sungjiblim's picture

4 1

sungjiblim

sungzip

·

sungzip

AI & ML interests

None yet

Recent Activity

upvoted a paper about 21 hours ago

Where Should Diffusion Enter a Language Model? Geometry-Guided Hidden-State Replacement

upvoted a paper 8 days ago

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

upvoted a paper 8 days ago

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

View all activity

Organizations

upvoted a paper about 21 hours ago

Where Should Diffusion Enter a Language Model? Geometry-Guided Hidden-State Replacement

Paper • 2605.14368 • Published 5 days ago • 11

upvoted 2 papers 8 days ago

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

Paper • 2605.07579 • Published 11 days ago • 16

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

Paper • 2605.07865 • Published 11 days ago • 19

upvoted a paper 25 days ago

ThinkBrake: Efficient Reasoning via Log-Probability Margin Guided Decoding

Paper • 2510.00546 • Published 29 days ago • 14