Teaching #physics to myself and to my computer: with #geogram AABB-tree, could implement a raytracer in less than 700 lines in one week-end (cc Peter Shirley 🔮🛡). Now my optimal-transport fluid sim looks like a fluid !

KeOps symbolic tensors now accelerate (x10-x100) a wide range of methods, from UMAP embeddings to geometric neural networks. B. Charlier, Joan Glaunes, Michael Bronstein and myself will be happy to discuss it this Wednesday at #NeurIPS2020: neurips.cc/virtual/2020/p…

New #MaSIF architecture for #geometricdeeplearning on proteins with Bruno Correia Freyr Jean Feydy works directly on the atomic point cloud, computes the molecular surface on the fly, is end-to-end differentiable, and runs 10x-100x faster biorxiv.org/content/10.110…

our paper with Bruno Correia Freyr Jean Feydy on fast learning on proteins is accepted to #CVPR2025 End-to-end differentiable architecture, precomputations on the fly, more accurate and x100 faster than #MaSIF biorxiv.org/content/10.110… Code coming soon

Membranes and tubules are part of the same family! These 3D shape textures optimize curvature functionals that generalize the traditional Willmore and Helfrich energies. arxiv.org/abs/2103.04856

A most original use of GeomLoss on 3D shape textures, with pairwise Wasserstein distances between 1,000 curvature histograms. Enabling the use of OT as a "standard" tool for large-scale data analysis is a major target for 2021! Rémi Flamary 🦋