SAF-OPD: Stable Advantage Fusion for On-Policy Distillation
Paper • 2607.29209 • Published • 34
Hande Huang
Timiduck
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 8 days ago
SAF-OPD: Stable Advantage Fusion for On-Policy DistillationOrganizations
None yet