keivalya/mini-vla
a minimal, beginner-friendly VLA to show how robot policies can fuse images, text, and states to generate actions
This project helps robotics students and researchers understand how to build models that enable robots to follow instructions. It takes robot sensor data (images, internal state) and text commands, then outputs continuous actions for the robot to perform. This is for anyone learning or prototyping robot control policies, particularly those interested in vision-language-action (VLA) models.
204 stars.
Use this if you are a student or researcher looking for a clear, minimalist example to learn or prototype vision-language-action models for robotics.
Not ideal if you need a production-ready, state-of-the-art robot control system or a robust solution for real-world industrial applications.
Stars
204
Forks
40
Language
Python
License
MIT
Category
Last pushed
Mar 17, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/keivalya/mini-vla"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
UCSC-VLAA/story-iter
[ICLR 2026] A Training-free Iterative Framework for Long Story Visualization
PaddlePaddle/PaddleMIX
Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks,...
adobe-research/custom-diffusion
Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)
byliutao/1Prompt1Story
🔥ICLR 2025 (Spotlight) One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation...
zai-org/ImageReward
[NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation