The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 556
Simon Jones II
Kaur3081
·
AI & ML interests
inference optimization, mechanistic interpretability, data engineering, machine learning, anomaly detection
Recent Activity
upvoted a paper 1 day ago
VisionHOPE: Visual Backbones as Self-Modifying Learning Systems updated a model 6 days ago
Kaur3081/dino-baselineOrganizations
None yet
upvoted 2
papers 1 day ago
updated a
model 6 days ago
published a
model 6 days ago
liked a
model 6 days ago
