Events

CDS Seminar Series: Modeling Complex System Dynamics with Flow Matching Across Time and Conditions

Speaker: Romain Lopez

Location: 60 Fifth Avenue, Room 150

Date: Friday, November 7, 2025

Modeling the dynamics of complex real-world systems from temporal snapshot data is crucial for understanding phenomena such as gene regulation, climate change, and financial market fluctuations. Researchers have recently proposed a few methods based either on the Schroedinger Bridge or Flow Matching to tackle this problem, but these approaches remain limited in their ability to effectively combine data from multiple time points and different experimental settings. This integration is essential in real-world scenarios where observations from certain combinations of time points and experimental conditions are missing, either because of experimental costs or sensory failure. To address this challenge, we propose a novel method named Multi-Marginal Flow Matching (MMFM). MMFM first constructs a flow using smooth spline-based interpolation across time points and conditions and regresses it with a neural network using the classifier-free guided Flow Matching framework. This framework allows for the sharing of contextual information about the dynamics across multiple trajectories. We demonstrate the effectiveness of our method on both synthetic and real-world datasets, including a recent single-cell genomics data set with around a hundred chemical perturbations across time points. Our results show that MMFM significantly outperforms existing methods at imputing data at missing time points.
Bio: Romain Lopez is an Assistant Professor of Computer Science and Biology at New York University. He received his MSc in Applied Mathematics from École polytechnique and his PhD in Electrical Engineering and Computer Sciences from UC Berkeley, advised by Professors Michael I. Jordan and Nir Yosef. He was a Postdoctoral Fellow at Genentech and Stanford University, hosted by Professors Aviv Regev and Jonathan Pritchard. He has received Best Paper honors at leading AI and computational biology venues as well as a STAT Wunderkind Award (2024), recognizing North America’s most promising early-career scientists. His research develops probabilistic and causal machine learning methods to uncover the mechanisms that govern cellular behavior and disease, including the scVI framework and the scvi-tools ecosystem for deep generative modeling of single-cell omics data.