The reviewed record of science sign in
Pith

Bill Wu

Identifiers

  • name variant Bill Wu 0.60 · backfill

Papers (2)

  1. Averaging log-likelihoods in direct alignment cs.LG · 2024 · author #5
  2. Contrastive Policy Gradient: Aligning LLMs on sequence-level scores in a supervised-friendly fashion cs.LG · 2024 · author #4

Mentions

  • 2406.19185 #4 · arxiv_oai · confidence 0.70 Bill Wu
  • 2406.19188 #5 · arxiv_oai · confidence 0.70 Bill Wu

Frequent Coauthors