pith. sign in

Dingyan Shang

Identifiers

  • name variant Dingyan Shang 0.60 · backfill

Papers (2)

  1. Self-Commitment Latency: A Reward-Free Probe for Prompted Implicit Hacking cs.AI · 2026 · author #3
  2. When LLM Reward Design Fails: Diagnostic-Driven Refinement for Sparse Structured RL cs.LG · 2026 · author #5

Mentions

  • 2606.05625 #3 · arxiv_oai · confidence 0.70 Dingyan Shang
  • 2605.28918 #5 · arxiv_oai · confidence 0.70 Dingyan Shang

Frequent Coauthors