S N

Refinath

19

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 16 days ago

iSDFT: Information-Proximal Self-Distillation for Continual Learning in LLMs

upvoted a paper 16 days ago

Beam Search as Test-Time Self-Distillation via Counterfactual Contexts

upvoted a paper 16 days ago

The Weakest Link: Distilling LLM Reasoning with Worst-Case Constrained Reinforcement Learning

View all activity

Organizations

models 0

None public yet

datasets 24

Refinath/so101_cube_top_cookies_to_drawer_cleaned

SO-101 • Updated Jul 29 • 101 episodes • 40

Refinath/so101_cube_top_bbox_to_drawer_cleaned

SO-101 • Updated Jul 29 • 104 episodes • 24

Refinath/so101_cube_cookies_to_rect_cleaned

SO-101 • Updated Jul 29 • 101 episodes • 35

Refinath/so101_cube_blue_box_to_rect_cleaned

SO-101 • Updated Jul 29 • 103 episodes • 67

Refinath/so101_cube_drawer_to_bbox_cleaned

SO-101 • Updated Jul 29 • 101 episodes • 37

Refinath/so101_cube_between_to_drawer_cleaned

SO-101 • Updated Jul 29 • 101 episodes • 37

Refinath/so101_bowl_top_drawer_to_rect_cleaned

SO-101 • Updated Jul 29 • 101 episodes • 36

Refinath/so101_bowl_top_cookies_to_bbox_cleaned

SO-101 • Updated Jul 29 • 101 episodes • 30

Refinath/so101_bowl_top_bbox_to_drawer_cleaned

SO-101 • Updated Jul 29 • 96 episodes • 43

Refinath/so101_bowl_yellow_rect_to_bbox_cleaned

SO-101 • Updated Jul 29 • 103 episodes • 36

View 24 datasets