World Models**, World Models. [![arXiv](https://img.shields.io/badge/arXiv-1803.10122-b31b1b.svg)](https://arxiv.org/abs/1803.10122) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://worldmodels.github.io/) \n* [⭐️] **Yann Lecun's Speech**, \"A Path Towards Autonomous Machine Intelligence\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/pdf?id=BZ5a1r-kVsf)\n\nSome other great blogposts on world models include:\n- [⭐️] **Towards Video World Models**, \"Towards Video World Models\". [![Blog](https://img.shields.io/badge/Blog-Link-orange)](https://www.xunhuang.me/blogs/world_model.html)\n- **Status of World Models in 2025**, \"Beyond the Hype: How I See World Models Evolving in 2025\". [![Blog](https://img.shields.io/badge/Blog-Link-orange)](https://knightnemo.github.io/blog/posts/wm_2025/)\n- [⭐️] **Jim Fan's tweet**. [![Blog](https://img.shields.io/badge/Blog-Link-orange)](https://x.com/DrJimFan/status/1709947595525951787)\n\n---\n## Surveys of World Models\n\n### 1. World Models and Video Generation:\n- [⭐️] **Is Sora a World Simulator**, \"Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond\". [![arXiv](https://img.shields.io/badge/arXiv-2405.03520-b31b1b.svg)](https://arxiv.org/abs/2405.03520) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://github.com/GigaAI-research/General-World-Models-Survey)\n- **Physics Cognition in Video Generation**, \"Exploring the Evolution of Physics Cognition in Video Generation: A Survey\". [![arXiv](https://img.shields.io/badge/arXiv-2503.21765-b31b1b.svg)](https://arxiv.org/abs/2503.21765) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://github.com/minnie-lin/Awesome-Physics-Cognition-based-Video-Generation)\n\n### 2. World Models and 3D Generation:\n- [⭐️] **3D and 4D World Modeling: A Survey**, \"3D and 4D World Modeling: A Survey\". [![arXiv](https://img.shields.io/badge/arXiv-2509.07996-b31b1b.svg)](https://arxiv.org/abs/2509.07996)\n- [⭐️] **Understanding World or Predicting Future?**, \"Understanding World or Predicting Future? A Comprehensive Survey of World Models\". [![arXiv](https://img.shields.io/badge/arXiv-2411.14499-b31b1b.svg)](https://arxiv.org/abs/2411.14499)\n- **From 2D to 3D Cognition**, \"From 2D to 3D Cognition: A Brief Survey of General World Models\". [![arXiv](https://img.shields.io/badge/arXiv-2506.20134-b31b1b.svg)](https://arxiv.org/abs/2506.20134)\n\n### 3. World Models and Embodied Artificial Intelligence:\n- [⭐️] **World Models for Embodied AI**, \"A Comprehensive Survey on World Models for Embodied AI\". [![arXiv](https://img.shields.io/badge/arXiv-2510.16732-b31b1b.svg)](https://arxiv.org/abs/2510.16732) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://github.com/Li-Zn-H/AwesomeWorldModels)\n- **World Models and Physical Simulation**, \"A Survey: Learning Embodied Intelligence from Physical Simulators and World Models\". [![arXiv](https://img.shields.io/badge/arXiv-2507.00917-b31b1b.svg)](https://arxiv.org/abs/2507.00917) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://github.com/NJU3DV-LoongGroup/Embodied-World-Models-Survey)\n- **Embodied AI Agents: Modeling the World**, \"Embodied AI Agents: Modeling the World\". [![arXiv](https://img.shields.io/badge/arXiv-2506.22355-b31b1b.svg)](https://arxiv.org/abs/2506.22355)\n- **Aligning Cyber Space with Physical World**, \"Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI\". [![arXiv](https://img.shields.io/badge/arXiv-2407.06886-b31b1b.svg)](https://arxiv.org/abs/2407.06886) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://github.com/HCPLab-SYSU/Embodied_AI_Paper_List)\n\n### 4. World Models for Autonomous Driving:\n- [⭐️] **A Survey of World Models for Autonomous Driving**, \"A Survey of World Models for Autonomous Driving\". [![arXiv](https://img.shields.io/badge/arXiv-2501.11260-b31b1b.svg)](https://arxiv.org/abs/2501.11260)\n- **World Models for Autonomous Driving: An Initial Survey**, \"World Models for Autonomous Driving: An Initial Survey\". [![arXiv](https://img.shields.io/badge/arXiv-2403.02622-b31b1b.svg)](https://arxiv.org/abs/2403.02622)\n- **Interplay Between Video Generation and World Models in Autonomous Driving**, \"Exploring the Interplay Between Video Generation and World Models in Autonomous Driving: A Survey\". [![arXiv](https://img.shields.io/badge/arXiv-2411.02914-b31b1b.svg)](https://arxiv.org/abs/2411.02914)\n\n### 5. Other Good Surveys:\n- **From Masks to Worlds**, \"From Masks to Worlds: A Hitchhiker's Guide to World Models\". [![arXiv](https://img.shields.io/badge/arXiv-2510.20668-b31b1b.svg)](https://arxiv.org/abs/2510.20668) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://github.com/M-E-AGI-Lab/Awesome-World-Models)\n- **The Safety Challenge of World Models**, \"The Safety Challenge of World Models for Embodied AI Agents: A Review\". [![arXiv](https://img.shields.io/badge/arXiv-2510.05865-b31b1b.svg)](https://arxiv.org/abs/2510.05865)\n- **World Models in AI: Like a Child**, \"World Models in Artificial Intelligence: Sensing, Learning, and Reasoning Like a Child\". [![arXiv](https://img.shields.io/badge/arXiv-2503.15168-b31b1b.svg)](https://arxiv.org/abs/2503.15168)\n- **World Model Safety**, \"World Models: The Safety Perspective\". [![arXiv](https://img.shields.io/badge/arXiv-2411.07690-b31b1b.svg)](https://arxiv.org/abs/2411.07690)\n- **Model-based reinforcement learning**: \"A survey on model-based reinforcement learning\".  [![Website](https://img.shields.io/badge/Website-Link-blue)](https://link.springer.com/article/10.1007/s11432-022-3696-5)\n\n---\n\n## World Models for Game Simulation\nPixel Space:\n- [⭐️] **GameNGen**, \"Diffusion Models Are Real-Time Game Engines\". [![arXiv](https://img.shields.io/badge/arXiv-2408.14837-b31b1b.svg)](https://arxiv.org/abs/2408.14837) \n- [⭐️] **DIAMOND**, \"Diffusion for World Modeling: Visual Details Matter in Atari\".  [![arXiv](https://img.shields.io/badge/arXiv-2405.12399-b31b1b.svg)](https://arxiv.org/abs/2405.12399) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/eloialonso/diamond)\n- **MineWorld**, \"MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraft\". [![arXiv](https://img.shields.io/badge/arXiv-2504.07257-b31b1b.svg)](https://arxiv.org/abs/2504.07257) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://aka.ms/mineworld)\n- **Oasis**, \"Oasis: A Universe in a Transformer\". [![Website](https://img.shields.io/badge/Website-Link-blue)](https://oasis-model.github.io/)\n- **AnimeGamer**, \"AnimeGamer: Infinite Anime Life Simulation with Next Game State Prediction\". [![arXiv](https://img.shields.io/badge/arXiv-2504.01014-b31b1b.svg)](http://arxiv.org/abs/2504.01014)[![Website](https://img.shields.io/badge/Website-Link-blue)](https://howe125.github.io/AnimeGamer.github.io/)\n- [⭐️] **Matrix-Game**, \"Matrix-Game: Interactive World Foundation Model.\" [![arXiv](https://img.shields.io/badge/arXiv-2506.18701-b31b1b.svg)](https://arxiv.org/abs/2506.18701) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/SkyworkAI/Matrix-Game)\n- [⭐️] **Matrix-Game 2.0**, Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model. [![arXiv](https://img.shields.io/badge/arXiv-2508.13009-b31b1b.svg)](https://arxiv.org/abs/2508.13009) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://matrix-game-v2.github.io/)\n- **RealPlay**, \"From Virtual Games to Real-World Play\". [![arXiv](https://img.shields.io/badge/arXiv-2506.18901-b31b1b.svg)](https://arxiv.org/abs/2506.18901) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://wenqsun.github.io/RealPlay/) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/wenqsun/Real-Play)\n- **GameFactory**, \"GameFactory: Creating New Games with Generative Interactive Videos\". [![arXiv](https://img.shields.io/badge/arXiv-2501.08325-b31b1b.svg)](http://arxiv.org/abs/2501.08325) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://yujiwen.github.io/gamefactory/) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/KwaiVGI/GameFactory)\n- **WORLDMEM**, \"Worldmem: Long-term Consistent World Simulation with Memory\". [![arXiv](https://img.shields.io/badge/arXiv-2504.12369-b31b1b.svg)](http://arxiv.org/abs/2504.12369) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://xizaoqu.github.io/worldmem/) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/xizaoqu/WorldMem)\n\n3D Mesh Space:\n- [⭐️] **HunyuanWorld 1.0**, HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels. [![arXiv](https://img.shields.io/badge/arXiv-2507.21809-b31b1b.svg)](https://arxiv.org/abs/2507.21809) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://3d-models.hunyuan.tencent.com/world/) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/Tencent-Hunyuan/HunyuanWorld-1.0)\n- [⭐️] **Matrix-3D**, Matrix-3D: Omnidirectional Explorable 3D World Generation. [![arXiv](https://img.shields.io/badge/arXiv-2508.08086-b31b1b.svg)](https://arxiv.org/abs/2508.08086) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://matrix-3d.github.io)\n\n\n---\n## World Models for Autonomous Driving\n_Refer to https://github.com/LMD0311/Awesome-World-Model for full list._\n\n\u003e [!NOTE]\n\u003e 📢 [Call for Maintenance] The repo creator is no expert of autonomous driving, so this is a more-than-concise list of works without classification. We anticipate community effort on turning this section cleaner and more well-sorted.\n\n- [⭐️] **Cosmos-Drive-Dreams**, \"Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models\". [![arXiv](https://img.shields.io/badge/arXiv-2506.09042-b31b1b.svg)](https://arxiv.org/abs/2506.09042) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://research.nvidia.com/labs/toronto-ai/cosmos_drive_dreams)\n- [⭐️] **GAIA-2**, \"GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving\". [![arXiv](https://img.shields.io/badge/arXiv-2503.20523-b31b1b.svg)](https://arxiv.org/abs/2503.20523) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://wayve.ai/thinking/gaia-2)\n- **Copilot4D**, \"Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion\". [![arXiv](https://img.shields.io/badge/arXiv-2311.01017-b31b1b.svg)](https://arxiv.org/abs/2311.01017)\n- **OmniNWM**: \"OmniNWM: Omniscient Driving Navigation World Models\". [![arXiv](https://img.shields.io/badge/arXiv-2510.18313-b31b1b.svg)](https://arxiv.org/abs/2510.18313) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://arlo0o.github.io/OmniNWM/) \n- **GAIA-1**, \"Introducing GAIA-1: A Cutting-Edge Generative AI Model for Autonomy\". [![arXiv](https://img.shields.io/badge/arXiv-2309.17080-b31b1b.svg)](https://arxiv.org/abs/2309.17080) [![Blog](https://img.shields.io/badge/Blog-Link-orange)](https://wayve.ai/thinking/introducing-gaia1/) \n* **PWM**, \"From Forecasting to Planning: Policy World Model for Collaborative State-Action Prediction\". [![arXiv](https://img.shields.io/badge/arXiv-2510.19654-b31b1b.svg)](https://arxiv.org/abs/2510.19654) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/6550Zhao/Policy-World-Model) \n* **Dream4Drive**, \"Rethinking Driving World Model as Synthetic Data Generator for Perception Tasks\". [![arXiv](https://img.shields.io/badge/arXiv-2510.19195-b31b1b.svg)](https://arxiv.org/abs/2510.19195) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://wm-research.github.io/Dream4Drive/) \n* **SparseWorld**, \"SparseWorld: A Flexible, Adaptive, and Efficient 4D Occupancy World Model Powered by Sparse and Dynamic Queries\". [![arXiv](https://img.shields.io/badge/arXiv-2510.17482-b31b1b.svg)](https://arxiv.org/abs/2510.17482) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/MSunDYY/SparseWorld) \n* **DriveVLA-W0**: \"DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving\". [![arXiv](https://img.shields.io/badge/arXiv-2510.12796-b31b1b.svg)](https://arxiv.org/abs/2510.12796) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/BraveGroup/DriveVLA-W0) \n* \"Enhancing Physical Consistency in Lightweight World Models\". [![arXiv](https://img.shields.io/badge/arXiv-2509.12437-b31b1b.svg)](https://arxiv.org/abs/2509.12437)\n* **IRL-VLA**: \"IRL-VLA: Training an Vision-Language-Action Policy via Reward World Model\". [![arXiv](https://img.shields.io/badge/arXiv-2508.06571-b31b1b.svg)](https://arxiv.org/abs/2508.06571) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://lidarcrafter.github.io) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/lidarcrafter/toolkit)\n* **LiDARCrafter**: \"LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequences\". [![arXiv](https://img.shields.io/badge/arXiv-2508.03692-b31b1b.svg)](https://arxiv.org/abs/2508.03692) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://lidarcrafter.github.io) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/lidarcrafter/toolkit)\n* **FASTopoWM**: \"FASTopoWM: Fast-Slow Lane Segment Topology Reasoning with Latent World Models\". [![arXiv](https://img.shields.io/badge/arXiv-2507.23325-b31b1b.svg)](https://arxiv.org/abs/2507.23325) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/YimingYang23/FASTopoWM)\n* **Orbis**: \"Orbis: Overcoming Challenges of Long-Horizon Prediction in Driving World Models\". [![arXiv](https://img.shields.io/badge/arXiv-2507.13162-b31b1b.svg)](https://arxiv.org/abs/2507.13162) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://lmb-freiburg.github.io/orbis.github.io/)\n* \"World Model-Based End-to-End Scene Generation for Accident Anticipation in Autonomous Driving\". [![arXiv](https://img.shields.io/badge/arXiv-2507.12762-b31b1b.svg)](https://arxiv.org/abs/2507.12762)\n* **NRSeg**: \"NRSeg: Noise-Resilient Learning for BEV Semantic Segmentation via Driving World Models\" [![arXiv](https://img.shields.io/badge/arXiv-2507.04002-b31b1b.svg)](https://arxiv.org/abs/2507.04002) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/lynn-yu/NRSeg)\n* **World4Drive**: \"World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Model\". [![arXiv](https://img.shields.io/badge/arXiv-2507.00603-b31b1b.svg)](https://arxiv.org/abs/2507.00603) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/ucaszyp/World4Drive)\n* **Epona**: \"Epona: Autoregressive Diffusion World Model for Autonomous Driving\". [![arXiv](https://img.shields.io/badge/arXiv-2506.24113-b31b1b.svg)](https://arxiv.org/abs/2506.24113) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://kevin-thu.github.io/Epona/)\n* \"Towards foundational LiDAR world models with efficient latent flow matching\". [![arXiv](https://img.shields.io/badge/arXiv-2506.23434-b31b1b.svg)](https://arxiv.org/abs/2506.23434)\n* **SceneDiffuser++**: \"SceneDiffuser++: City-Scale Traffic Simulation via a Generative World Model\". [![arXiv](https://img.shields.io/badge/arXiv-2506.21976-b31b1b.svg)](https://arxiv.org/abs/2506.21976)\n* **COME**: \"COME: Adding Scene-Centric Forecasting Control to Occupancy World Model\" [![arXiv](https://img.shields.io/badge/arXiv-2506.13260-b31b1b.svg)](https://arxiv.org/abs/2506.13260) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/synsin0/COME)\n* **STAGE**: \"STAGE: A Stream-Centric Generative World Model for Long-Horizon Driving-Scene Simulation\". [![arXiv](https://img.shields.io/badge/arXiv-2506.13138-b31b1b.svg)](https://arxiv.org/abs/2506.13138) \n* **ReSim**: \"ReSim: Reliable World Simulation for Autonomous Driving\". [![arXiv](https://img.shields.io/badge/arXiv-2506.09981-b31b1b.svg)](https://arxiv.org/abs/2506.09981) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/OpenDriveLab/ReSim) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://opendrivelab.com/ReSim)\n* \"Ego-centric Learning of Communicative World Models for Autonomous Driving\". [![arXiv](https://img.shields.io/badge/arXiv-2506.08149-b31b1b.svg)](https://arxiv.org/abs/2506.08149) \n* **Dreamland**: \"Dreamland: Controllable World Creation with Simulator and Generative Models\". [![arXiv](https://img.shields.io/badge/arXiv-2506.08006-b31b1b.svg)](https://arxiv.org/abs/2506.08006) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://metadriverse.github.io/dreamland/) \n* **LongDWM**: \"LongDWM: Cross-Granularity Distillation for Building a Long-Term Driving World Model\". [![arXiv](https://img.shields.io/badge/arXiv-2506.01546-b31b1b.svg)](https://arxiv.org/abs/2506.01546) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://wang-xiaodong1899.github.io/longdwm/) \n* **GeoDrive**: \"GeoDrive: 3D Geometry-Informed Driving World Model with Precise Action Control\". [![arXiv](https://img.shields.io/badge/arXiv-2505.22421-b31b1b.svg)](https://arxiv.org/abs/2505.22421) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/antonioo-c/GeoDrive) \n* **FutureSightDrive**: \"FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving\". [![arXiv](https://img.shields.io/badge/arXiv-2505.17685-b31b1b.svg)](https://arxiv.org/abs/2505.17685) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/MIV-XJTU/FSDrive) \n* **Raw2Drive**: \"Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)\". [![arXiv](https://img.shields.io/badge/arXiv-2505.16394-b31b1b.svg)](https://arxiv.org/abs/2505.16394)\n* **VL-SAFE**: \"VL-SAFE: Vision-Language Guided Safety-Aware Reinforcement Learning with World Models for Autonomous Driving\". [![arXiv](https://img.shields.io/badge/arXiv-2505.16377-b31b1b.svg)](https://arxiv.org/abs/2505.16377) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://ys-qu.github.io/vlsafe-website/) \n* **PosePilot**: \"PosePilot: Steering Camera Pose for Generative World Models with Self-supervised Depth\". [![arXiv](https://img.shields.io/badge/arXiv-2505.01729-b31b1b.svg)](https://arxiv.org/abs/2505.01729)\n* \"World Model-Based Learning for Long-Term Age of Information Minimization in Vehicular Networks\". [![arXiv](https://img.shields.io/badge/arXiv-2505.01712-b31b1b.svg)](https://arxiv.org/abs/2505.01712)\n* \"Learning to Drive from a World Model\". [![arXiv](https://img.shields.io/badge/arXiv-2504.19077-b31b1b.svg)](https://arxiv.org/abs/2504.19077)\n* **DriVerse**: \"DriVerse: Navigation World Model for Driving Simulation via Multimodal Trajectory Prompting and Motion Alignment\". [![arXiv](https://img.shields.io/badge/arXiv-2504.18576-b31b1b.svg)](https://arxiv.org/abs/2504.18576) \n* \"End-to-End Driving with Online Trajectory Evaluation via BEV World Model\". [![arXiv](https://img.shields.io/badge/arXiv-2504.01941-b31b1b.svg)](https://arxiv.org/abs/2504.01941) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/liyingyanUCAS/WoTE) \n* \"Knowledge Graphs as World Models for Semantic Material-Aware Obstacle Handling in Autonomous Vehicles\". [![arXiv](https://img.shields.io/badge/arXiv-2503.21232-b31b1b.svg)](https://arxiv.org/abs/2503.21232)\n* **MiLA**: \"MiLA: Multi-view Intensive-fidelity Long-term Video Generation World Model for Autonomous Driving\". [![arXiv](https://img.shields.io/badge/arXiv-2503.15875-b31b1b.svg)](https://arxiv.org/abs/2503.15875) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://github.com/xiaomi-mlab/mila.github.io) \n* **SimWorld**: \"SimWorld: A Unified Benchmark for Simulator-Conditioned Scene Generation via World Model\". [![arXiv](https://img.shields.io/badge/arXiv-2503.13952-b31b1b.svg)](https://arxiv.org/abs/2503.13952) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://github.com/Li-Zn-H/SimWorld) \n* **UniFuture**: \"Seeing the Future, Perceiving the Future: A Unified Driving World Model for Future Generation and Perception\". [![arXiv](https://img.shields.io/badge/arXiv-2503.13587-b31b1b.svg)](https://arxiv.org/abs/2503.13587) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://github.com/dk-liang/UniFuture) \n* **EOT-WM**: \"Other Vehicle Trajectories Are Also Needed: A Driving World Model Unifies Ego-Other Vehicle Trajectories in Video Latent Space\". [![arXiv](https://img.shields.io/badge/arXiv-2503.09215-b31b1b.svg)](https://arxiv.org/abs/2503.09215)\n* \"Temporal Triplane Transformers as Occupancy World Models\". [![arXiv](https://img.shields.io/badge/arXiv-2503.07338-b31b1b.svg)](https://arxiv.org/abs/2503.07338)\n* **InDRiVE**: \"InDRiVE: Intrinsic Disagreement based Reinforcement for Vehicle Exploration through Curiosity Driven Generalized World Model\". [![arXiv](https://img.shields.io/badge/arXiv-2503.05573-b31b1b.svg)](https://arxiv.org/abs/2503.05573)\n* **MaskGWM**: \"MaskGWM: A Generalizable Driving World Model with Video Mask Reconstruction\". [![arXiv](https://img.shields.io/badge/arXiv-2502.11663-b31b1b.svg)](https://arxiv.org/abs/2502.11663)\n* **Dream to Drive**: \"Dream to Drive: Model-Based Vehicle Control Using Analytic World Models\". [![arXiv](https://img.shields.io/badge/arXiv-2502.10012-b31b1b.svg)](https://arxiv.org/abs/2502.10012)\n* \"Semi-Supervised Vision-Centric 3D Occupancy World Model for Autonomous Driving\". [![arXiv](https://img.shields.io/badge/arXiv-2502.07309-b31b1b.svg)](https://arxiv.org/abs/2502.07309)\n* \"Dream to Drive with Predictive Individual World Model\". [![arXiv](https://img.shields.io/badge/arXiv-2501.16733-b31b1b.svg)](https://arxiv.org/abs/2501.16733) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/gaoyinfeng/PIWM)\n* **HERMES**: \"HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation\". [![arXiv](https://img.shields.io/badge/arXiv-2501.14729-b31b1b.svg)](https://arxiv.org/abs/2501.14729) \n* **AdaWM**: \"AdaWM: Adaptive World Model based Planning for Autonomous Driving\". [![arXiv](https://img.shields.io/badge/arXiv-2501.13072-b31b1b.svg)](https://arxiv.org/abs/2501.13072) \n* **AD-L-JEPA**: \"AD-L-JEPA: Self-Supervised Spatial World Models with Joint Embedding Predictive Architecture for Autonomous Driving with LiDAR Data\". [![arXiv](https://img.shields.io/badge/arXiv-2501.04969-b31b1b.svg)](https://arxiv.org/abs/2501.04969)  \n* **DrivingWorld**: \"DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT\". [![arXiv](https://img.shields.io/badge/arXiv-2412.19505-b31b1b.svg)](https://arxiv.org/abs/2412.19505) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/YvanYin/DrivingWorld) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://huxiaotaostasy.github.io/DrivingWorld/index.html) \n* **DrivingGPT**: \"DrivingGPT: Unifying Driving World Modeling and Planning with Multi-modal Autoregressive Transformers\". [![arXiv](https://img.shields.io/badge/arXiv-2412.18607-b31b1b.svg)](https://arxiv.org/abs/2412.18607) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://rogerchern.github.io/DrivingGPT/)\n* \"An Efficient Occupancy World Model via Decoupled Dynamic Flow and Image-assisted Training\". [![arXiv](https://img.shields.io/badge/arXiv-2412.13772-b31b1b.svg)](https://arxiv.org/abs/2412.13772)\n* **GEM**: \"GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control\". [![arXiv](https://img.shields.io/badge/arXiv-2412.11198-b31b1b.svg)](https://arxiv.org/abs/2412.11198) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://vita-epfl.github.io/GEM.github.io/)\n* **GaussianWorld**: \"GaussianWorld: Gaussian World Model for Streaming 3D Occupancy Prediction\". [![arXiv](https://img.shields.io/badge/arXiv-2412.04380-b31b1b.svg)](https://arxiv.org/abs/2412.04380) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/zuosc19/GaussianWorld)\n* **Doe-1**: \"Doe-1: Closed-Loop Autonomous Driving with Large World Model\". [![arXiv](https://img.shields.io/badge/arXiv-2412.09627-b31b1b.svg)](https://arxiv.org/abs/2412.09627) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://wzzheng.net/Doe/) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/wzzheng/Doe)\n* \"Physical Informed Driving World Model\". [![arXiv](https://img.shields.io/badge/arXiv-2412.08410-b31b1b.svg)](https://arxiv.org/abs/2412.08410) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://metadrivescape.github.io/papers_project/DrivePhysica/page.html)\n* **InfiniCube**: \"InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models\". [![arXiv](https://img.shields.io/badge/arXiv-2412.03934-b31b1b.svg)](https://arxiv.org/abs/2412.03934) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://research.nvidia.com/labs/toronto-ai/infinicube/)\n* **InfinityDrive**: \"InfinityDrive: Breaking Time Limits in Driving World Models\". [![arXiv](https://img.shields.io/badge/arXiv-2412.01522-b31b1b.svg)](https://arxiv.org/abs/2412.01522) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://metadrivescape.github.io/papers_project/InfinityDrive/page.html)\n* **ReconDreamer**: \"ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration\". [![arXiv](https://img.shields.io/badge/arXiv-2411.19548-b31b1b.svg)](https://arxiv.org/abs/2411.19548) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://recondreamer.github.io/)\n* **Imagine-2-Drive**: \"Imagine-2-Drive: High-Fidelity World Modeling in CARLA for Autonomous Vehicles\". [![arXiv](https://img.shields.io/badge/arXiv-2411.10171-b31b1b.svg)](https://arxiv.org/abs/2411.10171) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://anantagrg.github.io/Imagine-2-Drive.github.io/)\n* **DynamicCity**: \"DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes\". [![arXiv](https://img.shields.io/badge/arXiv-2410.18084-b31b1b.svg)](https://arxiv.org/abs/2410.18084) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://dynamic-city.github.io) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/3DTopia/DynamicCity)\n* **DriveDreamer4D**: \"World Models Are Effective Data Machines for 4D Driving Scene Representation\". [![arXiv](https://img.shields.io/badge/arXiv-2410.13571-b31b1b.svg)](https://arxiv.org/abs/2410.13571) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://drivedreamer4d.github.io/)\n* **DOME**: \"Taming Diffusion Model into High-Fidelity Controllable Occupancy World Model\". [![arXiv](https://img.shields.io/badge/arXiv-2410.10429-b31b1b.svg)](https://arxiv.org/abs/2410.10429) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://gusongen.github.io/DOME)\n* **SSR**: \"Does End-to-End Autonomous Driving Really Need Perception Tasks?\". [![arXiv](https://img.shields.io/badge/arXiv-2409.18341-b31b1b.svg)](https://arxiv.org/abs/2409.18341) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/PeidongLi/SSR)\n* \"Mitigating Covariate Shift in Imitation Learning for Autonomous Vehicles Using Latent Space Generative World Models\". [![arXiv](https://img.shields.io/badge/arXiv-2409.16663-b31b1b.svg)](https://arxiv.org/abs/2409.16663)\n* **LatentDriver**: \"Learning Multiple Probabilistic Decisions from Latent World Model in Autonomous Driving\". [![arXiv](https://img.shields.io/badge/arXiv-2409.15730-b31b1b.svg)](https://arxiv.org/abs/2409.15730) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/Sephirex-X/LatentDriver)\n* **RenderWorld**: \"World Model with Self-Supervised 3D Label\". [![arXiv](https://img.shields.io/badge/arXiv-2409.11356-b31b1b.svg)](https://arxiv.org/abs/2409.11356)\n* **OccLLaMA**: \"An Occupancy-Language-Action Generative World Model for Autonomous Driving\". [![arXiv](https://img.shields.io/badge/arXiv-2409.03272-b31b1b.svg)](https://arxiv.org/abs/2409.03272)\n* **DriveGenVLM**: \"Real-world Video Generation for Vision Language Model based Autonomous Driving\". [![arXiv](https://img.shields.io/badge/arXiv-2408.16647-b31b1b.svg)](https://arxiv.org/abs/2408.16647)\n* **Drive-OccWorld**: \"Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous Driving\". [![arXiv](https://img.shields.io/badge/arXiv-2408.14197-b31b1b.svg)](https://arxiv.org/abs/2408.14197)\n* **CarFormer**: \"Self-Driving with Learned Object-Centric Representations\". [![arXiv](https://img.shields.io/badge/arXiv-2407.15843-b31b1b.svg)](https://arxiv.org/abs/2407.15843) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://kuis-ai.github.io/CarFormer/)\n* **BEVWorld**: \"A Multimodal World Model for Autonomous Driving via Unified BEV Latent Space\". [![arXiv](https://img.shields.io/badge/arXiv-2407.05679-b31b1b.svg)](https://arxiv.org/abs/2407.05679) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/zympsyche/BevWorld)\n* **TOKEN**: \"Tokenize the World into Object-level Knowledge to Address Long-tail Events in Autonomous Driving\". [![arXiv](https://img.shields.io/badge/arXiv-2407.00959-b31b1b.svg)](https://arxiv.org/abs/2407.00959)\n* **UMAD**: \"Unsupervised Mask-Level Anomaly Detection for Autonomous Driving\". [![arXiv](https://img.shields.io/badge/arXiv-2406.06370-b31b1b.svg)](https://arxiv.org/abs/2406.06370)\n* **SimGen**: \"Simulator-conditioned Driving Scene Generation\". [![arXiv](https://img.shields.io/badge/arXiv-2406.09386-b31b1b.svg)](https://arxiv.org/abs/2406.09386) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://metadriverse.github.io/simgen/)\n* **AdaptiveDriver**: \"Planning with Adaptive World Models for Autonomous Driving\". [![arXiv](https://img.shields.io/badge/arXiv-2406.10714-b31b1b.svg)](https://arxiv.org/abs/2406.10714) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://arunbalajeev.github.io/world_models_planning/world_model_paper.html)\n* **UnO**: \"Unsupervised Occupancy Fields for Perception and Forecasting\". [![arXiv](https://img.shields.io/badge/arXiv-2406.08691-b31b1b.svg)](https://arxiv.org/abs/2406.08691) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://waabi.ai/research/uno)\n* **LAW**: \"Enhancing End-to-End Autonomous Driving with Latent World Model\". [![arXiv](https://img.shields.io/badge/arXiv-2406.08481-b31b1b.svg)](https://arxiv.org/abs/2406.08481) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/BraveGroup/LAW)\n* **Delphi**: \"Unleashing Generalization of End-to-End Autonomous Driving with Controllable Long Video Generation\". [![arXiv](https://img.shields.io/badge/arXiv-2406.01349-b31b1b.svg)](https://arxiv.org/abs/2406.01349) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/westlake-autolab/Delphi)\n* **OccSora**: \"4D Occupancy Generation Models as World Simulators for Autonomous Driving\". [![arXiv](https://img.shields.io/badge/arXiv-2405.20337-b31b1b.svg)](https://arxiv.org/abs/2405.20337) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/wzzheng/OccSora)\n* **MagicDrive3D**: \"Controllable 3D Generation for Any-View Rendering in Street Scenes\". [![arXiv](https://img.shields.io/badge/arXiv-2405.14475-b31b1b.svg)](https://arxiv.org/abs/2405.14475) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://gaoruiyuan.com/magicdrive3d/)\n* **Vista**: \"A Generalizable Driving World Model with High Fidelity and Versatile Controllability\". [![arXiv](https://img.shields.io/badge/arXiv-2405.17398-b31b1b.svg)](https://arxiv.org/abs/2405.17398) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/OpenDriveLab/Vista)\n* **CarDreamer**: \"Open-Source Learning Platform for World Model based Autonomous Driving\". [![arXiv](https://img.shields.io/badge/arXiv-2405.09111-b31b1b.svg)](https://arxiv.org/abs/2405.09111) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/ucd-dare/CarDreamer)\n* **DriveSim**: \"Probing Multimodal LLMs as World Models for Driving\". [![arXiv](https://img.shields.io/badge/arXiv-2405.05956-b31b1b.svg)](https://arxiv.org/abs/2405.05956) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/sreeramsa/DriveSim)\n* **DriveWorld**: \"4D Pre-trained Scene Understanding via World Models for Autonomous Driving\". [![arXiv](https://img.shields.io/badge/arXiv-2405.04390-b31b1b.svg)](https://arxiv.org/abs/2405.04390)\n* **LidarDM**: \"Generative LiDAR Simulation in a Generated World\". [![arXiv](https://img.shields.io/badge/arXiv-2404.02903-b31b1b.svg)](https://arxiv.org/abs/2404.02903) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/vzyrianov/lidardm)\n* **SubjectDrive**: \"Scaling Generative Data in Autonomous Driving via Subject Control\". [![arXiv](https://img.shields.io/badge/arXiv-2403.19438-b31b1b.svg)](https://arxiv.org/abs/2403.19438) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://subjectdrive.github.io/)\n* **DriveDreamer-2**: \"LLM-Enhanced World Models for Diverse Driving Video Generation\". [![arXiv](https://img.shields.io/badge/arXiv-2403.06845-b31b1b.svg)](https://arxiv.org/abs/2403.06845) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://drivedreamer2.github.io/)\n* **Think2Drive**: \"Efficient Reinforcement Learning by Thinking in Latent World Model for Quasi-Realistic Autonomous Driving\". [![arXiv](https://img.shields.io/badge/arXiv-2402.16720-b31b1b.svg)](https://arxiv.org/abs/2402.16720)\n* **MARL-CCE**: \"Modelling Competitive Behaviors in Autonomous Driving Under Generative World Model\". [![arXiv](https://img.shields.io/badge/arXiv-Paper-b31b1b.svg)](https://www.ecva.net/papers/eccv_2024/papers_ECCV/papers/05085.pdf) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/qiaoguanren/MARL-CCE)\n* **GenAD**: \"Generalized Predictive Model for Autonomous Driving\". [![arXiv](https://img.shields.io/badge/arXiv-2403.09630-b31b1b.svg)](https://arxiv.org/abs/2403.09630) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://github.com/OpenDriveLab/DriveAGI?tab=readme-ov-file#genad-dataset-opendv-youtube)\n* **GenAD**: \"Generative End-to-End Autonomous Driving\". [![arXiv](https://img.shields.io/badge/arXiv-2402.11502-b31b1b.svg)](https://arxiv.org/abs/2402.11502) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/wzzheng/GenAD)\n* **NeMo**: \"Neural Volumetric World Models for Autonomous Driving\". [![arXiv](https://img.shields.io/badge/arXiv-Paper-b31b1b.svg)](https://www.ecva.net/papers/eccv_2024/papers_ECCV/papers/02571.pdf)\n* **MARL-CCE**: \"Modelling-Competitive-Behaviors-in-Autonomous-Driving-Under-Generative-World-Model\". [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/qiaoguanren/MARL-CCE)\n* **ViDAR**: \"Visual Point Cloud Forecasting enables Scalable Autonomous Driving\". [![arXiv](https://img.shields.io/badge/arXiv-2312.17655-b31b1b.svg)](https://arxiv.org/abs/2312.17655) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/OpenDriveLab/ViDAR)\n* **Drive-WM**: \"Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving\". [![arXiv](https://img.shields.io/badge/arXiv-2311.17918-b31b1b.svg)](https://arxiv.org/abs/2311.17918) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/BraveGroup/Drive-WM)\n* **Cam4DOCC**: \"Benchmark for Camera-Only 4D Occupancy Forecasting in Autonomous Driving Applications\". [![arXiv](https://img.shields.io/badge/arXiv-2311.17663-b31b1b.svg)](https://arxiv.org/abs/2311.17663) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/haomo-ai/Cam4DOcc)\n* **Panacea**: \"Panoramic and Controllable Video Generation for Autonomous Driving\". [![arXiv](https://img.shields.io/badge/arXiv-2311.16813-b31b1b.svg)](https://arxiv.org/abs/2311.16813) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://panacea-ad.github.io/)\n* **OccWorld**: \"Learning a 3D Occupancy World Model for Autonomous Driving\". [![arXiv](https://img.shields.io/badge/arXiv-2311.16038-b31b1b.svg)](https://arxiv.org/abs/2311.16038) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/wzzheng/OccWorld)\n\n* **DrivingDiffusion**: \"Layout-Guided multi-view driving scene video generation with latent diffusion model\". [![arXiv](https://img.shields.io/badge/arXiv-2310.07771-b31b1b.svg)](https://arxiv.org/abs/2310.07771) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/shalfun/DrivingDiffusion)\n* **SafeDreamer**: \"Safe Reinforcement Learning with World Models\". [![arXiv](https://img.shields.io/badge/arXiv-Paper-b31b1b.svg)](https://openreview.net/forum?id=tsE5HLYtYg) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/PKU-Alignment/SafeDreamer)\n* **MagicDrive**: \"Street View Generation with Diverse 3D Geometry Control\". [![arXiv](https://img.shields.io/badge/arXiv-2310.02601-b31b1b.svg)](https://arxiv.org/abs/2310.02601) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/cure-lab/MagicDrive)\n* **DriveDreamer**: \"Towards Real-world-driven World Models for Autonomous Driving\". [![arXiv](https://img.shields.io/badge/arXiv-2309.09777-b31b1b.svg)](https://arxiv.org/abs/2309.09777) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/JeffWang987/DriveDreamer)\n* **SEM2**: \"Enhance Sample Efficiency and Robustness of End-to-end Urban Autonomous Driving via Semantic Masked World Model\". [![arXiv](https://img.shields.io/badge/arXiv-Paper-b31b1b.svg)](https://ieeexplore.ieee.org/abstract/document/10538211/)\n\n\u003c!-- inserted --\u003e\n* **COMPARATIVE STUDY OF WORLD MODELS**: \"COMPARATIVE STUDY OF WORLD MODELS, NVAE- BASED HIERARCHICAL MODELS, AND NOISYNET- AUGMENTED MODELS IN CARRACING-V2\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=ICLR.cc/2025/Workshop/World_Models#tab-accept) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://sites.google.com/view/worldmodel-iclr2025/accepted-papers)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **Knowledge Graphs as World Models**: \"Knowledge Graphs as World Models for Material-Aware Obstacle Handling in Autonomous Vehicles\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=ICLR.cc/2025/Workshop/World_Models#tab-accept) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://sites.google.com/view/worldmodel-iclr2025/accepted-papers)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **Uncertainty Modeling**: \"Uncertainty Modeling in Autonomous Vehicle Trajectory Prediction: A Comprehensive Survey\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=ICML.cc/2025/Workshop/World_Models#tab-accept) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://worldmodelbench.github.io/)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **Divide and Merge**: \"Divide and Merge: Motion and Semantic Learning in End-to-End Autonomous Driving\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=NeurIPS.cc/2025/Workshop/EWM#tab-accept-oral) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://embodied-world-models.github.io/)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **RDAR**: \"RDAR: Reward-Driven Agent Relevance Estimation for Autonomous Driving\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=NeurIPS.cc/2025/Workshop/EWM#tab-accept-oral) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://embodied-world-models.github.io/)\n\u003c!-- end inserted --\u003e\n\n## World Models for Embodied AI\n### 1. Foundation Embodied World Models\n- [⭐️] **Genie Envisioner**: \"Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation\". [![arXiv](https://img.shields.io/badge/arXiv-2508.05635-b31b1b.svg)](https://arxiv.org/abs/2508.05635) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://genie-envisioner.github.io/)\n- [⭐️] **WoW**, \"WoW: Towards a World omniscient World model Through Embodied Interaction\". [![arXiv](https://img.shields.io/badge/arXiv-2509.22642-b31b1b.svg)](https://arxiv.org/abs/2509.22642) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://wow-world-model.github.io) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/wow-world-model/wow-world-model)\n- **UnifoLM-WMA-0**, \"UnifoLM-WMA-0: A World-Model-Action (WMA) Framework under UnifoLM Family\". [![Website](https://img.shields.io/badge/Website-Link-blue)](https://unigen-x.github.io/unifolm-world-model-action.github.io/) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/unitreerobotics/unifolm-world-model-action/tree/main)\n- [⭐️] **iVideoGPT**, \"iVideoGPT: Interactive VideoGPTs are Scalable World Models\". [![arXiv](https://img.shields.io/badge/arXiv-2405.15223-b31b1b.svg)](https://arxiv.org/abs/2405.15223)[![Website](https://img.shields.io/badge/Website-Link-blue)](https://thuml.github.io/iVideoGPT/)\u003c!-- inserted --\u003e\n* **Direct Robot Configuration Space Construction**: \"Direct Robot Configuration Space Construction using Convolutional Encoder-Decoders\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=ICML.cc/2025/Workshop/World_Models#tab-accept) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://physical-world-modeling.github.io/)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **ViPRA**: \"ViPRA: Video Prediction for Robot Actions\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=NeurIPS.cc/2025/Workshop/EWM#tab-accept-oral) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://embodied-world-models.github.io/)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **ROPES**: \"ROPES: Robotic Pose Estimation via Score-based Causal Representation Learning\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=NeurIPS.cc/2025/Workshop/EWM#tab-accept-oral) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://embodied-world-models.github.io/)\n\u003c!-- end inserted --\u003e\n\n### 2. World Models for Manipulation\n- [⭐️] **FLARE**, \"FLARE: Robot Learning with Implicit World Modeling\". [![arXiv](https://img.shields.io/badge/arXiv-2505.15659-b31b1b.svg)](http://arxiv.org/abs/2505.15659) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://research.nvidia.com/labs/gear/flare/)\n- [⭐️] **Enerverse**, \"EnerVerse: Envisioning Embodied Future Space for Robotics Manipulation\". [![arXiv](https://img.shields.io/badge/arXiv-2501.01895-b31b1b.svg)](http://arxiv.org/abs/2501.01895) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://sites.google.com/view/enerverse)\n- [⭐️] **AgiBot-World**, \"AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems\". [![arXiv](https://img.shields.io/badge/arXiv-2503.06669-b31b1b.svg)](https://arxiv.org/abs/2503.06669) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://agibot-world.com/) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/OpenDriveLab/AgiBot-World)\n- [⭐️] **DyWA**: \"DyWA: Dynamics-adaptive World Action Model for Generalizable Non-prehensile Manipulation\" [![arXiv](https://img.shields.io/badge/arXiv-2503.16806-b31b1b.svg)](https://arxiv.org/abs/2503.16806) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://pku-epic.github.io/DyWA/) \n- [⭐️] **TesserAct**, \"TesserAct: Learning 4D Embodied World Models\". [![arXiv](https://img.shields.io/badge/arXiv-2504.20995-b31b1b.svg)](https://arxiv.org/abs/2504.20995) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://tesseractworld.github.io/)\n- [⭐️] **DreamGen**: \"DreamGen: Unlocking Generalization in Robot Learning through Video World Models\". [![arXiv](https://img.shields.io/badge/arXiv-2505.12705-b31b1b.svg)](https://arxiv.org/abs/2505.12705) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/nvidia/GR00T-dreams)\n- [⭐️] **HiP**, \"Compositional Foundation Models for Hierarchical Planning\". [![arXiv](https://img.shields.io/badge/arXiv-2309.08587-b31b1b.svg)](http://arxiv.org/abs/2309.08587) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://hierarchical-planning-foundation-model.github.io/)\n- **PAR**: \"Physical Autoregressive Model for Robotic Manipulation without Action Pretraining\". [![arXiv](https://img.shields.io/badge/arXiv-2508.09822-b31b1b.svg)](https://arxiv.org/abs/2508.09822) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://songzijian1999.github.io/PAR_ProjectPage/)\n- **iMoWM**: \"iMoWM: Taming Interactive Multi-Modal World Model for Robotic Manipulation\". [![arXiv](https://img.shields.io/badge/arXiv-2510.07313-b31b1b.svg)](https://arxiv.org/abs/2510.07313) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://xingyoujun.github.io/imowm/)\n- **WristWorld**: \"WristWorld: Generating Wrist-Views via 4D World Models for Robotic Manipulation\". [![arXiv](https://img.shields.io/badge/arXiv-2510.07313-b31b1b.svg)](https://arxiv.org/abs/2510.07313)\n- \"A Recipe for Efficient Sim-to-Real Transfer in Manipulation with Online Imitation-Pretrained World Models\". [![arXiv](https://img.shields.io/badge/arXiv-2510.02538-b31b1b.svg)](https://arxiv.org/abs/2510.02538)\n- **EMMA**: \"EMMA: Generalizing Real-World Robot Manipulation via Generative Visual Transfer\". [![arXiv](https://img.shields.io/badge/arXiv-2509.22407-b31b1b.svg)](https://arxiv.org/abs/2509.22407)\n- **PhysTwin**, \"PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videos\". [![arXiv](https://img.shields.io/badge/arXiv-2503.17973-b31b1b.svg)](http://arxiv.org/abs/2503.17973) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://jianghanxiao.github.io/phystwin-web/) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/Jianghanxiao/PhysTwin)\n- [⭐️] **KeyWorld**: \"KeyWorld: Key Frame Reasoning Enables Effective and Efficient World Models\". [![arXiv](https://img.shields.io/badge/arXiv-2509.21027-b31b1b.svg)](https://arxiv.org/abs/2509.21027)\n- **World4RL**: \"World4RL: Diffusion World Models for Policy Refinement with Reinforcement Learning for Robotic Manipulation\". [![arXiv](https://img.shields.io/badge/arXiv-2509.19080-b31b1b.svg)](https://arxiv.org/abs/2509.19080)\n- [⭐️] **SAMPO**: \"SAMPO:Scale-wise Autoregression with Motion PrOmpt for generative world models\". [![arXiv](https://img.shields.io/badge/arXiv-2509.15536-b31b1b.svg)](https://arxiv.org/abs/2509.15536)\n- **PhysicalAgent**: \"PhysicalAgent: Towards General Cognitive Robotics with Foundation World Models\". [![arXiv](https://img.shields.io/badge/arXiv-2509.13903-b31b1b.svg)](https://arxiv.org/abs/2509.13903)\n- \"Empowering Multi-Robot Cooperation via Sequential World Models\". [![arXiv](https://img.shields.io/badge/arXiv-2509.13095-b31b1b.svg)](https://arxiv.org/abs/2509.13095)\n- [⭐️] \"Learning Primitive Embodied World Models: Towards Scalable Robotic Learning\". [![arXiv](https://img.shields.io/badge/arXiv-2508.20840-b31b1b.svg)](https://arxiv.org/pdf/2508.20840) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://qiaosun22.github.io/PrimitiveWorld/)\n- [⭐️] **GWM**: \"GWM: Towards Scalable Gaussian World Models for Robotic Manipulation\". [![arXiv](https://img.shields.io/badge/arXiv-2508.17600-b31b1b.svg)](https://arxiv.org/abs/2508.17600) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://gaussian-world-model.github.io/)\n- [⭐️] **Flow-as-Action**, \"Latent Policy Steering with Embodiment-Agnostic Pretrained World Models\". [![arXiv](https://img.shields.io/badge/arXiv-2507.13340-b31b1b.svg)](https://arxiv.org/abs/2507.13340)\n- **EmbodieDreamer**: \"EmbodieDreamer: Advancing Real2Sim2Real Transfer for Policy Training via Embodied World Modeling\". [![arXiv](https://img.shields.io/badge/arXiv-2507.05198-b31b1b.svg)](https://arxiv.org/pdf/2507.05198) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://embodiedreamer.github.io/)\n- **RoboScape**: \"RoboScape: Physics-informed Embodied World Model\". [![arXiv](https://img.shields.io/badge/arXiv-2506.23135-b31b1b.svg)](https://arxiv.org/abs/2506.23135) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/tsinghua-fib-lab/RoboScape)\n- **FWM**, \"Factored World Models for Zero-Shot Generalization in Robotic Manipulation\". [![arXiv](https://img.shields.io/badge/arXiv-2202.05333-b31b1b.svg)](http://arxiv.org/abs/2202.05333)\n- [⭐️] **ParticleFormer**: \"ParticleFormer: A 3D Point Cloud World Model for Multi-Object, Multi-Material Robotic Manipulation\". [![arXiv](https://img.shields.io/badge/arXiv-2506.23126-b31b1b.svg)](https://arxiv.org/abs/2506.23126) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://particleformer.github.io/)\n- **ManiGaussian++**: \"ManiGaussian++: General Robotic Bimanual Manipulation with Hierarchical Gaussian World Model\". [![arXiv](https://img.shields.io/badge/arXiv-2506.19842-b31b1b.svg)](https://arxiv.org/abs/2506.19842) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/April-Yz/ManiGaussian_Bimanual)\n- **ReOI**: \"Reimagination with Test-time Observation Interventions: Distractor-Robust World Model Predictions for Visual Model Predictive Control\". [![arXiv](https://img.shields.io/badge/arXiv-2506.16565-b31b1b.svg)](https://arxiv.org/abs/2506.16565) \n- **GAF**: \"GAF: Gaussian Action Field as a Dynamic World Model for Robotic Manipulation\". [![arXiv](https://img.shields.io/badge/arXiv-2506.14135-b31b1b.svg)](https://arxiv.org/abs/2506.14135) [![Website](https://img.shields.io/badge/Website-Link-blue)](http://chaiying1.github.io/GAF.github.io/project_page/)\n- \"Prompting with the Future: Open-World Model Predictive Control with Interactive Digital Twins\". [![arXiv](https://img.shields.io/badge/arXiv-2506.13761-b31b1b.svg)](https://arxiv.org/abs/2506.13761) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://prompting-with-the-future.github.io/)\n- \"Time-Aware World Model for Adaptive Prediction and Control\". [![arXiv](https://img.shields.io/badge/arXiv-2506.08441-b31b1b.svg)](https://arxiv.org/abs/2506.08441) \n- [⭐️] **3DFlowAction**: \"3DFlowAction: Learning Cross-Embodiment Manipulation from 3D Flow World Model\". [![arXiv](https://img.shields.io/badge/arXiv-2506.06199-b31b1b.svg)](https://arxiv.org/abs/2506.06199) \n- [⭐️] **ORV**: \"ORV: 4D Occupancy-centric Robot Video Generation\". [![arXiv](https://img.shields.io/badge/arXiv-2506.03079-b31b1b.svg)](https://arxiv.org/abs/2506.03079) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/OrangeSodahub/ORV) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://orangesodahub.github.io/ORV/)\n- [⭐️] **WoMAP**: \"WoMAP: World Models For Embodied Open-Vocabulary Object Localization\". [![arXiv](https://img.shields.io/badge/arXiv-2506.01600-b31b1b.svg)](https://arxiv.org/abs/2506.01600) \n- \"Sparse Imagination for Efficient Visual World Model Planning\". [![arXiv](https://img.shields.io/badge/arXiv-2506.01392-b31b1b.svg)](https://arxiv.org/abs/2506.01392)\n- [⭐️] **OSVI-WM**: \"OSVI-WM: One-Shot Visual Imitation for Unseen Tasks using World-Model-Guided Trajectory Generation\". [![arXiv](https://img.shields.io/badge/arXiv-2505.20425-b31b1b.svg)](https://arxiv.org/abs/2505.20425) \n- [⭐️] **LaDi-WM**: \"LaDi-WM: A Latent Diffusion-based World Model for Predictive Manipulation\". [![arXiv](https://img.shields.io/badge/arXiv-2505.11528-b31b1b.svg)](https://arxiv.org/abs/2505.11528)\n- **FlowDreamer**: \"FlowDreamer: A RGB-D World Model with Flow-based Motion Representations for Robot Manipulation\". [![arXiv](https://img.shields.io/badge/arXiv-2505.10075-b31b1b.svg)](https://arxiv.org/abs/2505.10075) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://sharinka0715.github.io/FlowDreamer/)\n- **PIN-WM**: \"PIN-WM: Learning Physics-INformed World Models for Non-Prehensile Manipulation\". [![arXiv](https://img.shields.io/badge/arXiv-2504.16693-b31b1b.svg)](https://arxiv.org/abs/2504.16693) \n- **RoboMaster**, \"Learning Video Generation for Robotic Manipulation with Collaborative Trajectory Control\". [![arXiv](https://img.shields.io/badge/arXiv-2506.01943-b31b1b.svg)](http://arxiv.org/abs/2506.01943) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://fuxiao0719.github.io/projects/robomaster/) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/KwaiVGI/RoboMaster)\n- **ManipDreamer**: \"ManipDreamer: Boosting Robotic Manipulation World Model with Action Tree and Visual Guidance\". [![arXiv](https://img.shields.io/badge/arXiv-2504.16464-b31b1b.svg)](https://arxiv.org/abs/2504.16464) \n- [⭐️] **AdaWorld**: \"AdaWorld: Learning Adaptable World Models with Latent Actions\" [![arXiv](https://img.shields.io/badge/arXiv-2503.18938-b31b1b.svg)](https://arxiv.org/abs/2503.18938) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://adaptable-world-model.github.io/) \n- \"Towards Suturing World Models: Learning Predictive Models for Robotic Surgical Tasks\" [![arXiv](https://img.shields.io/badge/arXiv-2503.12531-b31b1b.svg)](https://arxiv.org/abs/2503.12531) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://mkturkcan.github.io/suturingmodels/) \n- [⭐️] **EVA**: \"EVA: An Embodied World Model for Future Video Anticipation\". [![arXiv](https://img.shields.io/badge/arXiv-2410.15461-b31b1b.svg)](https://arxiv.org/abs/2410.15461) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://sites.google.com/view/eva-publi) \n- \"Representing Positional Information in Generative World Models for Object Manipulation\". [![arXiv](https://img.shields.io/badge/arXiv-2409.12005-b31b1b.svg)](https://arxiv.org/abs/2409.12005)\n- **DexSim2Real$^2$**: \"DexSim2Real$^2: Building Explicit World Model for Precise Articulated Object Dexterous Manipulation\". [![arXiv](https://img.shields.io/badge/arXiv-2409.08750-b31b1b.svg)](https://arxiv.org/abs/2409.08750)\n- \"Physically Embodied Gaussian Splatting: A Realtime Correctable World Model for Robotics\". [![arXiv](https://img.shields.io/badge/arXiv-2406.10788-b31b1b.svg)](https://arxiv.org/abs/2406.10788) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://embodied-gaussians.github.io/)\n- [⭐️] **LUMOS**: \"LUMOS: Language-Conditioned Imitation Learning with World Models\". [![arXiv](https://img.shields.io/badge/arXiv-2503.10370-b31b1b.svg)](https://arxiv.org/abs/2503.10370) [![Website](https://img.shields.io/badge/Website-Link-blue)](http://lumos.cs.uni-freiburg.de/) \n- [⭐️] \"Object-Centric World Model for Language-Guided Manipulation\" [![arXiv](https://img.shields.io/badge/arXiv-2503.06170-b31b1b.svg)](https://arxiv.org/abs/2503.06170) \n- [⭐️] **DEMO^3**: \"Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model Learning\" [![arXiv](https://img.shields.io/badge/arXiv-2503.01837-b31b1b.svg)](https://arxiv.org/abs/2503.01837) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://adrialopezescoriza.github.io/demo3/) \n- \"Strengthening Generative Robot Policies through Predictive World Modeling\". [![arXiv](https://img.shields.io/badge/arXiv-2502.00622-b31b1b.svg)](https://arxiv.org/abs/2502.00622) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://computationalrobotics.seas.harvard.edu/GPC) \n- **RoboHorizon**: \"RoboHorizon: An LLM-Assisted Multi-View World Model for Long-Horizon Robotic Manipulation. [![arXiv](https://img.shields.io/badge/arXiv-2501.06605-b31b1b.svg)](https://arxiv.org/abs/2501.06605) \n- **Dream to Manipulate**: \"Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imagination\". [![arXiv](https://img.shields.io/badge/arXiv-2412.14957-b31b1b.svg)](https://arxiv.org/abs/2412.14957) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://leobarcellona.github.io/DreamToManipulate/) \n- [⭐️] **RoboDreamer**: \"RoboDreamer: Learning Compositional World Models for Robot Imagination\". [![arXiv](https://img.shields.io/badge/arXiv-2404.12377-b31b1b.svg)](https://arxiv.org/abs/2404.12377) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://robovideo.github.io/)\n- **ManiGaussian**: \"ManiGaussian: Dynamic Gaussian Splatting for Multi-task Robotic Manipulation\". [![arXiv](https://img.shields.io/badge/arXiv-2403.08321-b31b1b.svg)](https://arxiv.org/abs/2403.08321) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://guanxinglu.github.io/ManiGaussian/)\n- [⭐️] **WHALE**: \"WHALE: Towards Generalizable and Scalable World Models for Embodied Decision-making\". [![arXiv](https://img.shields.io/badge/arXiv-2411.05619-b31b1b.svg)](https://arxiv.org/abs/2411.05619)\n- [⭐️] **VisualPredicator**: \"VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot Planning\". [![arXiv](https://img.shields.io/badge/arXiv-2410.23156-b31b1b.svg)](https://arxiv.org/abs/2410.23156) \n- [⭐️] \"Multi-Task Interactive Robot Fleet Learning with Visual World Models\". [![arXiv](https://img.shields.io/badge/arXiv-2410.22689-b31b1b.svg)](https://arxiv.org/abs/2410.22689) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://ut-austin-rpl.github.io/sirius-fleet/)\n- **PIVOT-R**: \"PIVOT-R: Primitive-Driven Waypoint-Aware World Model for Robotic Manipulation\". [![arXiv](https://img.shields.io/badge/arXiv-2410.10394-b31b1b.svg)](https://arxiv.org/pdf/2410.10394)\n- **Video2Action**, \"Grounding Video Models to Actions through Goal Conditioned Exploration\". [![arXiv](https://img.shields.io/badge/arXiv-2411.07223-b31b1b.svg)](http://arxiv.org/abs/2411.07223) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://video-to-action.github.io/) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/video-to-action/video-to-action-release)\n- **Diffuser**, \"Planning with Diffusion for Flexible Behavior Synthesis\". [![arXiv](https://img.shields.io/badge/arXiv-2205.09991-b31b1b.svg)](http://arxiv.org/abs/2205.09991)\n- **Decision Diffuser**, \"Is Conditional Generative Modeling all you need for Decision-Making?\". [![arXiv](https://img.shields.io/badge/arXiv-2211.15657-b31b1b.svg)](http://arxiv.org/abs/2211.15657)\n- **Potential Based Diffusion Motion Planning**, \"Potential Based Diffusion Motion Planning\". [![arXiv](https://img.shields.io/badge/arXiv-2407.06169-b31b1b.svg)](http://arxiv.org/abs/2407.06169)\u003c!-- inserted --\u003e\n* **GRIM**: \"GRIM: Task-Oriented Grasping with Conditioning on Generative Examples\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=ICML.cc/2025/Workshop/World_Models#tab-accept) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://physical-world-modeling.github.io/)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **World4Omni**: \"World4Omni: A Zero-Shot Framework from Image Generation World Model to Robotic Manipulation\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=ICML.cc/2025/Workshop/World_Models#tab-accept) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://physical-world-modeling.github.io/)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **In-Context Policy Iteration**: \"In-Context Policy Iteration for Dynamic Manipulation\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=NeurIPS.cc/2025/Workshop/EWM#tab-accept-oral) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://embodied-world-models.github.io/)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **HDFlow**: \"HDFlow: Hierarchical Diffusion-Flow Planning for Long-horizon Robotic Assembly\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=NeurIPS.cc/2025/Workshop/EWM#tab-accept-oral) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://embodied-world-models.github.io/)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **Mobile Manipulation with Active Inference**: \"Mobile Manipulation with Active Inference for Long-Horizon Rearrangement Tasks\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=NeurIPS.cc/2025/Workshop/EWM#tab-accept-oral) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://embodied-world-models.github.io/)\n\u003c!-- end inserted --\u003e\n\n### 3. World Models for Navigation\n- [⭐️] **NWM**, \"Navigation World Models\". [![arXiv](https://img.shields.io/badge/arXiv-2412.03572-b31b1b.svg)](https://arxiv.org/abs/2412.03572) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://www.amirbar.net/nwm/)\n- [⭐️] **MindJourney**: \"MindJourney: Test-Time Scaling with World Models for Spatial Reasoning\". [![arXiv](https://img.shields.io/badge/arXiv-2507.12508-b31b1b.svg)](https://arxiv.org/abs/2507.12508) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://umass-embodied-agi.github.io/MindJourney)\u003c!-- inserted --\u003e\n* **Test-Time Scaling**: \"Test-Time Scaling with World Models for Spatial Reasoning\". [![arXiv](https://img.shields.io/badge/arXiv-2507.12508-b31b1b.svg)](https://arxiv.org/abs/2507.12508) [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=NeurIPS.cc/2025/Workshop/EWM#tab-accept-oral) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://umass-embodied-agi.github.io/MindJourney/)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **Scaling Inference-Time Search**: \"Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=ICLR.cc/2025/Workshop/World_Models#tab-accept) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://sites.google.com/view/worldmodel-iclr2025/accepted-papers)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **FalconWing**: \"FalconWing: An Ultra-Light Fixed-Wing Platform for Indoor Aerial Applications\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=NeurIPS.cc/2025/Workshop/EWM#tab-accept-oral) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://embodied-world-models.github.io/)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **Foundation Models as World Models**: \"Foundation Models as World Models: A Foundational Study in Text-Based GridWorlds\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=NeurIPS.cc/2025/Workshop/EWM#tab-accept-oral) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://embodied-world-models.github.io/)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **Geosteering Through the Lens of Decision Transformers**: \"Geosteering Through the Lens of Decision Transformers: Toward Embodied Sequence Decision-Making\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=NeurIPS.cc/2025/Workshop/EWM#tab-accept-oral) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://embodied-world-models.github.io/)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **Latent Weight Diffusion**: \"Latent Weight Diffusion: Generating reactive policies instead of trajectories\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=NeurIPS.cc/2025/Workshop/EWM#tab-accept-oral) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://embodied-world-models.github.io/)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **Abstract Sim2Real**: \"Abstract Sim2Real through Approximate Information States\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=NeurIPS.cc/2025/Workshop/EWM#tab-accept-oral) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://embodied-world-models.github.io/)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **FLAM**: \"FLAM: Scaling Latent Action Models with Factorization\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=NeurIPS.cc/2025/Workshop/EWM#tab-accept-oral) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://embodied-world-models.github.io/)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n- **NavMorph**: \"NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environments\". [![arXiv](https://img.shields.io/badge/arXiv-2506.23468-b31b1b.svg)](https://arxiv.org/abs/2506.23468) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/Feliciaxyao/NavMorph)\n- **Unified World Models**: \"Unified World Models: Memory-Augmented Planning and Foresight for Visual Navigation\". [![arXiv](https://img.shields.io/badge/arXiv-2510.08713-b31b1b.svg)](https://arxiv.org/abs/2510.08713) [[code](https://github.com/F1y1113/UniWM)]\n- **RECON**, \"Rapid Exploration for Open-World Navigation with Latent Goal Models\". [![arXiv](https://img.shields.io/badge/arXiv-2104.05859-b31b1b.svg)](http://arxiv.org/abs/2104.05859) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://sites.google.com/view/recon-robot)\n- **WMNav**: \"WMNav: Integrating Vision-Language Models into World Models for Object Goal Navigation\". [![arXiv](https://img.shields.io/badge/arXiv-2503.02247-b31b1b.svg)](https://arxiv.org/abs/2503.02247) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://b0b8k1ng.github.io/WMNav/)\n- **NaVi-WM**, \"Deductive Chain-of-Thought Augmented Socially-aware Robot Navigation World Model\". [![arXiv](https://img.shields.io/badge/arXiv-2510.23509-b31b1b.svg)](https://arxiv.org/abs/2510.23509) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://sites.google.com/view/NaviWM) \n- **AIF**, \"Deep Active Inference with Diffusion Policy and Multiple Timescale World Model for Real-World Exploration and Navigation\". [![arXiv](https://img.shields.io/badge/arXiv-2510.23258-b31b1b.svg)](https://arxiv.org/abs/2510.23258)\n- \"Kinodynamic Motion Planning for Mobile Robot Navigation across Inconsistent World Models\". [![arXiv](https://img.shields.io/badge/arXiv-2509.26339-b31b1b.svg)](https://arxiv.org/abs/2509.26339)\n- \"World Model Implanting for Test-time Adaptation of Embodied Agents\". [![arXiv](https://img.shields.io/badge/arXiv-2509.03956-b31b1b.svg)](https://arxiv.org/abs/2509.03956)\n- \"Imaginative World Modeling with Scene Graphs for Embodied Agent Navigation\". [![arXiv](https://img.shields.io/badge/arXiv-2508.06990-b31b1b.svg)](https://arxiv.org/abs/2508.06990)\n- [⭐️] **Persistent Embodied World Models**, \"Learning 3D Persistent Embodied World Models\". [![arXiv](https://img.shields.io/badge/arXiv-2505.05495-b31b1b.svg)](https://arxiv.org/abs/2505.05495)\n- \"Perspective-Shifted Neuro-Symbolic World Models: A Framework for Socially-Aware Robot Navigation\" [![arXiv](https://img.shields.io/badge/arXiv-2503.20425-b31b1b.svg)](https://arxiv.org/abs/2503.20425) \n- **X-MOBILITY**: \"X-MOBILITY: End-To-End Generalizable Navigation via World Modeling\". [![arXiv](https://img.shields.io/badge/arXiv-2410.17491-b31b1b.svg)](https://arxiv.org/abs/2410.17491)\n- **MWM**, \"Masked World Models for Visual Control\". [![arXiv](https://img.shields.io/badge/arXiv-2206.14244-b31b1b.svg)](http://arxiv.org/abs/2206.14244) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://sites.google.com/view/mwm-rl) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/younggyoseo/MWM)\n\n\n### 4. World Models for Locomotion\nLocomotion:\n- [⭐️] **Ego-VCP**, \"Ego-Vision World Model for Humanoid Contact Planning\". [![arXiv](https://img.shields.io/badge/arXiv-2510.11682-b31b1b.svg)](https://arxiv.org/abs/2510.11682) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://ego-vcp.github.io/) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/HybridRobotics/Ego-VCP)\n- [⭐️] **RWM-O**, \"Offline Robotic World Model: Learning Robotic Policies without a Physics Simulator\". [![arXiv](https://img.shields.io/badge/arXiv-2504.16680-b31b1b.svg)](https://arxiv.org/abs/2504.16680) \n- [⭐️] **DWL**: \"Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learning\". [![arXiv](https://img.shields.io/badge/arXiv-2408.14472-b31b1b.svg)](https://arxiv.org/abs/2408.14472)\n- **HRSSM**: \"Learning Latent Dynamic Robust Representations for World Models\". [![arXiv](https://img.shields.io/badge/arXiv-2405.06263-b31b1b.svg)](https://arxiv.org/abs/2405.06263) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/bit1029public/HRSSM)\n- **WMP**: \"World Model-based Perception for Visual Legged Locomotion\". [![arXiv](https://img.shields.io/badge/arXiv-2409.16784-b31b1b.svg)](https://arxiv.org/abs/2409.16784) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://wmp-loco.github.io/)\n- **TrajWorld**, \"Trajectory World Models for Heterogeneous Environments\". [![arXiv](https://img.shields.io/badge/arXiv-2502.01366-b31b1b.svg)](https://arxiv.org/abs/2502.01366) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/thuml/TrajWorld)\n- **Puppeteer**: \"Hierarchical World Models as Visual Whole-Body Humanoid Controllers\". [![arXiv](https://img.shields.io/badge/arXiv-2405.18418-b31b1b.svg)](https://arxiv.org/abs/2405.18418) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://nicklashansen.com/rlpuppeteer)\n- **ProTerrain**: \"ProTerrain: Probabilistic Physics-Informed Rough Terrain World Modeling\". [![arXiv](https://img.shields.io/badge/arXiv-2510.19364-b31b1b.svg)](https://arxiv.org/abs/2510.19364)\n- **Occupancy World Model**, \"Occupancy World Model for Robots\". [![arXiv](https://img.shields.io/badge/arXiv-2505.05512-b31b1b.svg)](https://arxiv.org/abs/2505.05512)\n- [⭐️] \"Accelerating Model-Based Reinforcement Learning with State-Space World Models\". [![arXiv](https://img.shields.io/badge/arXiv-2502.20168-b31b1b.svg)](https://arxiv.org/abs/2502.20168) \n- [⭐️] \"Learning Humanoid Locomotion with World Model Reconstruction\". [![arXiv](https://img.shields.io/badge/arXiv-2502.16230-b31b1b.svg)](https://arxiv.org/abs/2502.16230) \n- [⭐️] **Robotic World Model**: \"Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics. [![arXiv](https://img.shields.io/badge/arXiv-2501.10100-b31b1b.svg)](https://arxiv.org/abs/2501.10100)\n\n\nLoco-Manipulation:\n- [⭐️] **1X World Model**, 1X World Model. [![Blog](https://img.shields.io/badge/Blog-Link-orange)](https://www.1x.tech/discover/1x-world-model)\n- [⭐️] **GROOT-Dreams**, \"Dream Come True — NVIDIA Isaac GR00T-Dreams Advances Robot Training With Synthetic Data and Neural Simulation\". [![Blog](https://img.shields.io/badge/Blog-Link-orange)](https://blogs.nvidia.com/blog/nvidia-gtc-washington-dc-2025-news/#gr00t-dreams)\n- **Humanoid World Models**: \"Humanoid World Models: Open World Foundation Models for Humanoid Robotics\". [![arXiv](https://img.shields.io/badge/arXiv-2506.01182-b31b1b.svg)](https://arxiv.org/abs/2506.01182)  \n- **Ego-Agent**, \"EgoAgent: A Joint Predictive Agent Model in Egocentric Worlds\". [![arXiv](https://img.shields.io/badge/arXiv-2502.05857-b31b1b.svg)](https://arxiv.org/abs/2502.05857)\n- **D^2PO**, \"World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning\" [![arXiv](https://img.shields.io/badge/arXiv-2503.10480-b31b1b.svg)](https://arxiv.org/abs/2503.10480) \n- **COMBO**: \"COMBO: Compositional World Models for Embodied Multi-Agent Cooperation. [![arXiv](https://img.shields.io/badge/arXiv-2404.10775-b31b1b.svg)](https://arxiv.org/abs/2404.10775) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://vis-www.cs.umass.edu/combo/) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/UMass-Foundation-Model/COMBO)\u003c!-- inserted --\u003e\n* **Scalable Humanoid Whole-Body Control**: \"Scalable Humanoid Whole-Body Control via Differentiable Neural Network Dynamics\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=ICLR.cc/2025/Workshop/World_Models#tab-accept) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://sites.google.com/view/worldmodel-iclr2025/accepted-papers)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **HuWo**: \"HuWo: Building Physical Interaction World Models for Humanoid Robot Locomotion\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=ICLR.cc/2025/Workshop/World_Models#tab-accept) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://sites.google.com/view/worldmodel-iclr2025/accepted-papers)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **Bridging the Sim-to-Real Gap**: \"Bridging the Sim-to-Real Gap in Humanoid Dynamics via Learned Nonlinear Operators\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=NeurIPS.cc/2025/Workshop/EWM#tab-accept-oral) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://embodied-world-models.github.io/)\n\u003c!-- end inserted --\u003e\n\n### 5. World Models x VLAs\nUnifying World Models and VLAs in one model:\n- [⭐️] **CoT-VLA**: \"CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models\". [![arXiv](https://img.shields.io/badge/arXiv-2503.22020-b31b1b.svg)](https://arxiv.org/abs/2503.22020) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://cot-vla.github.io/)\n- [⭐️] **UP-VLA**, \"UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent\". [![arXiv](https://img.shields.io/badge/arXiv-2501.18867-b31b1b.svg)](https://arxiv.org/abs/2501.18867) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/CladernyJorn/UP-VLA)\n- [⭐️] **VPP**, \"Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations\". [![arXiv](https://img.shields.io/badge/arXiv-2412.14803-b31b1b.svg)](https://arxiv.org/abs/2412.14803) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://video-prediction-policy.github.io)\n- [⭐️] **FLARE**: \"FLARE: Robot Learning with Implicit World Modeling\". [![arXiv](https://img.shields.io/badge/arXiv-2505.15659-b31b1b.svg)](https://arxiv.org/abs/2505.15659) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/NVIDIA/Isaac-GR00T) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://research.nvidia.com/labs/gear/flare)\n- [⭐️] **MinD**: \"MinD: Unified Visual Imagination and Control via Hierarchical World Models\". [![arXiv](https://img.shields.io/badge/arXiv-2506.18897-b31b1b.svg)](https://arxiv.org/abs/2506.18897) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://manipulate-in-dream.github.io/)\n- [⭐️] **DreamVLA**, \"DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge\".  [![arXiv](https://img.shields.io/badge/arXiv-2507.04447-b31b1b.svg)](https://arxiv.org/abs/2507.04447) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/Zhangwenyao1/DreamVLA) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://zhangwenyao1.github.io/DreamVLA/)\n- [⭐️] **WorldVLA**: \"WorldVLA: Towards Autoregressive Action World Model\". [![arXiv](https://img.shields.io/badge/arXiv-2506.21539-b31b1b.svg)](https://arxiv.org/abs/2506.21539) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/alibaba-damo-academy/WorldVLA)\n- **3D-VLA**: \"3D-VLA: A 3D Vision-Language-Action Generative World Model\". [![arXiv](https://img.shields.io/badge/arXiv-2403.09631-b31b1b.svg)](https://arxiv.org/abs/2403.09631)\n- **LAWM**: \"Latent Action Pretraining Through World Modeling\". [![arXiv](https://img.shields.io/badge/arXiv-2509.18428-b31b1b.svg)](https://arxiv.org/abs/2509.18428) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/baheytharwat/lawm)\n- [⭐️] **UniVLA**: \"UniVLA: Unified Vision-Language-Action Model\". [![arXiv](https://img.shields.io/badge/arXiv-2506.19850-b31b1b.svg)](https://arxiv.org/abs/2506.19850) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://robertwyq.github.io/univla.github.)\n- [⭐️] **dVLA**, \"dVLA: Diffusion Vision-Language-Action Model with Multimodal Chain-of-Thought\". [![arXiv](https://img.shields.io/badge/arXiv-2509.25681-b31b1b.svg)](https://arxiv.org/abs/2509.25681)\n- [⭐️] **Vidar**, \"Vidar: Embodied Video Diffusion Model for Generalist Manipulation\". [![arXiv](https://img.shields.io/badge/arXiv-2507.12898-b31b1b.svg)](https://arxiv.org/pdf/2507.12898)\n- [⭐️] **UD-VLA**, \"Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denoising Diffusion Process\". [![arXiv](https://img.shields.io/badge/arXiv-2511.01718-b31b1b.svg)](https://arxiv.org/abs/2511.01718) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/OpenHelix-Team/UD-VLA) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://irpn-eai.github.io/UD-VLA.github.io/)\n- **Goal-VLA**: \"Goal-VLA: Image-Generative VLMs as Object-Centric World Models Empowering Zero-shot Robot Manipulation\". [![arXiv](https://img.shields.io/badge/arXiv-2506.23919-b31b1b.svg)](https://arxiv.org/abs/2506.23919) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://nus-lins-lab.github.io/goalvlaweb/)\n\n\nCombining World Models and VLAs:\n- [⭐️] **Ctrl-World**: \"Ctrl-World: A Controllable Generative World Model for Robot Manipulation\". [![arXiv](https://img.shields.io/badge/arXiv-2510.10125-b31b1b.svg)](https://arxiv.org/pdf/2510.10125) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://ctrl-world.github.io/) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/Robert-gyj/Ctrl-World)\n- **VLA-RFT**: \"VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulators\". [![arXiv](https://img.shields.io/badge/arXiv-2510.00406-b31b1b.svg)](https://arxiv.org/abs/2510.00406) \n- **World-Env**: \"World-Env: Leveraging World Model as a Virtual Environment for VLA Post-Training\". [![arXiv](https://img.shields.io/badge/arXiv-2509.24948-b31b1b.svg)](https://arxiv.org/abs/2509.24948) \n- [⭐️] **Self-Improving Embodied Foundation Models**, \"Self-Improving Embodied Foundation Models\". [![arXiv](https://img.shields.io/badge/arXiv-2509.15155-b31b1b.svg)](https://arxiv.org/abs/2509.15155)\n- **GigaBrain-0**, GigaBrain-0: A World Model-Powered Vision-Language-Action Model. [![arXiv](https://img.shields.io/badge/arXiv-2510.19430-b31b1b.svg)](https://arxiv.org/abs/2510.19430) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://gigabrain0.github.io/)\u003c!-- inserted --\u003e\n* **NinA**: \"NinA: Normalizing Flows in Action. Training VLA Models with Normalizing Flows\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=NeurIPS.cc/2025/Workshop/EWM#tab-accept-oral) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://embodied-world-models.github.io/)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **Ada-Diffuser**: \"Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=NeurIPS.cc/2025/Workshop/EWM#tab-accept-oral) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://embodied-world-models.github.io/)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **Steering Diffusion Policies**: \"Steering Diffusion Policies with Value-Guided Denoising\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=NeurIPS.cc/2025/Workshop/EWM#tab-accept-oral) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://embodied-world-models.github.io/)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **SPUR**: \"SPUR: Scaling Reward Learning from Human Demonstrations\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=NeurIPS.cc/2025/Workshop/EWM#tab-accept-oral) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://embodied-world-models.github.io/)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **A Smooth Sea Never Made a Skilled SAILOR**: \"A Smooth Sea Never Made a Skilled SAILOR: Robust Imitation via Learning to Search\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=NeurIPS.cc/2025/Workshop/EWM#tab-accept-oral) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://embodied-world-models.github.io/)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **RADI**: \"RADI: LLMs as World Models for Robotic Action Decomposition and Imagination\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=ICLR.cc/2025/Workshop/World_Models#tab-accept) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://sites.google.com/view/worldmodel-iclr2025/accepted-papers)\n- **WMPO**: \"WMPO: World Model-based Policy Optimization for Vision-Language-Action Models\". [![arXiv](https://img.shields.io/badge/arXiv-2511.09515-b31b1b.svg)](https://arxiv.org/abs/2511.09515) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://wm-po.github.io)\n\n\u003c!-- end inserted --\u003e\n\n### 6. World Models x Policy Learning\nThis subsection focuses on general policy learning methods in embodied intelligence via leveraging world models.\n- [⭐️] **UWM**, \"Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets\". [![arXiv](https://img.shields.io/badge/arXiv-2504.02792-b31b1b.svg)](https://arxiv.org/abs/2504.02792) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://weirdlabuw.github.io/uwm/)\n- [⭐️] **UVA**, Unified Video Action Model. [![arXiv](https://img.shields.io/badge/arXiv-2503.00200-b31b1b.svg)](https://arxiv.org/abs/2503.00200) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://unified-video-action-model.github.io/) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/ShuangLI59/unified_video_action)\n- **DiWA**, \"DiWA: Diffusion Policy Adaptation with World Models\". [![arXiv](https://img.shields.io/badge/arXiv-2508.03645-b31b1b.svg)](https://arxiv.org/abs/2508.03645) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://diwa.cs.uni-freiburg.de)\n- [⭐️] **Dreamerv4**, \"Training Agents Inside of Scalable World Models\". [![arXiv](https://img.shields.io/badge/arXiv-2509.24527-b31b1b.svg)](https://arxiv.org/abs/2509.24527) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://danijar.com/project/dreamer4/)\u003c!-- inserted --\u003e\n* **Latent Action Learning Requires Supervision**: \"Latent Action Learning Requires Supervision in the Presence of Distractors\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=ICLR.cc/2025/Workshop/World_Models#tab-accept) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://sites.google.com/view/worldmodel-iclr2025/accepted-papers)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **Beyond Experience**: \"Beyond Experience: Fictive Learning as an Inherent Advantage of World Models\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=NeurIPS.cc/2025/Workshop/EWM#tab-accept-oral) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://embodied-world-models.github.io/)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **Robotic World Model**: \"Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=NeurIPS.cc/2025/Workshop/EWM#tab-accept-oral) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://embodied-world-models.github.io/)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **Sim-to-Real Contact-Rich Pivoting**: \"Sim-to-Real Contact-Rich Pivoting via Optimization-Guided RL with Vision and Touch\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=NeurIPS.cc/2025/Workshop/EWM#tab-accept-oral) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://embodied-world-models.github.io/)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **Hierarchical Task Environments**: \"Hierarchical Task Environments as the Next Frontier for Embodied World Models in Robot Soccer\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=NeurIPS.cc/2025/Workshop/EWM#tab-accept-oral) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://embodied-world-models.github.io/)\n\u003c!-- end inserted --\u003e\n\n### 7. World Models for Policy evaluation\nReal-world policy evaluation is expensive and noisy. The promise of world models is by accurately capturing environment dynamics, it can serve as a surrogate evaluation environment with high correlation to the policy performance in the real world. Before world models, the role for that was simulators: \n- [⭐️] **Simpler**, \"Evaluating Real-World Robot Manipulation Policies in Simulation\". [![arXiv](https://img.shields.io/badge/arXiv-2405.05941-b31b1b.svg)](https://arxiv.org/abs/2405.05941) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/simpler-env/SimplerEnv)\n\nFor World Model Evaluation:\n- [⭐️] **WorldGym**, \"WorldGym: Evaluating Robot Policies in a World Model\". [![arXiv](https://img.shields.io/badge/arXiv-2506.00613-b31b1b.svg)](https://arxiv.org/abs/2506.00613) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://world-model-eval.github.io)\n- [⭐️] **WorldEval**: \"WorldEval: World Model as Real-World Robot Policies Evaluator\". [![arXiv](https://img.shields.io/badge/arXiv-2505.19017-b31b1b.svg)](https://arxiv.org/abs/2505.19017) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://worldeval.github.io)\n- [⭐️] **WoW!**: \"WOW!: World Models in a Closed-Loop World\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/pdf/e6aed49462d9e080633e727436cc95a0a8d61c57.pdf) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://wow202509.github.io/WOW_project_page/)\n- **Cosmos-Surg-dVRK**: \"Cosmos-Surg-dVRK: World Foundation Model-based Automated Online Evaluation of Surgical Robot Policy Learning\". [![arXiv](https://img.shields.io/badge/arXiv-2510.16240-b31b1b.svg)](https://arxiv.org/abs/2510.16240)\n---\n\n## World Models for Science\nNatural Science:\n\n- [⭐️] **CellFlux**, \"CellFlux: Simulating Cellular Morphology Changes via Flow Matching\". [![arXiv](https://img.shields.io/badge/arXiv-2502.09775-b31b1b.svg)](https://arxiv.org/abs/2502.09775)[![Website](https://img.shields.io/badge/Website-Link-blue)](https://yuhui-zh15.github.io/CellFlux/).\n- **CheXWorld**, \"CheXWorld: Exploring Image World Modeling for Radiograph Representation Learning\". [![arXiv](https://img.shields.io/badge/arXiv-2504.13820-b31b1b.svg)](http://arxiv.org/abs/2504.13820)[![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/LeapLabTHU/CheXWorld)\n- **EchoWorld**: \"EchoWorld: Learning Motion-Aware World Models for Echocardiography Probe Guidance\". [![arXiv](https://img.shields.io/badge/arXiv-2504.13065-b31b1b.svg)](https://arxiv.org/abs/2504.13065) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/LeapLabTHU/EchoWorld)\n- **ODesign**, \"ODesign: A World Model for Biomolecular Interaction Design.\" [![arXiv](https://img.shields.io/badge/arXiv-2510.22304-b31b1b.svg)](https://arxiv.org/pdf/2510.22304) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://odesign.lglab.ac.cn)\n- [⭐️] **SFP**, \"Spatiotemporal Forecasting as Planning: A Model-Based Reinforcement Learning Approach with Generative World Models\". [![arXiv](https://img.shields.io/badge/arXiv-2510.04020-b31b1b.svg)](https://arxiv.org/abs/2510.04020)\n- **Xray2Xray**, \"Xray2Xray: World Model from Chest X-rays with Volumetric Context\". [![arXiv](https://img.shields.io/badge/arXiv-2506.19055-b31b1b.svg)](https://arxiv.org/abs/2506.19055)\n- [⭐️] **Medical World Model**: \"Medical World Model: Generative Simulation of Tumor Evolution for Treatment Planning\". [![arXiv](https://img.shields.io/badge/arXiv-2506.02327-b31b1b.svg)](https://arxiv.org/abs/2506.02327)\n- **Surgical Vision World Model**, \"Surgical Vision World Model\". [![arXiv](https://img.shields.io/badge/arXiv-2503.02904-b31b1b.svg)](https://arxiv.org/abs/2503.02904) \n\nSocial Science:\n- **Social World Models**, \"Social World Models\". [![arXiv](https://img.shields.io/badge/arXiv-2509.00559-b31b1b.svg)](https://arxiv.org/abs/2509.00559)\n- \"Social World Model-Augmented Mechanism Design Policy Learning\". [![arXiv](https://img.shields.io/badge/arXiv-2510.19270-b31b1b.svg)](https://arxiv.org/abs/2510.19270)\n- **SocioVerse**, \"SocioVerse: A World Model for Social Simulation Powered by LLM Agents and A Pool of 10 Million Real-World Users\". [![arXiv](https://img.shields.io/badge/arXiv-2504.10157-b31b1b.svg)](http://arxiv.org/abs/2504.10157) [![Code](https://img.shields.io/badge/Code-GitHub-green)](https://github.com/FudanDISC/SocioVerse)\n\n\u003c!-- inserted --\u003e\n* **Effectively Designing 2-Dimensional Sequence Models**: \"Effectively Designing 2-Dimensional Sequence Models for Multivariate Time Series\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=ICLR.cc/2025/Workshop/World_Models#tab-accept) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://sites.google.com/view/worldmodel-iclr2025/accepted-papers)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **A Virtual Reality-Integrated System**: \"A Virtual Reality-Integrated System for Behavioral Analysis in Neurological Decline\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=ICLR.cc/2025/Workshop/World_Models#tab-accept) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://sites.google.com/view/worldmodel-iclr2025/accepted-papers)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **TwinMarket**: \"TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=ICLR.cc/2025/Workshop/World_Models#tab-accept) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://sites.google.com/view/worldmodel-iclr2025/accepted-papers)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **Latent Representation Encoding**: \"Latent Representation Encoding and Multimodal Biomarkers for Post-Stroke Speech Assessment\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=ICLR.cc/2025/Workshop/World_Models#tab-accept) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://sites.google.com/view/worldmodel-iclr2025/accepted-papers)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **Reconstructing Dynamics**: \"Reconstructing Dynamics from Steady Spatial Patterns with Partial Observations\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=ICLR.cc/2025/Workshop/World_Models#tab-accept) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://sites.google.com/view/worldmodel-iclr2025/accepted-papers)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **SP: Learning Physics from Sparse Observations**: \"SP: Learning Physics from Sparse Observations — Three Pitfalls of PDE-Constrained Diffusion Models\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=ICML.cc/2025/Workshop/World_Models#tab-accept) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://physical-world-modeling.github.io/)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **SP: Continuous Autoregressive Generation**: \"SP: Continuous Autoregressive Generation with Mixture of Gaussians\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=ICML.cc/2025/Workshop/World_Models#tab-accept) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://physical-world-modeling.github.io/)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **EquiReg**: \"EquiReg: Symmetry-Driven Regularization for Physically Grounded Diffusion-based Inverse Solvers\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=ICML.cc/2025/Workshop/World_Models#tab-accept) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://physical-world-modeling.github.io/)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **Neural Modular World Model**: \"Neural Modular World Model\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=ICML.cc/2025/Workshop/World_Models#tab-accept) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://physical-world-modeling.github.io/)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **Bidding for Influence**: \"Bidding for Influence: Auction-Driven Diffusion Image Generation\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=ICML.cc/2025/Workshop/World_Models#tab-accept) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://physical-world-modeling.github.io/)\n\u003c!-- end inserted --\u003e\n\u003c!-- inserted --\u003e\n* **PINT**: \"PINT: Physics-Informed Neural Time Series Models with Applications to Long-term Inference on WeatherBench 2m-Temperature Data\". [![OpenReview](https://img.shields.io/badge/OpenReview-Paper-8E44AD.svg)](https://openreview.net/group?id=ICLR.cc/2025/Workshop/World_Models#tab-accept) [![Website](https://img.shields.io/badge/Website-Link-blue)](https://sites.google.com/view/worldmodel-iclr2025/accepted-papers)\n\u003c!-- end inserted --\u003e\n\u003c!-- in","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fknightnemo%2FAwesome-World-Models","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fknightnemo%2FAwesome-World-Models","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fknightnemo%2FAwesome-World-Models/lists"}