gson-pi

AI & ML interests

None defined yet.

Recent Activity

talzoomanzoo  authored a paper 6 days ago

Self-Improvement with Auxiliary Rewards: Learning from Verified Traces and Evaluating Transfer

talzoomanzoo  submitted a paper 7 days ago

Self-Improvement with Auxiliary Rewards: Learning from Verified Traces and Evaluating Transfer

talzoomanzoo  authored a paper 5 months ago

Web-Shepherd: Advancing PRMs for Reinforcing Web Agents

View all activity

Team members 3