The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 555
Atharv Das
atharvdas
·
AI & ML interests
Working on AI projects: transformers, datasets and fine-tuning.
Recent Activity
updated a model 7 days ago
atharvdas/poolformer-baseline published a model 7 days ago
atharvdas/poolformer-baselineOrganizations
None yet
upvoted a paper 7 days ago