Kudos to the committee Janine George Volker Deringer Nadine Schneider Fernanda Duarte for such a great workshop. Super impressed by the speakers line up, quality of the papers #FD_data and 'right amount' of enthusiasm in discussions. And still feeling inspired by Alan Aspuru-Guzik's talk!

A pleasure to be part of the GAP/(M)ACE Meeting CECAM, Berlin, courtesy of Hendrik, Miguel Caro Johannes Margraf, Albert Bartok-Partay and others. I presented a talk/tutorial on machine learning for quantum dynamics and spectroscopy Tutorial here -> github.com/venkatkapil24/…

Almost two months after i-pi v3.0 release and we are already working in the one. We want to gather some feedback from the community, please share your opinions with us completing this survey forms.gle/msWufsEjpy4Xmp… (5 min max). Sporadic users and non-users opinions welcome!

A lovely, community focused, idea... (And if you haven't seen it yet - i-PI is a great code which is fun to work with, and easy enough to get started with that you can build undergraduate projects around it.)

🚀 Call for Abstracts! 🚀 Join us at the APS March Meeting symposium "Machine Learning for Atomistic Simulations" to shape this rapidly-evolving field! 📝 Submission Deadline: October 25, 2024 🌐 Submit here: march.aps.org #APS #MarchMeeting #ML Michele Pavanello

Starting soon: Advances in modelling defects and interfaces workshop thomasyoungcentre.org/event/advances… via Thomas Young Centre

We study #quantum nuclear effects (NQEs) for proton disorder in nanoconfined water. Pavan Ravindra uses #MachineLearning potentials to show NQEs play a heightened role compared to bulk and induce superionic proton transport in other molecular water. arxiv.org/abs/2410.03272

New version of i-PI is out: faster and ready for the machine-learning era in atomistic simulations. New features enabling research on the hottest topics in physical chemistry make the code complete! aippub.org/47O32Pl

Do you have any suggestions for good tutorials on developing machine learning potentials for #ML-literate undergrad students who have not done condensed matter or quantum chemistry courses?

🚨 New Preprint Alert! 🚨 👉 doi.org/10.26434/chemr… We’re thrilled to share our latest #compchem work, now live on ChemRxiv! 🎉 In this study, we've combined our MB-pol #datadriven #manybody potential with the Te-PIGS #machinelearning representation of nuclear quantum

Progress towards rigorous #quantum statmech from classical dynamics by #MachineLearning quantum corrections to potentials. In this collaboration with Cecilia Clementi, we obtain exact statics (beyond a centroid description) for paradigmatic aqueous system doi.org/10.1063/5.0226…

🔭 Looking for #PhD opportunities in theoretical/computational neuroscience and #MachineLearning? ⏰ Less than 2 weeks left to apply to our PhD programme. Come join us!

I am glad to have received so many retweets on this, although no tutorial so far. Clearly shows the need for a gentle intro to MLIPs for enthusiastic undergrads.

Congratulations to Michele Ceriotti for delivering his E. Bright Wilson Prize Lecture on machine learning for chemistry at Harvard Chemistry! chemistry.harvard.edu/news/michele-c… #chemtwitter

Congratulations to Prof. Michele Ceriotti from Materials Science & Engineering @EPFL for being awarded the prestigious E. Bright Wilson Prize at Harvard University! Find out more: actu.epfl.ch/news/michele-c…

Manuscript update on MACE organic GNN forcefield for first-principles (bio)molecular simulations. We include a MACE dipole model tested on finite temperature IR spectra (see paracetamol IR). Please try and crash-test the model: github.com/venkatkapil24/… arxiv.org/abs/2312.15211

Tomorrow: TYC AI/ML Interest Group Seminar: advances in machine learning for electrochemical systems thomasyoungcentre.org/event/tyc-ai-m… via Thomas Young Centre

New preprint 📢 Finite-temperature full #quantum sublimation enthalpies for the X23 set of molecular crystals are possible with ML potentials trained on less than 200 configurations. Made possible by fine-tuning the MACE-MP-0 model. Feedback welcome arxiv.org/pdf/2502.15530

Come join us at the APS Focus session Machine Learning for Atomistic Simulation to attend the talks of our invited speakers: Bowen Deng , Yong Xu, Dr. Kamal Choudhary, and Venkat Kapil! Looking forward to see the discussions that will shape the field of ML for materials! ✨🚀

Accurate and efficient machine learning interatomic potentials for finite temperature modelling of molecular crystals #machinelearning #compchem pubs.rsc.org/en/Content/Art…