Ryan Tanaka

ryantanakawyn

2

·

AI & ML interests

Reinforcement learning is my therapy

Recent Activity

updated a model 9 days ago

ryantanakawyn/review-data-efficient-learning5

published a model 9 days ago

ryantanakawyn/review-data-efficient-learning5

upvoted a paper 9 days ago

The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation

View all activity

Organizations

None yet

models 2

ryantanakawyn/review-data-efficient-learning5

49.6k • Updated 9 days ago • 21

ryantanakawyn/classification-exp

33.1k • Updated 14 days ago • 22

datasets 2

ryantanakawyn/document-ocr-image-audio-benchmark

Updated Sep 13 • 11

ryantanakawyn/hw2-retriever

Updated Aug 25 • 10