KL for a KL: On-Policy Distillation with Control Variate Baseline
Paper • 2605.07865 • Published • 13
gyubin choi
gyubinc
AI & ML interests
None yet
Recent Activity
upvoted a paper about 11 hours ago
KL for a KL: On-Policy Distillation with Control Variate Baseline updated a model about 1 year ago
gyubinc/Mistral-7B-Instruct-v3-EMMET1000_zsre published a model about 1 year ago
gyubinc/Mistral-7B-Instruct-v3-EMMET1000_zsreOrganizations
None yet
upvoted a paper about 11 hours ago