Sangjun Song's picture

5 1

Sangjun Song

ssangjun706

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 5 days ago

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

upvoted a paper 5 days ago

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

upvoted a paper 24 days ago

In-N-Out: A Parameter-Level API Graph Dataset for Tool Agents

View all activity

Organizations

None yet

upvoted 2 papers 5 days ago

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

Paper • 2605.07865 • Published 9 days ago • 17

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

Paper • 2605.07579 • Published 9 days ago • 15

upvoted 2 papers 24 days ago

In-N-Out: A Parameter-Level API Graph Dataset for Tool Agents

Paper • 2509.01560 • Published Dec 30, 2025 • 4

ThinkBrake: Efficient Reasoning via Log-Probability Margin Guided Decoding

Paper • 2510.00546 • Published 27 days ago • 14

upvoted an article 25 days ago

Article

Everything You Need to Know about Knowledge Distillation

Kseniase

•

Mar 6, 2025

• 80

liked a model 6 months ago

allenai/Olmo-3-7B-Think

Text Generation • 528k • Updated Jan 5 • 149k • 94