Research

Research Interests

My research interests focus on multimodal representation learning and causal inference, with an emphasis on building scalable, reliable, and decision-focused machine learning systems for real-world applications. In particular, my work emphasizes:

• Causal Learning
• Efficient AI: Efficient Reasoning and Efficient Token Use
• Causal Inference
• Multimodal representation learning
• Evidence-Based Auto Research

Working Papers and Publications

• A path-specific effect approach to mediation analysis with time-varying mediators and time-to-event outcomes accounting for competing risks
  Arce Domingo-Relloso, Yuchen Zhang, Ziqing Wang, Astrid M. Suchy-Dicey, Dedra S. Buchwald, Ana Navas-Acien, Joel Schwartz, Kiros Berhane, Brent A. Coull, Linda Valeri.
  Statistics in Medicine, 45(3-5), e70425
  Statistics in Medicine.

MELON: Multimodal Learning Framework for Spatial Multimodal Omics Data Integration
Yuchen Zhang, Chunru Lin, Liuqing Yang, Yuying Xie, Yu Shen, Lulu Shang.
ICML 2026 AI4Science, Poster.

• The Role of Coronary Artery Calcification in Metal-Related Cardiovascular Disease
  Arce Domingo-Relloso, Katlyn E. McGraw, Irene Martinez-Morata, Yuchen Zhang, Kathrin Schilling, Ronald A. Glabonjat, Ziqing Wang, Kiros Berhane, Brent A. Coull, Marta Galvez-Fernandez, Miranda R. Jones, Wendy S. Post, Joel Kaufman, Tiffany R. Sanchez, Maria Tellez-Plaza, Graham R. Barr, Steven Shea, Ana Navas-Acien, Linda Valeri.
  Environment International, 110095
  Environment International.

Uncovering the features of industrial odors-derived environmental complaints and proactive countermeasures by using machine learning
H. Xiao, J. Tian, Y. Chen, C. Wang, Y. Zhang, L. Chen.
Journal of Environmental Management, 370, 122900.