NVlabs/vla0
vla0
VLA-0: Building State-of-the-Art VLAs with Zero Modification
Builder
NVlabs
NVlabs • individual
Stars
465
Using upstream star count
Forks
26
Using upstream fork count
Open Issues
0
Activity Score
0/100
0 commits in 30d
Created
Oct 14, 2025
Project creation date
README Summary
VLA-0 is a framework for building state-of-the-art Vision-Language-Action (VLA) models that can be trained and deployed without requiring any modifications to existing codebases. It provides a unified interface for training multimodal models that can understand visual inputs, process natural language instructions, and generate appropriate robotic actions.
AI Dev Skills
Unmapped
roboticscomputer-visionnatural-language-processingmachine-learningmultimodal-ai
Tags
roboticscomputer-visionnatural-language-processingmachine-learningmultimodal-aipytorchtransformersrobotic-manipulation
Taxonomy
Modalities
Recent Activity
Updated 1 months ago
7 Days
0
30 Days
0
90 Days
0
Quality
research- Quality
- high
- Maturity
- research
Categories
Multimodal AIPrimaryDev Tools & AutomationFoundation ModelsModel TrainingComputer VisionRoboticsOther AI / ML
PM Skills
Developer Platform
Languages
Python100.0%
Timeline
- Project created
- Oct 14, 2025
- Forked
- Mar 31, 2026
- Your last push
- 1 months ago
- Upstream last push
- 1 months ago
- Tracked since
- Feb 21, 2026
Similar Repos
pgvector cosine similarity · $0
Loading…