Publications

• OC-Distill: Ontology-aware Contrastive Learning with Cross-Modal Distillation for ICU Risk Prediction
  Zhongyuan Liang, Junhyung Jo, Hyang-Jung Lee, Sang Kyu Kim, Irene Y. Chen.
  Under review, 2026

• Falsifying Sparse Autoencoder Reasoning Features in Language Models
  George Ma, Zhongyuan Liang, Irene Y. Chen, Somayeh Sojoudi.
  ICML, 2026

• Hybrid Meta-learners for Estimating Heterogeneous Treatment Effects
  Zhongyuan Liang, Lars van der Laan, Ahmed Alaa.
  AISTATS, 2026

• Local MDI+: Local Feature Importances for Tree-Based Models
  Zhongyuan Liang*, Zachary T. Rewolinski*, Abhineet Agarwal, Tiffany M. Tang, Bin Yu.
  TMLR, 2026

• Revealing Treatment Non-Adherence Bias in Clinical Machine Learning Using Large Language Models
  Zhongyuan Liang, Arvind Suresh, Irene Y. Chen.
  CHIL, 2025

• A Learning Based Hypothesis Test for Harmful Covariate Shift
  Tom Ginsberg, Zhongyuan Liang, Rahul G. Krishnan.
  ICLR, 2023