ActiveVisionLab/Awesome-LLM-3D
A curated paper list covering multi-modal LLMs applied to 3D understanding, reasoning, generation, and embodied agent tasks.
Not currently ranked — collecting fresh signals.
star history
This repository maintains a comprehensive collection of academic papers on large language models operating in 3D environments. It catalogs research across multiple task categories including 3D scene understanding, spatial reasoning, 3D content generation, and embodied AI agents. The list also incorporates foundation models like CLIP and SAM to provide broader context on the field. The repository is actively maintained with regular updates tracking the latest advances through 2025.
Frequently asked
- What is ActiveVisionLab/Awesome-LLM-3D?
- A curated paper list covering multi-modal LLMs applied to 3D understanding, reasoning, generation, and embodied agent tasks.
- Is Awesome-LLM-3D open source?
- Yes — ActiveVisionLab/Awesome-LLM-3D is open source, released under the MIT license.
- How popular is Awesome-LLM-3D?
- ActiveVisionLab/Awesome-LLM-3D has 2.2k stars on GitHub.
- Where can I find Awesome-LLM-3D?
- ActiveVisionLab/Awesome-LLM-3D is on GitHub at https://github.com/ActiveVisionLab/Awesome-LLM-3D.