Ryo Yamamoto

ryoyamamotoina

3

·

AI & ML interests

Exploring deep learning, computer vision and LLMs.

Recent Activity

updated a dataset 23 days ago

ryoyamamotoina/news-media-samples

published a dataset 23 days ago

ryoyamamotoina/news-media-samples

upvoted a paper 23 days ago

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

View all activity

Organizations

None yet

upvoted 2 papers 23 days ago

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

Paper • 2609.36484 • Published Sep 29 • 179

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

Paper • 2609.39102 • Published Sep 30 • 158

upvoted a paper about 2 months ago

Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments

Paper • 2609.04148 • Published Sep 3 • 81