KL for a KL: On-Policy Distillation with Control Variate Baseline
Paper • 2605.07865 • Published • 13
Heejae Suh
boribori
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 20 hours ago
KL for a KL: On-Policy Distillation with Control Variate Baseline upvoted a paper about 20 hours ago
Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States liked a model 2 months ago
openvla/openvla-7bOrganizations
None yet
upvoted 2
papers about 20 hours ago