pith. sign in

John D Co-Reyes

Identifiers

  • name variant John D Co-Reyes 0.60 · backfill

Papers (1)

  1. Training Language Models to Self-Correct via Reinforcement Learning cs.LG · 2024 · author #5

Mentions

  • 2409.12917 #5 · arxiv_oai · confidence 0.70 John D Co-Reyes

Frequent Coauthors