[2310.04925] Crystal-GFN: sampling crystals with desirable properties and constraints

Computer Science > Machine Learning arXiv:2310.04925 (cs) [Submitted on 7 Oct 2023 (v1), last revised 3 Mar 2026 (this version, v3)] Title:Crystal-GFN: sampling crystals with desirable properties and constraints Authors:Mila AI4Science: Alex Hernandez-Garcia, Alexandre Duval, Alexandra Volokhova, Yoshua Bengio, Divya Sharma, Pierre Luc Carrier, Yasmine Benabed, Michał Koziarski, Victor Schmidt, Gian-Marco Rignanese, Pierre-Paul De Breuck, Paulette Clancy View a PDF of the paper titled Crystal-GFN: sampling crystals with desirable properties and constraints, by Mila AI4Science: Alex Hernandez-Garcia and Alexandre Duval and Alexandra Volokhova and Yoshua Bengio and Divya Sharma and Pierre Luc Carrier and Yasmine Benabed and Micha{\l} Koziarski and Victor Schmidt and Gian-Marco Rignanese and Pierre-Paul De Breuck and Paulette Clancy View PDF HTML (experimental) Abstract:The discovery of novel solid-state materials, such as electrocatalysts, super-ionic conductors, or photovoltaic materials, plays a critical role in addressing various global challenges. It has, for instance, the potential to significantly improve the efficiency of renewable energy production and storage, thereby making substantial contributions to climate crisis mitigation strategies. In this paper, we introduce Crystal-GFN, a generative model of crystal structures possessing desirable properties and constraints. Operating as a multi-environment, continuous-discrete GFlowNet, it sequentially samples structural...