SAF-OPD: Stable Advantage Fusion for On-Policy Distillation
Paper • 2607.29209 • Published • 22
hanser Jiang
PSG-LGD-ame
AI & ML interests
None yet
Recent Activity
upvoted a paper about 5 hours ago
SAF-OPD: Stable Advantage Fusion for On-Policy Distillation upvoted a paper 9 months ago
ReCode: Unify Plan and Action for Universal Granularity Control upvoted a paper about 1 year ago
SWE-Factory: Your Automated Factory for Issue Resolution Training Data
and Evaluation BenchmarksOrganizations
