The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 578
Krish E. Gupta
krishgna7809
·
AI & ML interests
Building AI products for the enterprise
Recent Activity
liked a dataset 4 days ago
gmongaras/Stable_Diffusion_3_Recaption liked a Space 4 days ago
mihretgold/Steering_Vision_Language_Models_with_Subjective_Concepts liked a model 4 days ago
Edge0/Audio8-ASR-InfiniteOrganizations
None yet
upvoted 2
papers 4 days ago