Théo Uscidda
Ph.D. with Marco Cuturi @ CREST - ENSAE, Institut Polytechnique de Paris
Visiting Ph.D. hosted by Fabian Theis @ Helmholtz Munich, Technical University of Munich
Internships: incoming (winter) @ Amazon AI, Fundamental Research Team– past @ Flatiron Institute, Simons Foundation.
Education: I am a Ph.D. student in machine learning working with Marco Cuturi (Apple MLR). Prior to that, I completed a master’s degree in Mathematics, Vision and Learning (MVA) at ENS Paris-Saclay. During my master’s thesis, I worked with Claire Boyer (Sorbonne Université), Julie Josse (INRIA) and Boris Muzellec (Owkin) at LPSM.
Research: I study the interplay between optimal transport (OT) and machine learning. My primary goal is to demonstrate how OT can be used to introduce inductive biases in various learning contexts, particularly in generative modeling and representational learning. For instance, my work has been applied to image generation/unpaired image translation, disentangled representation learning, optimization over probability spaces, geographic information, and various single-cell genomics problems like trajectory inference, perturbation effect prediction, and modality translation. Currently, I am focused on using OT to improve the training and performance of foundation language/vision models, with a particular interest in state-space models. Broadly speaking, I thrive on exploring diverse learning paradigms, as I believe the most creative and impactful research ideas emerge from the synergies between different fields.
Experiences: Since February 2024, I have been a visting Ph.D. student in Fabian Theis’ lab at Helmholtz Munich, where I have been working on generative models for single-cell perturbation discovery. Additionally, from June to August 2024, I interned at the Flatiron Institute collaborating with Victor Chardes and Surya Maddu in Michael Shelley’s team to develop generative models for inferring biophysical dynamics from omics data. During winter 2024, I will be interning at Amazon AI with Matthew Tragger, within the fundamental research team led by Alessandro Achille, where I will work on state-space models.
news
Sep 26, 2024 | Thrilled to announce two accepted papers at NeurIPS 2024: GENOT: Entropic (Gromov) Wasserstein Flow Matching and Mirror and Preconditioned Gradient Descent in Wasserstein Space, with the latter receiving a spotlight! Huge thanks to my coauthors for these amazing collaborations. See you in Vancouver! |
---|---|
Sep 2, 2024 | Back in Munich! I have rejoined Fabian Theis’ lab at Helmholtz Munich, where I will keep working on single-cell perturbations. |
Jun 20, 2024 | I have joined the Flatiron Institute, where I will spend the summer working with Victor Chardes and Surya Maddu, within Michael Shelley’s team. I will be developing generative models to infer biophysical dynamics from omics data. See you in New York City! |
Apr 25, 2024 | I gave a talk on unbalanced Monge maps at Google DeepMind’s reading group on generative models, transport and sampling, organized by Valentin de Bortoli and Arnaud doucet. Looking forward to presenting the paper at ICLR 2024! |
Feb 1, 2024 | I have joined Fabian Theis’ lab at Helmholtz Munich, where I will be developping generative models for discovering single-cell perturbations. |