Recovering Reliable Supervision via Critique-Guided On-Policy Distillation
Paper • 2610.20572 • Published • 77
Tomasz G. Wisniewski
tpwisn-iewski
·
AI & ML interests
model evaluation
Recent Activity
upvoted a paper 1 day ago
Recovering Reliable Supervision via Critique-Guided On-Policy Distillation updated a model 13 days ago
tpwisn-iewski/mocov3-baseline published a model 13 days ago
tpwisn-iewski/mocov3-baselineOrganizations
None yet
upvoted a paper 1 day ago
upvoted 3
papers 13 days ago
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents
Paper • 2609.39102 • Published • 665
Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It
Paper • 2609.36585 • Published • 72
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 564