Michael Scherbela

I am truly excited to share our latest work with @MScherbela, @GrohsPhilipp, and @guennemann on "Accurate Ab-initio Neural-network Solutions to Large-Scale Electronic Structure Problems"! arxiv.org/abs/2504.06087

Happy to share that our paper "Towards a transferable fermionic neural wavefunction for molecules", jointly with @MScherbela and @LeonGerard5 has finally appeard in Nature Communications @NatureComms see nature.com/articles/s4146…

@JannesNys Thanks everybody for joining. Was a pleasure organizing this and great to see all the amazing work in this community!

Spent the last 2 days at the DL-VMC workshop in Vienna. Very interesting to see the immense progress and ideas on solving electrons systems: molecules, solids, etc! It's undoubtedly become a valuable tool that's here to stay

Very happy to share our latest work arxiv.org/abs/2303.09949 on solving the electronic Schrödinger equation with deep neural networks. For the first time we present an architecture capable of learning a single wavefunction across multiple compounds and geometries. 1/n

Happy to announce that our paper "Gold-standard solutions to the Schrödinger equation: how much physics to we need?" joint with @LeonGerard5 @MScherbela @marquetand was accepted at #NeurIPS2022! See arxiv.org/abs/2205.09438 for the preprint.

In a recent Article, @Mscherbela, @GrohsPhilipp, @marquetand and colleagues propose weight-sharing neural network-based variational Monte Carlo methods for solving the electronic Schrödinger equation for multiple geometries (rdcu.be/cNVjx). nature.com/articles/s4358…