5 5 4

Francesco Capuano

fracapuano

https://fracapuano.github.io

AI & ML interests

Deep Reinforcement Learning, Deep NLP

Recent Activity

updated a dataset 12 days ago

fracapuano/smolvla_finetuned_stacking_action_chunks_20k

published a dataset 12 days ago

fracapuano/smolvla_finetuned_stacking_action_chunks_20k

updated a dataset 12 days ago

fracapuano/smolvla_finetuned_stacking_action_chunks_15k

View all activity

Organizations

upvoted an article 23 days ago

Article

Weekly Robotics June #1 - SmolVLA discovery and thoughts

•

23 days ago

• 9

upvoted a paper 24 days ago

SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics

Paper • 2506.01844 • Published 25 days ago • 103

upvoted an article 24 days ago

Article

SmolVLA: Efficient Vision-Language-Action Model trained on Lerobot Community Data

and 8 others •

24 days ago

• 166

upvoted 2 articles 5 months ago

Article

π0 and π0-FAST: Vision-Language-Action Models for General Robot Control

and 3 others •

Feb 4

• 166

Article

Mastering Tensor Dimensions in Transformers

•

Jan 12

• 73

Francesco Capuano

AI & ML interests

Recent Activity

Organizations

fracapuano's activity

Weekly Robotics June #1 - SmolVLA discovery and thoughts

SmolVLA: Efficient Vision-Language-Action Model trained on Lerobot Community Data

π0 and π0-FAST: Vision-Language-Action Models for General Robot Control

Mastering Tensor Dimensions in Transformers