The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 579
Jason Davis
jasondavi
·
AI & ML interests
Interested in machine learning, NLP and open source AI.
Recent Activity
updated a model 3 days ago
jasondavi/hybrid-matching published a model 3 days ago
jasondavi/hybrid-matching liked a model 3 days ago
autotrust/JEV-9BOrganizations
None yet