The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 415
Marie S. Mueller
mariemmm3
·
AI & ML interests
multimodal, recommendation systems
Recent Activity
updated a model about 12 hours ago
mariemmm3/tiny-transformer-contrastive published a model about 12 hours ago
mariemmm3/tiny-transformer-contrastive liked a model about 12 hours ago
autotrust/JEV-27B-VLOrganizations
None yet
upvoted 2
papers 5 days ago