The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 574
吴欣怡
Zhouko52
·
AI & ML interests
Working on AI projects: transformers, datasets and fine-tuning.
Recent Activity
updated a model 5 days ago
Zhouko52/mocov3-checkpoint published a model 5 days ago
Zhouko52/mocov3-checkpointOrganizations
None yet
upvoted 4
papers 5 days ago
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks
Paper • 2609.38288 • Published • 139
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents
Paper • 2609.39102 • Published • 478
MaLiang-Harness: A Programmable Path to Image and Video Generation
Paper • 2609.34309 • Published • 412