Skip to main content
Context Awesome

awesome-vla-post-training

github.com/aoqunjin/awesome-vla-post-training ↗

A collection of vision-language-action model post-training methods.

257
GitHub Stars
209
Curated Resources
6
Categories
23 hours ago
Last Refreshed
:star: Notable Works:earth_asia: Enhancing Environmental Perception:brain: Improving Embodiment Awareness:memo: Deepening Task Comprehension:wrench: Multiple Component Integration:clipboard: Survey

Use this list with your AI agent

Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:

"Show me visual interaction prediction resources from awesome-vla-post-training"

Installation instructions →

What's inside

Resources

:wrench: Multiple Component Integration

  • PaperVisual Interaction Prediction

  • PaperVisual Interaction Prediction

  • PaperActive Dataset Processing

  • PaperReinforcement Learning

  • PaperReinforcement Learning

  • PaperReinforcement Learning

:star: Notable Works

:brain: Improving Embodiment Awareness

  • PaperAction Head Designing

  • PaperForward and Inverse kinematics learning

  • PaperForward and Inverse kinematics learning

  • PaperForward and Inverse kinematics learning

  • PaperForward and Inverse kinematics learning

  • PaperAction Head Designing

:earth_asia: Enhancing Environmental Perception

  • PaperAffordance-Guided Learning

  • PaperAffordance-Guided Learning

  • PaperAffordance-Guided Learning

  • PaperAffordance-Guided Learning

  • PaperAffordance-Guided Learning

  • PaperAffordance-Guided Learning

:memo: Deepening Task Comprehension

  • PaperHierarchical Task Manipulation

  • PaperHuman–Robot-Interaction

  • PaperHuman–Robot-Interaction

  • PaperHuman–Robot-Interaction

  • PaperHuman–Robot-Interaction

  • PaperHuman–Robot-Interaction

Showing a sample of 209 resources. View the full list on GitHub →