John's picture

John

johnhan00

·

https://jongwook-han.github.io

AI & ML interests

Pluralistic value alignment

Recent Activity

upvoted a paper 4 days ago

Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States

upvoted a paper 4 days ago

KL for a KL: On-Policy Distillation with Control Variate Baseline

commentedon a paper 23 days ago

ThinkBrake: Efficient Reasoning via Log-Probability Margin Guided Decoding

View all activity

Organizations

models 0

None public yet

datasets 0

None public yet