🔥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

Thanks for participating at #simplaix_ml3m - have a safe trip home!

🎉 new preprint just dropped 🎉 We use machine-learned energy models to probe the impact of treating complicated metal-organic frameworks (MOFs) as simple AB₂ networks. Huge congratulations to Zoé Faure Beaulieu on her first first-author paper! The first of many I'm sure 😃

Professor Andrew Goodwin FRS is elected a Fellow of the Royal Society. His research focuses on understanding and exploiting the dual roles of flexibility and disorder in functional materials. #RSFellows royalsociety.org/people/andrew-…

A pleasure to welcome Dr Chiheb Ben Mahmoud (Chiheb Ben Mahmoud) as a new postdoctoral researcher Deringer Group Oxford! Chiheb will lead activities on #MachineLearning for spectroscopy & structural characterisation of amorphous materials, as key part of our UK Research and Innovation Frontier Research project.

Excited (and slightly nervous 🦋) to be giving my first invited talk about graphene, ML atomic energies, network topology and Monte-Carlo at the Lennard-Jones centre today at 2pm! talks.cam.ac.uk/talk/index/201…

New group photo! 😀 Such a pleasure to see team Deringer Group Oxford expanding and going strong - thanks to everyone's creative contributions, & to generous support by UK Research and Innovation Engineering and Physical Sciences Research Council and of course Oxford Chemistry

This week I'm in Berlin for the #PsikCECAM23 conference. Some amazing talks already, including personal highlights from Volker Deringer, Joe Morrow, Nicholas Runcie and Francesco Di Giovanni . 3 more days and loads more science still to go 😊

A pleasure to present work from Deringer Group Oxford, and later to discuss data for ML / #compchem more widely. Thank you Cecilia Clementi Gábor Lixin Michele Ceriotti for this opportunity - and Joe Morrow (OxICFM) for joining me on the stage 🙂

Very pleased to present our new pre-print: "Synthetic data for pre-training neural-network potentials" 😌 See 👇🧵 for a quick summary, or have a complete read here: arxiv.org/abs/2307.15714 All thoughts and comments very welcome! 1/

Slightly delayed (!!) but very pleased to announce that our paper: "Synthetic data for pre-training neural-network potentials" is out in Machine Learning: Science and Technology See 👇🧵 for a quick summary, or have a complete read here: doi.org/10.1088/2632-2… All thoughts and comments very welcome! 1/

Announcing "load-atoms": a simple-to-use Python package for downloading, inspecting and handling datasets of atomistic structures! #compchem jla-gardner.github.io/load-atoms/

Delighted to share this #compchem paper from Zoé Faure Beaulieu's ongoing DPhil project – a great collaboration with @fausto_martelli at IBM Research! Zoé studied #ML models that can classify different forms of amorphous ice. Read more in The Journal of Chemical Physics doi.org/10.1063/5.0193…

Very excited to see our comment out in Nature Computational Science 🎉 We seek to highlight the central role of high-quality datasets in atomistic #ML, and summarise established and recently proposed ways of building such.

🚨 Introducing graph-pes: a unified framework for building, training and using graph-based machine-learned models of potential energy surfaces! 🚨 #compchem #ML

I've been working hard behind the scenes, and am excited to announce that graph-pes version 0.1.0 is now out!

Extremely excited to be sharing the output of my internship in Microsoft Research's #AIForScience team: "Understanding multi-fidelity training of machine-learned force-fields" 🤖🧪

Excited to share the pre-print we’ve been working on for the last ~4 months: “Distillation of atomistic foundation models across architectures and chemical domains” Deep dive thread below! 🤿🧵