On-Policy Parameter Update Direction Underlies Generalization in LLM Post-Training
Paper • 2609.36659 • Published • 87
Robin He
robinhe8939
AI & ML interests
None yet
Recent Activity
upvoted a paper 11 days ago
On-Policy Parameter Update Direction Underlies Generalization in LLM Post-TrainingOrganizations
None yet
upvoted a paper 11 days ago