Jin-Hong Du

Jin-Hong Du

Assistant Professor at the University of Hong Kong

Welcome to Jin-Hong's Homepage

I am an HKU-100 Assistant Professor at the University of Hong Kong, beginning in Fall 2025. I hold joint appointments in the Department of Statistics and Actuarial Science (SAAS) and the Musketeers Foundation Institute of Data Science (IDS).

I earned my Ph.D. in Statistics and Machine Learning from Carnegie Mellon University, advised by Professor Kathryn Roeder and Professor Larry Wasserman. Previously, I obtained an M.S. in Statistics from the University of Chicago, advised by Professor Lek-Heng Lim, and a B.S. in Statistics from Sun Yat-sen University.

🔍 Research interests

Statistical methods for
  • 📊 Causal inference
  • 🤖 Interpretable machine learning
  • 🌐 Statistical network analysis
Applications in
  • 🧬 Single-cell multiomics
  • 🧪 CRISPR perturbation analysis
  • 💬 Large language model (LLM) evaluation

🔔 Updates

  • 2026/10 📢 I am recruiting 1 PhD student (Fall 2027) with experience in single-cell/spatial omics and/or medical imaging (CT/MRI). See the Prospective Students page for details.
  • 2026/09 🎓 Our paper ''Heterogeneous Judge-Aware Ranking with Sensitivity, Disagreement, and Confidence'' has been accepted by NeurIPS 2026! 🎉
  • 2026/09 📋 I will serve as an Area Chair for ICLR 2027.
  • 2026/03 🎓 Our paper ''Effects of distance metrics and scaling on the perturbation discrimination score'' has been accepted as oral presentation by ICLR 2026 Workshop on Generative AI in Genomics (Gen²): Barriers and Frontiers! 🎉
  • 2026/01 🎓 Our paper ''Flow-Disentangled feature importance'' has been accepted by ICLR 2026! 🎉
  • 2025/12 🎓 Our paper ''Assumption-lean post-integrated inference with surrogate control outcomes'' has been accepted by Biometrika! 🎉
  • 2025/12 🎉 In collaboration with researchers from UChicago and Dartmouth, our team Outlier secured 3rd place 🥉 in The First Virtual Cell Challenge! Huge thanks to everyone who contributed to this amazing achievement! 🚀
  • 2025/09 🏆 I will receive the IMS Lawrence D. Brown Ph.D. Student Award and present paper Disentangled Feature Importance at the 2026 IMS Annual Meeting. 🌟