SAF-OPD: Stable Advantage Fusion for On-Policy Distillation
Paper • 2607.29209 • Published • 34
Tao Gao
moralCompass
·
AI & ML interests
cryptocurrency
Recent Activity
upvoted a paper 28 days ago
SAF-OPD: Stable Advantage Fusion for On-Policy Distillation authored a paper over 1 year ago
AI-native Memory 2.0: Second Me upvoted a paper over 1 year ago
AI-native Memory 2.0: Second MeOrganizations
None yet