Hugging Face's logo
sungjiblim's picture
3 1

sungjiblim

sungzip
ยท

AI & ML interests

None yet

Recent Activity

upvoted a paper 6 days ago
Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States
upvoted a paper 6 days ago
KL for a KL: On-Policy Distillation with Control Variate Baseline
upvoted a paper 23 days ago
ThinkBrake: Efficient Reasoning via Log-Probability Margin Guided Decoding
View all activity

Organizations

Robust-Safety-Alignment's profile picture