Digging into the model we found intriguing behaviour, such as the unsupervised discovery by the model of ‘core’ electron orbitals for second row atoms.

This has been a fascinating project to be a part of! Check out the preprint for more details and results. (8/n)

We also saw very strong results confirming the experimental activation energy of a Diels-Alder reaction, and significantly outperforming earlier transferable QMC approaches (7/n)

We scaled this idea up and pushed it to work on strongly correlated systems. On a cost/error plot, we find that Orbformer is on or ahead of the Pareto frontier formed by traditional multireference methods, a first for deep QMC. (6/n)

To get cost down we make use of amortization: solving a single minimization problem with a more complex network that represents multiple wavefunctions simultaneously (5/n)

Describing strongly correlated quantum systems remains a major challenge in quantum chemistry. Deep QMC offer a potential solution, but at a huge computational cost. (4/n)

For a short ML focused introduction to this paper, I wrote this blog post ae-foster.github.io/posts/2025/0... (3/n)

Huge thanks to Zeno Schätzle, P Bernát Szabó, @lixuecheng-ai4chem.bsky.social @jonkhler.argmin.xyz @n-gao.bsky.social Jiawei Li, Gino Cassella @franknoe.bsky.social @jan.hermann.name (2/n)