🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

My first COSMO Lab paper out as a preprint, where we propose local prediction rigidity (#LPR) as a metric to quantify the robustness of local predictions in atomistic ML models. Have a look, and contact me if you are interested in computing the #LPR for your ML models! ☺️

Our work on the design of MOFs with tunable electrical conductivity (w/ Sven Rogge, Prof. Jihan Kim) has been featured in a virtual issue of Chemistry of Materials, along with many other great works on the chemistry of MOFs. ☺️ VI: rb.gy/eu1yo paper: rb.gy/nk4lg

Sven is awesome and his research is truly cutting-edge! Wholeheartedly recommend 👍

Very nice to see this one finally out, and happy to be presenting on this and some more subsequent developments at #F23MRS

This was a much-needed effort extending our prediction rigidity formalism to NN models. Be sure to also check out DPOSE by Matthias Kellner for the other flavor of UQ from our group! x.com/lab_COSMO/stat…

Yuri's paper extending cell2mols ability to process crystallographic files is now live: Automated Prediction of Ground State Spin for Transition Metal Complexes | ChemRxiv - go.shr.lc/4cIU9Jd

A simple yet strong message to those interested in machine learning the DOS, or any target quantity depending on the absolute eigenenergies as a matter of fact!

Excited to share my first PhD publication in Digital Discovery : "Automated Prediction of Ground State Spin for Transition Metal Complexes" A big thanks to Rubén Laplaza, Sergi, clemence corminboeuf, and funding by NCCR-MARVEL

Over the past ~year at COSMO Lab we have been working on something new, and we want to share a #preview of the #atomisticcookbook: lab-cosmo.github.io/atomistic-cook…. This is a repo/website collecting recipes to solve simulation problems 📖🧑‍🍳

Great new work by Filippo Bigi Sanggyu "Raymond" Chong Michele Ceriotti Federico Grasselli COSMO Lab EPFL UNIMORE - 'A prediction rigidity formalism for low-cost uncertainties in trained #neuralnetworks' - iopscience.iop.org/article/10.108… #machinelearning #statphys #Bayesian #compchem #AI

Digital Discovery and PCCP are proud to sponsor poster awards at the upcoming meeting on Uncertainty Quantification in Atomistic Modeling: from Uncertainty-Aware Density Functional Theory to Machine Learning. Find out more and register: cecam.org/workshop-detai…