KL for a KL: On-Policy Distillation with Control Variate Baseline
Paper • 2605.07865 • Published • 22
gyubin choi
gyubinc
AI & ML interests
None yet
Recent Activity
published a model 20 days ago
gyubinc/sciq published a model 20 days ago
gyubinc/gsm8k published a model 20 days ago
gyubinc/tacoOrganizations
None yet
upvoted a paper 29 days ago