pith. sign in

Garry Yang

Identifiers

  • name variant Garry Yang 0.60 · backfill

Papers (2)

  1. Hista and Numca: Estimate State Value Effectively for LLM Reinforcement Learning cs.LG · 2026 · author #4
  2. Knowing but Not Correcting: Routine Task Requests Suppress Factual Correction in LLMs cs.LG · 2026 · author #5

Mentions

  • 2605.29782 #4 · arxiv_oai · confidence 0.70 Garry Yang

Frequent Coauthors