SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
Paper
•
2506.01844
•
Published
•
94
Dakota Kim PRO
GhostScientist
AI & ML interests
Reasoning, Self-Modeling, Embodied intelligence / Robotics
Recent Activity
liked
a dataset
about 2 hours ago
LeRobot-worldwide-hackathon/335-MadWatch-Knock_Down_The_Box
updated
a dataset
about 2 hours ago
LeRobot-worldwide-hackathon/335-MadWatch-Knock_Down_The_Box
published
a dataset
about 4 hours ago
LeRobot-worldwide-hackathon/335-MadWatch-Knock_Down_The_Box
Organizations
GhostScientist's activity
upvoted
a
paper
6 days ago
upvoted
an
article
6 days ago
Article
SmolVLA: Efficient Vision-Language-Action Model trained on Lerobot Community Data
By
and 8 others
•
•
137