jonyzhang2023/awesome-embodied-vla-va-vln
A curated collection of 700+ research papers on embodied AI models including vision-language-action (VLA), world-action models (WAM), and vision-language navigation (VLN) systems.
Not currently ranked — collecting fresh signals.
star history
This repository aggregates state-of-the-art research in embodied AI, specifically covering vision-language-action models that enable robots to reason and act from visual and language inputs. It catalogs work on vision-language navigation tasks, diffusion-based action policies, and MLLM-driven robotic planning systems. The collection includes survey papers, model architectures, and benchmarking resources across the embodied AI research space.
Frequently asked
- What is jonyzhang2023/awesome-embodied-vla-va-vln?
- A curated collection of 700+ research papers on embodied AI models including vision-language-action (VLA), world-action models (WAM), and vision-language navigation (VLN) systems.
- Is awesome-embodied-vla-va-vln open source?
- Yes — jonyzhang2023/awesome-embodied-vla-va-vln is an open-source project tracked on heatdrop.
- How popular is awesome-embodied-vla-va-vln?
- jonyzhang2023/awesome-embodied-vla-va-vln has 3.3k stars on GitHub.
- Where can I find awesome-embodied-vla-va-vln?
- jonyzhang2023/awesome-embodied-vla-va-vln is on GitHub at https://github.com/jonyzhang2023/awesome-embodied-vla-va-vln.