PRIME-RL/SimpleVLA-RL
SimpleVLA-RL
[ICLR 2026] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
Builder
PRIME-RL
PRIME-RL • individual
Stars
1,549
Using upstream star count
Forks
95
Using upstream fork count
Open Issues
0
Activity Score
0/100
0 commits in 30d
Created
May 25, 2025
Project creation date
README Summary
SimpleVLA-RL is a research project that scales Vision-Language-Action (VLA) model training through reinforcement learning techniques. The repository contains the implementation for a paper accepted to ICLR 2026, focusing on improving VLA training efficiency and performance using RL methods.
AI Dev Skills
Unmapped
roboticsvision-language-actionreinforcement-learningmultimodal-learningmodel-training
Tags
roboticsvision-language-actionreinforcement-learningmultimodal-learningmodel-trainingscalingcomputer-visionnatural-language-processingpytorchmachine-learning
Taxonomy
Recent Activity
Updated 3 months ago
7 Days
0
30 Days
0
90 Days
0
Quality
research- Quality
- high
- Maturity
- research
Categories
Dev Tools & AutomationPrimaryRoboticsMultimodal AIOther AI / MLFoundation ModelsModel TrainingComputer Vision
PM Skills
Developer Platform
Languages
Python100.0%
Timeline
- Project created
- May 25, 2025
- Forked
- Mar 31, 2026
- Your last push
- 3 months ago
- Upstream last push
- 3 months ago
- Tracked since
- Jan 6, 2026
Similar Repos
pgvector cosine similarity · $0
Loading…