Quentin Garrido

PhD student in Computer Science

About Me

Currently a PhD Student at Meta AI and Université Gustave Eiffel under the supervision of Laurent Najman and Yann LeCun. My principal research area is currently self-supervised learning, with a focus on images and videos.
I previously completed a dual degree in Computer Science at ESIEE Paris and in Machine Learning at ENS Paris-Saclay (MVA program).

My interests include (in no particular order) Computer Vision, Self Supervised Learning, Topological Data Analysis, Geometric Deep Learning (especially GNNs) and Mathematical Morphology.


Visualizing hierarchies in scRNA-seq data using a density tree-biased autoencoder


Accepted at ISMB 2022.

Garrido, Q., Damrich, S., Jäger, A., Cerletti, D., Claassen, M., Najman, L., & Hamprecht, F. (2021). Visualizing hierarchies in scRNA-seq data using a density tree-biased autoencoder. arXiv preprint arXiv:2102.05892.


ENS Paris-Saclay


2020 - 2021

Highest honors (Mention très bien, félicitations du jury)

Considered one of the leading programs in Machine Learning in France, the MVA (Mathematics, computer vision, machine learning) master is an applied mathematics master’s program that focuses on the theoretical foundations of machine learning as well as modern developments in the field.

Courses taken include : Convex optimization, Large scale convex optimization, Topological Data Analysis, Image Denoising, Computer Vision, Point clouds and 3D modeling, Deep Learning in practice, Theoretical Foundations of Deep Learning, Graphs and machine learning.


MSc Computer Science

2016 - 2021

Top of the class

During the five years of my Diplome d’ingénieur at ESIEE Paris, I studied fundamental topics in mathematics, physics, electrical engineering with a focus on computer science.

Main topics studied : High Performance Computing, image processing, algorithmics, mathematical morphology, programming language theory, …

I was also part of Club*NIX (as a member and as president), a student association which aims at promoting open source software. Our actions included organizing events to teach to other students as well as teaching programming to primary school students.


Facebook AI Research (FAIR Paris)

Research Internship

May - September 2021

Self-Supervised Learning

Developped a new self-supervised approach, building upon recent developments in the field. Work still under progress.

Heidelberg University

Research Internship

May - August 2020

Dimensionality reduction on scRNA-seq data

Developed a new autoencoder based dimensionality reduction method which aims to preserve the hierarchical properties present in the data. Combined deep learning methods and graph based techniques such as a density based Minimum Spanning Tree. Applied and evaluated the method on single-cell transcriptomics data in order to visualize the cell development through time.

Notable projects

Maximin Affinity Learning of Image Segmentation


Project done during the first year of my master's degree.

The goal of this project is to implement an image segmentation technique combining deep learning as well as mathematical morphology. The project won ”Most innovative project” prize by Texas Instruments at ESIEE Paris Projects Day 2020. Please refer to the github link for more details as well as links to the paper presenting the method.

Towards Accessible Improved Generative Adversarial Networks


Project done during the third year of my bachelor's degree.

The goal of this project is to implement and analyze the foundational works on GANs, including DCGAN, WGAN, WGAN-GP and various other improvements. The main result is a comprehensive guide on this topic that is accessible with enough depth to be a good introduction on the topic. Please refer to the github link for more details as well as links to the relevant papers.