About Me
I’m a Ph.D. student in MIT EECS, advised by Caroline Uhler. My research focuses on establishing statistical and algorithmic foundations for discovery and decision-making within systems created by underlying causal rules. In particular, I develop tools to understand causal relationships from data, model and extrapolate to predict the effects of interventions, and select informative interventions for experimental design. Motivated by problems in cell biology, these tools help accelerate mechanistic discovery and translation to biomedical engineering.
My research has been supported by the Eric and Wendy Schmidt Center PhD Fellowship and the Apple Scholarship. I was a research intern at Byedance, Microsoft Research, and Apple. I obtained my Bachelor’s degree in Mathematics from Peking University, where I worked with Zaiwen Wen, Mengdi Wang, and Le Cong.
News
- Dec., 2025 (upcoming). We are organizing a NeurIPS2025 workshop on Uncovering Causality in Science (CauScien). Check out the topics and join us!
- Jul., 2025. We organized an ICML2025 workshop on Scaling up Intervention Models (SIM). Check out the talks and accepted papers.
- Jul., 2025. How to more efficiently study complex treatment interaction: MIT news covered our work on experimental design.
- Nov., 2024. A causal theory for studying the cause-and-effect relationships of genes: MIT news covered our work on causal theory.
- Oct., 2023. A more effective experimental design for engineering a cell into a new state: MIT news covered our work on active learning in causal models. Read also on EWSC news.
Papers
Preprints
MORPH Predicts the Single-cell Outcome of Genetic Perturbations across Various Data Modalities
Chujun He*, Jiaqi Zhang*, Munther Dahleh, Caroline Uhler.
[bioRxiv]
[code]
[bibtex]
On the Number of Conditional Indepdence Tests in Constraint-based Causal Discovery
Marc Franquesa Monés$^\dagger$*, Jiaqi Zhang*, Caroline Uhler.
Learning Genetic Perturbation Effects with Variational Causal Inference
Emily Liu$^\dagger$*, Jiaqi Zhang*, Caroline Uhler.
[bioRxiv]
[code]
[bibtex]
Faithfulness and Intervention-Only Causal Discovery
Bijan Mazaheri, Jiaqi Zhang, Caroline Uhler.
[workshop]
Meta-Dependence in Conditional Independence Testing
Bijan Mazaheri, Jiaqi Zhang, Caroline Uhler.
[arXiv]
[code]
[bibtex]
Publications
Can Diffusion Models Disentangle? A Theoretical Perspective
Liming Wang, Muhammad Jehanzeb Mirza, Yishu Gong, Yuan Gong, Jiaqi Zhang, Brian H. Tracey, Katerina Placek, Marco Vilela, James R. Glass. NeurIPS, 2025.
Probabilistic Factorial Experimental Design for Combinatorial Interventions
Divyal Shyamal$^\dagger$*, Jiaqi Zhang*, Caroline Uhler. ICML (Spotlight, < 2.6%), 2025.
[arXiv]
[conference]
[bibtex]
Identifiabiltiy Guarantees of Causal Disentanglement from Purely Observational Data
Ryan Welch$^\dagger$*, Jiaqi Zhang*, Caroline Uhler. NeurIPS, 2024.
[arXiv]
[code]
[conference]
[bibtex]
Causal Discovery with Fewer Conditional Independence Tests
Kirankumar Shiragur*, Jiaqi Zhang*, Caroline Uhler. ICML, 2024.
[arXiv]
[code]
[bibtex]
Towards Causal Foundation Model: on Duality between Causal Inference and Attention
Jiaqi Zhang*, Joel Jennings, Agrin Hilmkil, Nick Pawlowski, Cheng Zhang, Chao Ma*. ICML, 2024.
[arXiv]
[code]
[bibtex]
Membership Testing in Markov Equivalence Classes via Independence Query Oracles
Jiaqi Zhang*, Kirankumar Shiragur*, Caroline Uhler. AISTATS (Oral Presentation, <3%), 2024.
[arXiv]
[conference]
[bibtex]
Meek Separators and Their Applications in Targeted Causal Discovery
Kirankumar Shiragur*, Jiaqi Zhang*, Caroline Uhler. NeurIPS, 2023.
[arXiv]
[code]
[conference]
[bibtex]
Identifiability Guarantees for Causal Disentanglement from Soft Interventions
Jiaqi Zhang, Kristjan Greenewald, Chandler Squires, Akash Srivastava, Karthikeyan Shanmugam, Caroline Uhler. NeurIPS, 2023.
[arXiv]
[code]
[conference]
[bibtex]
Active Learning for Optimal Intervention Design in Causal Models
Jiaqi Zhang, Louis Cammarata, Chandler Squires, Themistoklis P Sapsis, Caroline Uhler. Nature Machine Intelligence, 2023.
[arXiv]
[code]
[journal]
[bibtex]
Machine-learning-optimized Cas12a Barcoding Enables the Recovery of Single-cell Lineages and Transcriptional Profiles
Nicholas W Hughes, Yuanhao Qu*, Jiaqi Zhang*, Weijing Tang*, Justin Pierce*, Chengkun Wang, Aditi Agrawal, Maurizio Morri, Norma Neff, Monte M Winslow, Mengdi Wang, Le Cong. Molecular Cell, 2022.
[code]
[journal]
[bibtex]
Stochastic Augmented Projected Gradient Methods for the Large-Scale Precoding Matrix Indicator Selection Problem
Jiaqi Zhang, Zeyu Jin, Bo Jiang, Zaiwen Wen. IEEE Transactions on Wireless Communications, 2022.
[journal]
[bibtex]
Matching a Desired Causal State via Shift Interventions
Jiaqi Zhang, Chandler Squires, Caroline Uhler. NeurIPS, 2021.
[arXiv]
[code]
[conference]
[bibtex]