Ellie Haber

ehaber at andrew.cmu.edu

I am a PhD student at the Machine Learning Department of Carnegie Mellon University, where I am advised by Professor Jian Ma. Previously, I obtained my B.S. in Computer Science at NYU, and I also spent time Columbia and MIT Lincoln Laboratory.

profile photo

Research Interests

I am broadly interested in building toward a “virtual cell”—computational models that can faithfully capture, simulate, and reason about cellular behavior across contexts. My work focuses on spatial transcriptomics and representation learning, with the goal of developing robust, generalizable spatial representations that span platforms and experimental settings, enabling comparisons of cell states, tissues, and microenvironments. I am also interested in perturbation prediction and, more generally, in understanding the mechanisms, inductive biases, and failure modes of single-cell foundation models so that their representations can be used not just for prediction, but for generating insight into underlying cellular processes.

Selected Papers

* equal contribution, † corresponding author

heimdall
HEIMDALL: A Modular Framework for Tokenization in Single-Cell Foundation Models
Ellie Haber*, Shahul Alam*, Nicholas Ho*, Renming Liu, Evan Trop, Shaoheng Liang, Muyu Yang, Spencer Krieger†, Jian Ma†
bioRxiv, 2025
LLOKI
Unified integration of spatial transcriptomics across platforms with LLOKI
Ellie Haber, Ajinkya Deshpande, Jian Ma†, Spencer Krieger†
Genome Research, 2025  | 

Early version in Proceedings of the 29th Annual Conference on Research in Computational Molecular Biology (RECOMB), 2025.

Eykthyr
EYKTHYR reveals transcriptional regulators of spatial gene programs
Spencer Krieger, Ellie Haber, Jian Ma
bioRxiv, 2025
Popari
POPARI: Modeling multisample variation in spatial transcriptomics
Shahul Alam, Tianming Zhou, Ellie Haber, Benjamin Chidester, Sophia Liu, Fei Chen, Jian Ma
bioRxiv, 2025
Optimizing MobileNet Algorithms for Real-time Vessel Detection on Smartphones
Lars A. Gjesteby, Ellie Haber, Shoyo Hakozaki, Alec Xu, Nancy DeLosa, Benjamin Roop, Joshua Werblin, Brian Telfer, Laura J. Brattain
2023 IEEE 19th International Conference on Body Sensor Networks (BSN)
Resource-Efficient Invariant Networks: Exponential Gains by Unrolled Optimization
Sam Buchanan, Jingkai Yan, Ellie Haber, John Wright
Arxiv, 2022

Teaching

  • Teaching Assistant, 10-701 Introduction to Machine Learning. Carnegie Mellon University. Spring 2025.
  • Teaching Assistant, Graduate-level Foundations of Computer Science. New York University. Spring 2020.

Updated November 2025. Template is adapted from here.