Tanaka Ryan

Schmidtphilipp

4 2

·

AI & ML interests

Former physicist, now doing ML

Recent Activity

upvoted a paper 1 day ago

False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents

upvoted a paper 1 day ago

The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation

upvoted a paper 1 day ago

UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement

View all activity

Organizations

None yet

upvoted 3 papers 1 day ago

False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents

Paper • 2609.39102 • Published 3 days ago • 256

The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation

Paper • 2609.36484 • Published 4 days ago • 341

UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement

Paper • 2609.38721 • Published 3 days ago • 273

upvoted a paper 29 days ago

Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments

Paper • 2609.04148 • Published 30 days ago • 248