About Me
I am a principal investigator at Aithyra in Vienna, Austria. Aithyra is a new research institute at the intersection of machine learning and life sciences led by Michael Bronstein and funded by the Boehringer Ingelheim Foundation. If you’re interested in PhD, Postdoc, or Visiting researcher positions please feel free to reach out via email!
Previously, I was briefly an assistant professor at Duke University. Before that I did my postdoc with Yoshua Bengio working on efficient machine learning algorithms with applications to cell and molecular biology at Mila in Montreal. I completed my PhD in the computer science department at Yale University in 2021 where I was advised by Smita Krishnaswamy. My dissertation can be found here. My research interests are in generative modeling, deep learning, and optimal transport. I’m working on applying ideas from generative modeling, causal discovery, optimal transport, and graph signal processing to understand how cells develop and respond to changing conditions. I’m also interested in generative models for protein design and cofounded Dreamfold to work on these problems.
I grew up in Seattle and graduated from Tufts University in 2017 with a BS and MS in computer science. Outside of work, I love sailing and running. I am the 2019 junior North American champion in the 505 class, and I recently ran my first 50 mile race the Vermont 50!
Recent News
- I’m co-organizing the Non-Autoregressive Language Models for Fast and Flexible Text Generation workshop at COLM 2026 in San Francisco (Oct 9). Submissions are due June 23, 2026 (AoE) via OpenReview — please consider submitting!
- Two papers accepted to ICML 2026. Checkout our work on autoregressive Boltzmann generators ARBG (Danyal) (spotlight) and topological guidance for macrocycle generation MacroGuide (Alicja Maksymiuk).
- Six papers (2 Oral 4 Poster) accepted to ICLR 2026. Checkout new work on discrete diffusion model training PAPL (Fred and Zack), crystal structure prediction with OXtal (Emily and Andrei), efficient Boltzmann generators with FALCON and RegFlow (Danyal), branched generative modeling in BranchSBM (Sophia), and Topological FM (Kacper).
- Three papers accepted to NeurIPS 2025. Checkout our work on non-gradient dynamics with Curly-FM (Katarina and Lazar), transferable amortized sampling with Prose (Charlie and Majdi), and annealing diffusion models for Boltzmann sampling with PITA (Tara and Yoon) (spotlight).
- Joined Aithyra as a principal investigator. If you’re interested in PhD, Postdoc, or Visiting positions please feel free to reach out via email!
- Congrats to Danyal Rehman and collaborators for winning the Best Paper Award at the Gen Bio workshop at ICML 2025 for our work on forward only regression training of normalizing flows FORT.
- Join us at the second edition of the Frontiers in Probabilistic Inference: Sampling meets Learning workshop at NeurIPS 2025 in San Diego.
Older News (2024)
- Started as an assistant professor at Duke University.
- Two papers accepted to ICML 2025. Checkout our work on Feynman-Kac steering of diffusion models (spotlight) and Scaling Boltzmann Generators as well as newer workshop papers such as FORT, PITA and other works coming soon.
- Congrats to Fred Zhangzhi Peng and collaborators for winning an outstanding paper award at the DELTA workshop at ICLR 2025 for our work on improved sampling from masked diffusion models in P2.
- Four papers accepted to ICLR 2025. Checkout our work on steering masked and continuous diffusion and our work on flow matching in cells with greater realism in CFGen and transferrability in Meta FM.
- Join us at our workshop Frontiers in Probabilistic Inference: Sampling meets Learning at ICLR 2025 in Singapore.
- Presenting a tutorial on Geometric Generative Models with Heli Ben-Hamu and Joey Bose at the LoG Conference 2024.
- Visiting the group of Michael Bronstein at Oxford winter 2024.
- Three papers accepted to NeurIPS 2024! Awesome work led by Xi (Nicole) Zhang, Yuan Pu, Guillaume Huguet, James Vuckovic, and Kacper Kapuśniak.
Interests
- Generative Modeling
- Flow Models
- Optimal Transport
- Protein Design
- Single Cell Dynamics
Education
Postdoc
Mila & University of Montreal
PhD in Computer Science, 2021
Yale University
MPhil in Computer Science, 2020
Yale University
MS in Computer Science, 2017
Tufts University
BS in Computer Science, 2017
Tufts University
Featured Publications
Publications
(2026).
Autoregressive Boltzmann Generators.
ICML (spotlight).
(2026).
Flow matching for generative modelling in bioinformatics and computational biology.
Nature Machine Intelligence, 1-18.
(2026).
Branched Schrödinger Bridge Matching.
ICLR 2026.
(2026).
Efficient Regression-Based Training of Normalizing Flows for Boltzmann Generators.
ICLR 2026.
(2026).
FALCON: Few-step Accurate Likelihoods for Continuous Flows.
ICLR 2026 (Oral).
(2026).
OXtal: An All-Atom Diffusion Model for Organic Crystal Structure Prediction.
ICLR 2026.
(2026).
Planner Aware Path Learning in Diffusion Language Models Training.
ICLR 2026 (Oral).
(2026).
Topological Flow Matching.
ICLR 2026.
(2025).
Progressive Inference-Time Annealing of Diffusion Models for Sampling from Boltzmann Densities.
In NeurIPS (spotlight).
(2025).
Amortized Sampling with Transferable Normalizing Flows.
In NeurIPS.
(2025).
Curly Flow Matching for Learning Non-gradient Field Dynamics.
In NeurIPS.
(2025).
Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Experts.
In ICML (spotlight).
(2025).
Scalable Equilibrium Sampling with Sequential Boltzmann Generators.
In ICML.
(2025).
Defining and Benchmarking Open Problems in Single-Cell Analysis.
Nature Biotechnology.
(2025).
SOAPIA: Siamese-Guided Generation of Off Target-Avoiding Protein Interactions with High Target Affinity.
ICML 2025 Generative AI and Biology (GenBio) Workshop.
(2025).
Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction.
In ICLR.
(2025).
Generating Multi-Modal and Multi-Attribute Single-Cell Counts with CFGen.
In ICLR.
(2025).
The Superposition of Diffusion Models Using the Itô Density Estimator.
In ICLR (spotlight).
(2025).
SOAPI: Siamese-guided generation of Off-Target-Avoiding Protein Interactions.
Learning Meaningful Representations of Life (LMRL) Workshop at ICLR 2025.
(2024).
Trajectory Flow Matching with Applications to Clinical Time Series Modeling.
In NeurIPS (Spotlight).
(2024).
Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Backbone Generation.
In NeurIPS.
(2024).
Metric Flow Matching for Smooth Interpolations on the Data Manifold.
In NeurIPS.
(2024).
Iterated Denoising Energy Matching for Sampling from Boltzmann Densities.
In ICML.
(2024).
A Computational Framework for Solving Wasserstein Lagrangian Flows.
In ICML.
(2024).
SE(3)-Stochastic Flow Matching for Protein Backbone Generation.
In ICLR (Spotlight).
(2024).
Simulation-Free Schrodinger Bridges via Score and Flow Matching.
In AISTATS.
Also presented at Frontiers4LCD Workshop @ ICML 2023.
Also presented at Frontiers4LCD Workshop @ ICML 2023.
(2024).
Learnable Filters for Geometric Scattering Modules.
In IEEE Transactions on Signal Processing.
(2023).
Trellis tree-based analysis reveals stromal regulation of patient-derived organoid drug responses.
Cell.
PDF Cite DOI code reproducible code Tutorial Cancer Research Spotlight Yale News News-Medical
(2023).
A Heat Diffusion Perspective on Geodesic Preserving Dimensionality Reduction.
In NeurIPS.
(2023).
DynGFN: Bayesian Dynamic Causal Discovery Using Generative Flow Networks.
In NeurIPS.
Also presented at Frontiers4LCD Workshop @ NeurIPS 2022.
Also presented at Frontiers4LCD Workshop @ NeurIPS 2022.
(2023).
Understanding Graph Neural Networks with Generalized Geometric Scattering Transforms.
In SIMODS.
(2023).
Geodesic Sinkhorn for Fast and Accurate Optimal Transport on Manifolds.
In IEEE MLSP.
(2023).
Time-Inhomogeneous Diffusion Geometry and Topology.
In SIMODS.
(2023).
Single-Cell Analysis Reveals Inflammatory Interactions Driving Macular Degeneration.
Nature Communications.
(2023).
Improving and Generalizing Flow-Based Generative Models with Minibatch Optimal Transport.
In TMLR
Also presented at Frontiers4LCD Workshop @ ICML 2023.
Also presented at Frontiers4LCD Workshop @ ICML 2023.
(2023).
Graph Fourier MMD for signals on data graphs.
In SAMPTA.
(2022).
Manifold Interpolating Optimal-Transport Flows for Trajectory Inference.
In NeurIPS.
(2022).
Embedding Signals on Knowledge Graphs with Unbalanced Diffusion Earth Mover's Distance.
In ICASSP.
(2022).
Immune Cells and Their Inflammatory Mediators Modify Beta Cells and Cause Checkpoint Inhibitor-Induced Diabetes.
JCI Insight.
(2022).
Topological Analysis of Single-Cell Hierarchy Reveals Inflammatory Glial Landscape of Macular Degeneration.
Investigative Ophthalmology & Visual Science.
(2022).
Multiscale PHATE identifies multimodal signatures of COVID-19.
Nature Biotechnology.
(2021).
MURAL: An Unsupervised Random Forest-Based Embedding for Electronic Health Record Data.
In IEEE Big Data.
(2021).
A sandbox for prediction and integration of DNA, RNA, and protein data in single cells.
In NeurIPS Datasets and Benchmarks.
(2021).
Fixing Bias in Reconstruction-based Anomaly Detection with Lipschitz Discriminators.
In Journal of Signal Processing Systems.
(2021).
Data-Driven Learning of Geometric Scattering Networks.
In IEEE MLSP.
Also presented at ML4M Workshop @ NeurIPS 2020.
Also presented at ML4M Workshop @ NeurIPS 2020.
(2021).
Multimodal data visualization and denoising with integrated diffusion.
In IEEE MLSP.
(2021).
Diffusion Earth Mover's Distance and Distribution Embeddings.
In ICML.
Also presented at LMRL Workshop @ NeurIPS 2020.
Also presented at LMRL Workshop @ NeurIPS 2020.
PDF Cite Code Poster Slides Video Arxiv ICML Page Tweetorial Workshop Poster
(2021).
POT: Python Optimal Transport.
In JMLR.
(2021).
Quantifying the effect of experimental perturbations in single-cell RNA-sequencing data using graph signal processing.
In Nature Biotechnology.
(2020).
Uncovering the Folding Landscape of RNA Secondary Structure with Deep Graph Embeddings.
In IEEE Big Data.
Also at GRLB Workshop @ ICML 2020.
Also at GRLB Workshop @ ICML 2020.
(2020).
Fixing Bias in Reconstruction-based Anomaly Detection with Lipschitz Discriminators.
In IEEE MLSP.
Best Student Paper Award.
Best Student Paper Award.
PDF Cite Code Slides Video Yale Daily Article Best Paper Award
(2020).
TrajectoryNet: A Dynamic Optimal Transport Network for Modeling Cellular Dynamics.
In ICML.
Also at LMRL Workshop @ NeurIPS 2019.
Also at LMRL Workshop @ NeurIPS 2019.
PDF Cite Code Project Slides Video Arxiv ICML Page Introductory Talk
(2020).
Interpretable Neuron Structuring with Graph Spectral Regularization.
In IDA
Also presented at RLGM Workshop @ ICLR 2019.
Also presented at RLGM Workshop @ ICLR 2019.
(2018).
Allocate-On-Use Space Complexity of Shared-Memory Algorithms.
In DISC.
Preprints
(2026).
Hacking Generative Perplexity: Why Unconditional Text Evaluation Needs Distributional Metrics.
ICML 2026 Workshop on Structured Probabilistic Inference & Generative.
(2026).
Why Are DMD Students Lazy? Understanding the Copying Behavior in Few-Step Distillation.
arXiv.
(2026).
Strong Stochastic Flow Maps.
arXiv.
(2026).
Entropy Across the Bridge: Conditional-Marginal Discretization for Flow and Schrödinger Samplers.
arXiv.
(2026).
Coupling Models for One-Step Discrete Generation.
arXiv.
(2026).
Don't Retrain, Align: Adapting Autoregressive LMs to Diffusion LMs via Representation Alignment.
arXiv.
(2026).
MIOFlow 2.0: A Unified Framework for Inferring Cellular Stochastic Dynamics from Single Cell and Spatial Transcriptomics Data.
arXiv.
(2026).
Stochastic Few-step Models.
arXiv.
(2025).
Foundations of Diffusion Models in General State Spaces: A Self-Contained Introduction.
arXiv.
(2025).
Simulation-free Structure Learning for Stochastic Dynamics.
arXiv.
(2025).
Gumbel-Softmax Flow Matching with Straight-Through Guidance for Controllable Biological Sequence Generation.
arXiv.
(2025).
geneRNIB: a living benchmark for gene regulatory network inference.
bioRxiv.