pith. sign in

Ziji Zhang

Identifiers

  • name variant Ziji Zhang 0.60 · backfill

Papers (2)

  1. Adaptive Layerwise Perturbation: Unifying Off-Policy Corrections for LLM RL cs.LG · 2026 · author #5
  2. Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training cs.LG · 2025 · author #3

Mentions

  • 2603.19470 #5 · arxiv_oai · confidence 0.70 Ziji Zhang
  • 2509.03403 #3 · arxiv_oai · confidence 0.70 Ziji Zhang

Frequent Coauthors