The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 418
许秀英
chenclaire9
·
AI & ML interests
Interested in machine learning, NLP and open source AI.
Recent Activity
updated a model 2 days ago
chenclaire9/matching-ablation published a model 2 days ago
chenclaire9/matching-ablationOrganizations
None yet