The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 511
Ashley Martinez
ashleymartinez
·
AI & ML interests
multimodal, summarization, edge computing, model evaluation, autonomous driving
Recent Activity
upvoted a paper about 9 hours ago
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents updated a model 4 days ago
ashleymartinez/tiny-transformer-classificationOrganizations
None yet