pith. sign in

Tianhao Cheng

Identifiers

  • name variant Tianhao Cheng 0.60 · backfill

Papers (4)

  1. The Cancellation Hypothesis in Critic-Free RL: From Outcome Rewards to Token Credits cs.LG · 2026 · author #1
  2. UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning cs.AI · 2025 · author #95
  3. Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling cs.LG · 2025 · author #2
  4. SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines cs.CL · 2025 · author #40

Mentions

  • 2507.01679 #2 · arxiv_oai · confidence 0.70 Tianhao Cheng
  • 2502.14739 #40 · arxiv_oai · confidence 0.70 Tianhao Cheng

Frequent Coauthors