Ke Xu

k.xu@yale.edu

Department of Computer Science

Yale University

New Haven, CT

I am a PhD student in Computer Science at Yale University, co-advised by Prof. Mark Gerstein and Prof. Smita Krishnaswamy. I received my MPH in Biostatistics from Yale and my BS in Mathematics from the University of Wisconsin–Madison.

My research centers on machine learning and statistical methods for sequential and dynamical data, spanning methods, theory, and applications. On the methods side, I work with continuous-time generative models (flow matching, neural ODEs/SDEs, diffusion models), sequence models (transformers, state-space models), optimal transport, and multi-agent systems. On the theory side, I am interested in the statistical and approximation-theoretic foundations of these models, particularly under irregular or sparse observation regimes. On the applications side, I work primarily in computational biology and medicine: multi-omics time-series, single-cell genomics, cellular interaction dynamics, and longitudinal medical imaging.

news

Sep 01, 2025	Our paper STAGED is accepted at MLCB 2025 (PMLR).
Jul 01, 2025	Our paper ChronODE is published in Nature Communications! Read it here.
May 01, 2025	Presented a poster on ChronODE at the Biology of Genomes meeting at Cold Spring Harbor Laboratory.
Apr 01, 2025	Our paper ImageFlowNet is accepted at IEEE ICASSP 2025.
Jan 01, 2025	Serving as a reviewer for ICLR 2025.

selected publications

MLCB

STAGED: A Multi-Agent Neural Network for Learning Cellular Interaction Dynamics

João Felipe Rocha^*, Ke Xu^*, Xinran Sun^*, and 6 more authors

In Machine Learning in Computational Biology (MLCB), 2025

arXiv Bib

@inproceedings{rocha2025staged,
  title = {STAGED: A Multi-Agent Neural Network for Learning Cellular Interaction Dynamics},
  author = {Rocha, Jo{\~a}o Felipe and Xu, Ke and Sun, Xinran and Krishna, Adi and Bhaskar, Dhananjay and Mongeon, Beatrice and Craig, Michael and Gerstein, Mark and Krishnaswamy, Smita},
  booktitle = {Machine Learning in Computational Biology (MLCB)},
  year = {2025},
  publisher = {PMLR},
}

ICASSP

ImageFlowNet: Forecasting Multiscale Image-Level Trajectories of Disease Progression

Corey Liu^*, Ke Xu^*, Luca Liebeskind Shen^&dagger;, and 8 more authors

In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025

arXiv Bib

@inproceedings{liu2025imageflownet,
  title = {ImageFlowNet: Forecasting Multiscale Image-Level Trajectories of Disease Progression},
  author = {Liu, Corey and Xu, Ke and Shendagger;, Luca Liebeskind and Huguetdagger;, Guillaume and Wang, Ziyang and Tong, Alexander and Bzdok, Danilo and Stewart, Jay and Wang, Jia Cheng and Del Priore, Lucian V. and Krishnaswamy, Smita},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  year = {2025},
}

Nat Commun

The chronODE Framework for Modelling Multi-Omic Time Series with Ordinary Differential Equations and Machine Learning

Beatrice Borsari^*, Matthew Frank^*, Eric S. Wattenberg^&dagger;, and 4 more authors

Nature Communications, 2025

Bib HTML

@article{borsari2025chronode,
  title = {The chronODE Framework for Modelling Multi-Omic Time Series with Ordinary Differential Equations and Machine Learning},
  author = {Borsari, Beatrice and Frank, Matthew and Wattenbergdagger;, Eric S. and Xudagger;, Ke and Liudagger;, Sherry X. and Yu, Xinchen and Gerstein, Mark},
  journal = {Nature Communications},
  volume = {16},
  pages = {7021},
  year = {2025},
}