# ActiveVisionLab/Awesome-LLM-3D

Awesome-LLM-3D: a curated list of Multi-modal Large Language Model in 3D world  Resources

Repository: https://github.com/ActiveVisionLab/Awesome-LLM-3D
Canonical: https://ross.abutalabs.com/products/awesome-llm-3d
License: MIT
License Family: permissive
Last push: 2026-04-16T16:28:04+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 77, release rhythm 35, longevity 70
- inputs: {"age_days": 992, "days_push": 139, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2253, forks 142 (observed 2026-08-28T04:06:31.086073+00:00)

## What it is
A curated awesome-list of papers and resources on multi-modal large language models applied to 3D tasks, accompanying a survey paper. It covers 3D understanding, reasoning, generation, embodied agents, and benchmarks.

## Use cases
- find papers on 3D scene understanding with LLMs
- research 3D generation using large language models
- survey embodied AI agents in 3D worlds
- find benchmarks for 3D spatial reasoning
- keep up with latest 3D-LLM research
- find foundation models like SAM and CLIP for 3D tasks

## When to choose
- you need a literature review of LLM-based 3D research
- you are starting research in 3D multi-modal learning
- you want a maintained, chronological paper list with a companion survey

## When to avoid
- you need runnable code or a library rather than a paper list
- you want a dataset or benchmark itself rather than links to papers

## Facets
- artifact type: learning-resource
- maturity: active
- function: documentation, machine-learning, nlp, computer-vision
- domain: artificial-intelligence, large-language-models, computer-vision, awesome-lists, tutorials
- platform: -
- tags: awesome-list, 3d, llm, survey, curated-papers, embodied-agents, 3d-understanding, 3d-generation, web-server

## Member repositories
- ActiveVisionLab/Awesome-LLM-3D (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:31.086073+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:43:47.157760+00:00, confidence not recorded.
  - readme: https://github.com/ActiveVisionLab/Awesome-LLM-3D (fetched 2026-08-28T04:06:31.086073+00:00, sha d321c48e0bb3)
- Data as of 2026-08-30T08:39:29.467469+00:00.