The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 548
नेहा कुमार
riykuma98
·
AI & ML interests
just here for the models
Recent Activity
updated a model 14 days ago
riykuma98/deit-classification published a model 14 days ago
riykuma98/deit-classification liked a model 14 days ago
autotrust/JEV-27B-VLOrganizations
None yet
upvoted a paper 14 days ago