SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
Paper
•
2506.01844
•
Published
•
141
•
28
Suhwan Choi
MilkClouds
AI & ML interests
None yet
Recent Activity
authored
a paper
25 days ago
Revisiting Residual Connections: Orthogonal Updates for Stable and
Efficient Deep Networks
authored
a paper
25 days ago
D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to
Embodied AI
authored
a paper
25 days ago
ESREAL: Exploiting Semantic Reconstruction to Mitigate Hallucinations in
Vision-Language Models
Organizations
Hi, how did you trained this model?
#2 opened 5 months ago
by
MilkClouds
commented
a
paper
5 months ago
[WARNING for everyone] image_observation is NOT IMAGE, it is frame-stacked 4 grayscale images
2
#3 opened over 1 year ago
by
MilkClouds
[WARNING for everyone] image_observation is NOT IMAGE, it is frame-stacked 4 grayscale images
2
#3 opened over 1 year ago
by
MilkClouds