About
I'm a PhD candidate (CIFRE) at
Meta AI (FAIR)
and
Inria Grenoble (THOTH)
/
Université Grenoble Alpes (UGA)
.
I am co-advised by Karteek Alahari (Inria) and Jakob Verbeek (Meta).
I specialize in diffusion- and flow-based generative models for large-scale image and
video generation.
Before my PhD, I completed the MVA master’s program in applied mathematics and machine learning, and an M.Sc.-level engineering degree (Diplôme d’ingénieur) with a major in Data and Information Sciences – Mathematics and Data Science (SDI–MDS) at CentraleSupélec .
My research focuses on developing training and sampling algorithms to obtain more efficient, flexible and controllable generative models, with applications on image, video and multimodal generation. I expect to graduate around March–April 2026.
⚠️ Open to Research Scientist positions in generative modeling and related topics starting Spring/Summer 2026.
Education
-
PhD (CIFRE), Computer Science
Meta AI (FAIR) & Inria Grenoble / Université Grenoble Alpes 2023 – present (expected Mar–Apr 2026) -
M2 – Mathematics, Vision, Learning (MVA)
ENS Paris-Saclay 2021 – 2022 -
M.Sc.-level engineering degree (Diplôme d’ingénieur)
CentraleSupélec – major in Data and Information Sciences – Mathematics and Data Science (SDI–MDS) 2018 – 2022
Selected Research
-
Flowception: Temporally Expansive Flow Matching for Video Generation FIRST AUTHORPreprint. 2025 arxiv | site
- OneFlow: Concurrent Mixed-Modal and Interleaved Generation with Edit Flows Preprint. 2025 arxiv | site
-
Entropy Rectifying Guidance for Diffusion and Flow Models FIRST AUTHORAdvances in Neural Information Processing Systems (NeurIPS). 2025 arxiv
-
Boosting Latent Diffusion with Perceptual Objectives FIRST AUTHORInternational Conference on Learning Representations (ICLR). 2025 arxiv
- EvalGIM: A Library for Evaluating Generative Image Models Preprint. 2025 arxiv | code
-
On Improved Conditioning Mechanisms and Pre-training Strategies for Diffusion Models FIRST AUTHORAdvances in Neural Information Processing Systems (NeurIPS). 2024 arxiv
-
Unlocking Pre-trained Image Backbones for Semantic Image Synthesis FIRST AUTHORIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2024 arxiv
-
Guided Distillation for Semi-supervised Instance Segmentation FIRST AUTHORIEEE/CVF Winter Conference on Applications of Computer Vision (WACV). 2024 arxiv | code