Offline-RL

AI & ML interests

None defined yet.

Recent Activity

shizhuo2  submitted a paper 3 days ago

Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning

shizhuo2  authored a paper over 1 year ago

$\textbf{Only-IF}$:Revealing the Decisive Effect of Instruction Diversity on Generalization

shizhuo2  authored a paper over 1 year ago

Instruction Diversity Drives Generalization To Unseen Tasks

View all activity

Team members 1