On-Policy Parameter Update Direction Underlies Generalization in LLM Post-Training
Paper • 2609.36659 • Published • 83
Mila He
milahe6755
AI & ML interests
None yet
Recent Activity
upvoted a paper 2 days ago
On-Policy Parameter Update Direction Underlies Generalization in LLM Post-Training upvoted a paper 7 days ago
Raven: The Harness of Harnesses for Composable Agentic Intelligence upvoted a paper 8 days ago
MassAlloc Attention: Let Attention Allocate Its Own ComputeOrganizations
None yet