pith. sign in

Hanshan Zhang

Identifiers

  • name variant Hanshan Zhang 0.60 · backfill

Papers (3)

  1. Predictable Scale: Part I, Step Law -- Optimal Hyperparameter Scaling Law in Large Language Model Pretraining cs.LG · 2025 · author #4
  2. Energy-Based Preference Model Offers Better Offline Alignment than the Bradley-Terry Preference Model cs.LG · 2024 · author #2
  3. Uncertainty Sentence Sampling by Virtual Adversarial Perturbation cs.CL · 2022 · author #1

Mentions

  • 2503.04715 #4 · arxiv_oai · confidence 0.70 Hanshan Zhang
  • 2412.13862 #2 · arxiv_oai · confidence 0.70 Hanshan Zhang
  • 2210.14576 #1 · arxiv_oai · confidence 0.70 Hanshan Zhang

Frequent Coauthors