# jonyzhang2023/awesome-embodied-vla-va-vln

A curated list of state-of-the-art research in embodied AI, focusing on vision-language-action (VLA) models, vision-language navigation (VLN), and related multimodal learning approaches.

Repository: https://github.com/jonyzhang2023/awesome-embodied-vla-va-vln
Canonical: https://ross.abutalabs.com/products/awesome-embodied-vla-va-vln
License Family: other
Last push: 2026-08-07T12:31:28+00:00

## Health v2 (maintenance only)
Score: 64/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 96, release rhythm 35, longevity 42
- inputs: {"age_days": 594, "days_push": 26, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3481, forks 165 (observed 2026-08-28T04:08:06.842784+00:00)

## What it is
A curated awesome-list of 700+ state-of-the-art research papers and resources in embodied AI, covering Vision-Language-Action (VLA) models, World-Action Models (WAM), Vision-Language Navigation (VLN), Vision-Action (VA) models, and MLLM-based embodied learning. It organizes papers by topic including surveys, sim-to-real transfer, physics-aware policies, benchmarks, and simulators, and is continuously updated by the community.

## Use cases
- find state-of-the-art papers on vision-language-action models for robotics
- survey research on vision-language navigation and embodied AI
- discover benchmarks and simulators for robot learning
- keep up with new VLA and world model papers for robot manipulation
- find resources on sim-to-real transfer and diffusion policies for robots
- research multimodal LLM approaches to embodied reasoning and planning

## When to choose
- you need a comprehensive, continuously updated index of embodied AI research papers
- you are surveying VLA, VLN, or world-action model literature for a project or thesis
- you want curated pointers to benchmarks, simulators, and related awesome lists in robot learning

## When to avoid
- you need runnable code or a software library rather than a paper index
- you want a single framework or model implementation instead of a curated reading list
- you need production tooling for robot deployment

## Facets
- artifact type: learning-resource
- maturity: active
- function: documentation, machine-learning, deep-learning, robotics, nlp, computer-vision, simulation, benchmarking
- domain: artificial-intelligence, machine-learning, robotics, computer-vision, simulation, awesome-lists, tutorials
- platform: cross-platform
- tags: awesome-list, embodied-ai, vision-language-action, vision-language-navigation, vla, vln, world-models, robot-learning, multimodal-learning, sim-to-real-transfer, diffusion-policy, research-papers, curated-list, natural-language-processing

## Member repositories
- jonyzhang2023/awesome-embodied-vla-va-vln (main) score 64

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:06.842784+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 2026-08-29T18:36:27.069402+00:00, confidence not recorded.
  - readme: https://github.com/jonyzhang2023/awesome-embodied-vla-va-vln (fetched 2026-08-28T04:08:06.842784+00:00, sha 10de5e5e251e)
- Data as of 2026-08-30T08:39:29.467469+00:00.