About me

I am a researcher at Isomorphic Labs. I have completed my PhD at EPFL in 2023 under the guidance of Pascal Frossard. During my PhD, I developed several denoising diffusion models for molecules and graphs in general, namely EDM, DiGress, MiDi and SparseDiff. Before that, I studied at École Polytechnique and ENS Paris-Saclay in France (master MVA - Mathematics, Vision and Learning).

My research interests lie in the representation and generation of unordered data (point clouds and graphs), with a particular focus on molecules.

Selection of papers:

Yiming Qin, Clément Vignac, Pascal Frossard - Sparse Training of Discrete Diffusion Models for Graph Generation (ArXiv)

Clément Vignac, Nagham Osman, Laura Toni, Pascal Frossard - MiDi: Mixed Graph and 3D Denoising Diffusion for Molecule Generation (ECML 2023)

Clément Vignac * , Igor Krawczuk * , Antoine Siraudin, Bohan Wang, Vokan Cevher, Pascal Frossard - DiGress: Discrete Denoising diffusion for graph generation (ICLR 2023)

Emiel Hoogeboom * , Victor Garcia Satorras * , Clément Vignac * , Max Welling - Equivariant diffusion for molecule generation in 3D (ICML 2022 long presentation)

Clément Vignac, Pascal Frossard - Top-N: Equivariant Set and Graph Generation without Exchangeability (ICLR 2022)

Clément Vignac, Andreas Loukas and Pascal Frossard - Building powerful and equivariant graph neural networks with structural message-passing (NeurIPS 2020)

Full list

For a full list of publications, look at my Google scholar page.