Hyeongjin Kim

madokalif's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper about 1 month ago

Human Psychometric Questionnaires Mischaracterize LLM Behavior

Paper • 2509.10078 • Published May 29 • 36

upvoted 2 papers 2 months ago

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

Paper • 2605.07579 • Published May 8 • 18

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

Paper • 2605.07865 • Published May 8 • 22