About Me

Hi! I’m Langzhou He, a second-year Ph.D. student in Big Data and Social Computing (BDSC) Lab at the University of Illinois Chicago. I’m fortunate to be advised by Prof. Philip S. Yu. I obtained my B.S. degree in Computer Science with honors from Southwest University, where I worked closely with Prof. Li Tao and Prof. Chao Gao.

My research interests primarily lie in machine learning, LLms and Agentic RL. My current research focuses on the fundamental challenges of generative AI, specifically addressing model hallucinations and optimizing inference efficiency. By developing principled frameworks for relational data, I strive to create robust and efficient autonomous agents for high-stakes scientific research.

News

  • 02/2026: One paper ACTOR-CURATOR is online. Check this out!
  • 12/2025: One benchmark paper RECODE-H has been accepted to ICLR 2026. Congrats to all collaborators!
  • 10/2025: One paper NSGNN has been accepted to IEEE TKDE. Congrats to all collaborators!
  • 09/2025: Our paper “Can Molecular Foundation Models Know What They Don’t Know?” is online. Check this out!
  • 05/2025: One paper SDMG has been accepted to ICML 2025. Congrats to all collaborators!

Selected Publications

In Submission
sym

Can Molecular Foundation Models Know What They Don’t Know? A Simple Remedy with Preference Optimization

Langzhou He, Junyou Zhu, Fangxin Wang, Haoyan Xu, Junhua Liu, Yue Zhao, Philip S. Yu, Qitian Wu

In Submission | arXiv

ICML 2025
sym

SDMG: Smoothing Your Diffusion Models for Powerful Graph Representation Learning

Junyou Zhu, Langzhou He, Chao Gao, Dongpeng Hou, Zhen Su, Philip S. Yu, Juergen Kurths, Frank Hellmann

ICML 2025 | Paper | Code

IEEE TKDE
sym

Network Measure-Enriched GNNs: A New Framework for Power Grid Stability Prediction

Junyou Zhu, Christian Nauck, Michael Lindner, Langzhou He, Philip Yu, Klaus-Robert Mueller, Jürgen Kurths, Frank Hellmann

IEEE Transactions on Knowledge and Data Engineering (TKDE) | Paper | Code

Honors

  • 2024: Outstanding Graduates
  • 2023: First-tier Scholarship, Innovation and Entrepreneurship Award
  • 2022: Academic Science Award
  • 2021: Merit Student of University, Second-tier Scholarship

Services

  • Conference Reviewer:
    • NeurIPS 2024, 2025
    • ICLR 2024, 2025, 2026, FM-Wild@ICLR 2024
    • ICML 2025, 2026
    • PDLM@AAAI 2025
  • Journal Reviewer:
    • IEEE Transactions on Neural Networks and Learning Systems
    • IEEE Transactions on Knowledge and Data Engineering

Misc