Manifold Drift in Flow Preference Optimization: A Root Cause of Reward Hacking
Paper • 2608.20011 • Published • 2
🤝 Open to Collab
yansenhan
yansenhan
AI & ML interests
None yet
Recent Activity
upvoted a paper 3 days ago
Manifold Drift in Flow Preference Optimization: A Root Cause of Reward Hacking upvoted a paper 8 months ago
QwenLong-L1.5: Post-Training Recipe for Long-Context Reasoning and Memory ManagementOrganizations
None yet
upvoted a paper 3 days ago