Peking University · CS PhD Candidate

Hongcheng Wang

I am a fourth-year CS PhD candidate at Peking University. My supervisor is Prof. Hao Dong.

My current research interests are organized into two parts:

  • Chain-of-thought Generation: I study reinforcement-learning post-training for large models, especially how to stably train <think> to better guide <answer>.
  • Human-centered Robot Decision Making: I take a Cognitive Behavioral Theory's perspective to enable robots to understand human cognition (e.g., latent demands and preferences) and behavior (e.g., observable habits and norms), so they can better serve people.

Blog

Education

Research

My current work has two main directions: (1) chain-of-thought generation for large models, and (2) cognitively grounded, human-centered robot decision making in embodied settings, where robots model human demands, preferences, habits, and norms to provide better assistance.

Services

  • ICRA (2023), Reviewer
  • IROS (2024), Reviewer
  • NeurIPS (2024, 2025), Reviewer
  • ACM MM (2025), Reviewer
  • ICLR (2025, 2026), Reviewer
  • ICML (2025, 2026), Reviewer
  • RA-L (2026), Reviewer

Teaching Assistant

  • Fundamentals of Artificial Intelligence, Spring (2023, 2024, 2025, 2026)
  • Introduction to Computation (A), Fall 2025