{"data":{"slug":"activevisionlab-awesome-llm-3d","name":"Awesome-LLM-3D","tagline":"Curated list of Multi-modal Large Language Model resources for 3D world tasks","github_url":"https://github.com/ActiveVisionLab/Awesome-LLM-3D","owner":"ActiveVisionLab","repo":"Awesome-LLM-3D","owner_avatar_url":"https://avatars.githubusercontent.com/u/21082947?v=4","primary_language":null,"stars":2233,"forks":142,"topics":[],"archived":false,"github_pushed_at":"2026-04-16T16:28:04+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/activevisionlab-awesome-llm-3d","markdown_url":"https://www.graphcanon.com/tools/activevisionlab-awesome-llm-3d.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/activevisionlab-awesome-llm-3d","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=activevisionlab-awesome-llm-3d","description":"Awesome-LLM-3D: a curated list of Multi-modal Large Language Model in 3D world  Resources","homepage_url":null,"license":"MIT","open_issues":7,"watchers":56,"ai_summary":"Awesome-LLM-3D is a meticulously curated list focusing on multi-modal large language models (LLMs) within the 3D domain. It encompasses a comprehensive range from foundational LLM-driven applications to cutting-edge benchmarks in areas like unified understanding, reasoning, and embodied agents.","readme_excerpt":"# Awesome-LLM-3D     <a href=\"\" target='_blank'><img src=\"https://visitor-badge.laobi.icu/badge?page_id=activevisionlab.llm3d&left_color=gray&right_color=blue\"> </a> \n\n<div align=\"center\">\n    <img src=\"assets/Figure1_v8_25.6.9.png\" width=\"100%\">\n</div>\n\n\n\n## 🏠 About\nHere is a curated list of papers about 3D-Related Tasks empowered by Large Language Models (LLMs). \nIt contains various tasks including 3D understanding, reasoning, generation, and embodied agents. Also, we include other Foundation Models (CLIP, SAM) for the whole picture of this area.\n\nThis is an active repository, you can watch for following the latest advances. If you find it useful, please kindly star ⭐ this repo and [cite](#citation) the paper.\n\n## 🔥 News\n- [2026-03-20] Our benchmark paper **Real-3DQA** is now available at ICLR 2026! Following our survey paper, we now release the benchmark paper on genuine 3D spatial understanding. [Project Page](https://real-3dqa.github.io/)\n- [2025-10-21] 📢 We have released the **second version** of our survey, updated to include literature up to **July 2025**:  \n👉 [*When LLMs Step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models*](https://arxiv.org/pdf/2405.10255v2)\n- [2024-05-16] Check out the first survey paper in the 3D-LLM domain: [When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models](https://arxiv.org/pdf/2405.10255) \n- [2024-01-06] [Runsen Xu](https://runsenxu.com/) added chronological information and [Xianzheng Ma](https://xianzhengma.github.io/) reorganized it in Z-A order for better following the latest advances.\n- [2023-12-16] [Xianzheng Ma](https://xianzhengma.github.io/) and [Yash Bhalgat](https://yashbhalgat.github.io/) curated this list and published the first version;\n\n## Table of Contents\n\n- [Awesome-LLM-3D](#awesome-llm-3D)\n  - [3D Unified Understanding and Generation (LLM)](#3d-unified-understanding-and-generation-via-llm)\n  - [3D Understanding (LLM)](#3d-understanding-via-llm)\n  - [3D Understanding (other Foundation Models)](#3d-understanding-via-other-foundation-models)\n  - [3D Reasoning](#3d-reasoning)\n  - [3D Generation](#3d-generation)\n  - [3D Embodied Agent](#3d-embodied-agent)\n  - [3D Benchmarks](#3d-benchmarks)\n  - [Contributing](#contributing)\n\n\n## 3D Unified Understanding and Generation via LLM\n\n|  Date |       Keywords       |    Institute (first)   | Paper                                                                                                                                                                               | Publication | Others |\n| :-----: | :------------------: | :--------------: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :---------: | :---------:\n| 2025-11-07 | Omni-View | PKU | [Omni-View: Unlocking How Generation Facilitates Understanding in Unified 3D Model based on Multiview images](https://arxiv.org/abs/2511.07222) | ICLR 2026 | [github](https://github.com/AIDC-AI/Omni-View) |\n| 2025-08-16 | UniUGG | FDU | [UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding](https://arxiv.org/abs/2508.11952) | ICLR 2026 | [github](https://github.com/fudan-zvg/UniUGG) |\n\n## 3D Understanding via LLM\n\n|  Date |       Keywords       |    Institute (first)   | Paper                                                                                                                                                                               | Publication | Others |\n| :-----: | :------------------: | :--------------: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :---------: | :---------:\n| 2026-03-07 | 3D-RFT | BIGAI | [3D-RFT: Reinforcement Fine-Tuning for Video-based 3D Scene Unde","github_created_at":"2023-12-15T06:02:44+00:00","created_at":"2026-07-11T10:33:06.235013+00:00","updated_at":"2026-07-11T11:16:08.47049+00:00","categories":[{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"},{"slug":"computer-vision","name":"Computer Vision","url":"https://www.graphcanon.com/categories/computer-vision","markdown_url":"https://www.graphcanon.com/categories/computer-vision.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/computer-vision"}],"tags":[{"slug":"3d-understanding","name":"3d understanding"},{"slug":"generation","name":"generation"},{"slug":"embodied-agents","name":"embodied agents"},{"slug":"reasoning","name":"reasoning"},{"slug":"foundation-models","name":"foundation-models"}],"trust":{"provenance":{"is_fork":false,"github_id":731892810,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-11T10:33:06.783Z","maintenance":{"label":"Steady","score":60,"methodology":"github_public_v1","releases_90d":0,"days_since_push":85,"last_release_at":null},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T10:33:07.407Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-11T11:15:30.213Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-07-11T11:15:30.213Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["- This repository does not require Docker or specific dependencies. It is a curated list of resources intended for researchers and developers interested in the "],"requires_docker":false},"constraints":{"requires_docker":false},"when_to_use":["- When you are looking for specific and updated information on how LLMs can be applied to various 3D tasks like understanding, generation, and embodied agents.","- If your project requires benchmarking in spatial understanding using multi-modal LLMs; the repository includes recent advancements like the 'Real-3DQA' benchmark paper."],"when_not_to_use":["- If you are seeking real-time applications or tools for immediate use case deployment rather than a curated list of research papers and resources.","- Avoid if your focus is on more general computer vision tasks that do not specifically involve multi-modal LLMs within the 3D domain."],"source":"enrich:decision_facts","observed_at":"2026-07-11T11:16:08.202Z"},"constraint_facets":{"requires_docker":false},"decision_summary":[{"label":"Requirements","value":"- This repository does not require Docker or specific dependencies. It is a curated list of resources intended for researchers and developers interested in the "},{"label":"Adopt for","value":"Awesome-LLM-3D is a curated list of multi-modal large language model resources dedicated to tasks in the 3D domain, including areas such as unified understanding, reasoning, and embodied agents."},{"label":"License detail","value":"The tool is licensed under MIT, allowing free use for both personal and commercial projects with appropriate attribution."}]}}