The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 168
Mateo Torres
michaelwrightwyn
·
AI & ML interests
Love fine-tuning models and sharing datasets.
Recent Activity
updated a model about 1 month ago
michaelwrightwyn/flamingo-finetuned published a model about 1 month ago
michaelwrightwyn/flamingo-finetunedOrganizations
None yet