Check out our new JOSS paper documenting DebeyeCalculator, which can be used to calculate scattering patterns with GPU acceleration. It should now be be possible to use DebeyeCalculator when training DL models for inorganic molecules!

DebyeCalculator is now published in JOSS 💻🧪🌐 joss.theoj.org/papers/10.2110…

🚨Our recent work on chemically-informed large-scale inorganic (CHILI) nanomaterial datasets is now on arXiv! Presenting the first large-scale nanomaterial datasets with high structural and elemental diversity. 📝Preprint: bit.ly/CHILI-preprint 🔗Code: bit.ly/CHILI-code

Are you looking for a challenging dataset to put your #graph #ML (or LLM) methods to test? Check out CHILI: our latest work where we curate a large-scale (>183M nodes, >1.2B edges) and a medium-scale graph dataset (>6M nodes, >49M edges) for #Inorganic #Nano #Materials modelling.

Andy S. Anker et al.: ClusterFinder: a fast tool to find cluster structures from pair distribution function data Københavns Uni Københavns Uni Københavns Uni Københavns Uni Københavns Uni... #IUCr scripts.iucr.org/cgi-bin/paper?…

The development of AI models is an overlooked climate culprit. Computer scientists at UCPH have created a recipe book for designing AI models that use much less energy without compromising performance 👉 via.ritzau.dk/pressemeddelel… With Raghav{endra}| ರಾಘವೇಂದ್ರ #ArtificialInteligence

A single ChatGPT prompt is estimated to consume, on average, as much energy as forty mobile phone charges. Computer scientists at SCIENCE have created a recipe book for designing AI models that use much less energy without compromising performance: shorturl.at/gjuBR #ai

Our work was featured in an evening news broadcast on TV 2 NEWS yesterday, and Pedram was amazing! Thanks Maria Hornbek for the work! If you have subscription, you can watch the segment here: play.tv2.dk/afspil/1360a39…

Back in November, Google announced 2.2 milllion new materials. Today, a paper in Chemistry of Materials from Ram Seshadri and Tony Cheetham dismantles that claim pubs.acs.org/doi/10.1021/ac…

#KDD2024 🚀 I'm delighted to share that our latest paper, featuring #CHILI, a graph #ML dataset for inorganic materials chemistry, will be presented at SIGKDD 2025! Kudos to Ulrik_F-J Andy Sode Anker Raghav{endra}| ರಾಘವೇಂದ್ರ @kirsten_mj !🎉

First benchmarking results using our large-scale nanomaterials dataset, #CHILI, to be presented at SIGKDD 2025 are coming out. If you are looking for a challenging dataset for GNN- or transformer- methods, put them to test against CHILI. arxiv.org/abs/2402.13221

Absolutely thrilled for a jam-packed week of #GenerativeAI lectures at GeMSS 2024 @TUeindhoven

Getting reports of a successful presentation of #CHILI paper at SIGKDD 2025 by Ulrik_F-J Frederik Lizak Johansen

A new paper about AI in Materials Discovery has gained a lot of attention - it reports a big increase in productivity of scientists using AI tools, and interesting secondary effects of using AI for science. But do the technical claims stack up? Let's see...

So, I have been working hard on a book for > 1 year now. Something that I am extremely excited about, as it is trying to present a holistic view of my research domain at the intersection of #ArtificialIntelligence and #Sustainability. It is simply called "Sustainable AI".