Noncovalent Interactions in Density Functional Theory: All the Charge Density We Do Not See | Journal of the American Chemical Society

I had a blast presenting our work with Catherine Mollart and Michelle Ernst on #COF and #MOF at the vdW/L Discussions! Thank you Alex and Mirela @TCPUniLu for having me!

Next steps in #compchem benchmarking @NatureComms: - diverse drug-pocket interaction models - dual gold standard reference: CCSD(T) = DMC - physicochemical properties & atomic forces Led by Tkatchenko group @TCPUniLu, @MirelaPuleva, @Lmedranos88! https://t.co/TC0kCRn7U4

Our recent work on SO3LR, a general-purpose machine learned force field for molecular simulations, has been published in @J_A_C_S! 🌞

🔬New tool for computational spectroscopy! Researchers from @TCPUniLu in collaboration with @JanssenGlobal unveil THeSeuSS, a Python-based platform automating IR & Raman spectra simulations for molecules & solids. Powered by 🇱🇺 #MeluXina supercomputer 👉 https://t.co/Csx1lqTgwD

New on #HPCSummerQuest: EquiDTB blends quantum chemistry with equivariant AI to reach DFT-level accuracy for large, flexible molecules. Trained on #MeluXina GPUs, cutting runtimes from weeks to days. ⚡️🧬🧠 Read more 👉 https://t.co/9ErSZAdKzs

Very happy to share our preprint of work led by @HengZ_921 on making DFT accurate for charged systems, with broad implications for biochemistry, enzymology, and materials. Big collaborative effort @nagyrpeter @TCPUniLu @unifrChemistry 🔗

🚨Check out our recent #preprint on advancing Density Functional Tight-Binding method with equivariant NNs. We have been developing this project for a while, the results now highlight the enhanced scalability/transferability of our DFTB+ML approach. 🌐 https://t.co/7ahA1Tyfjo

Check out @AriadniBoziki's talk at #ACSSpring2025: 'Automating polymorph characterization: THeSeuSS for simulating IR, Raman, and THz spectra' on March 26, 10:55 - 11:10 AM in Hall F Room 1.

Atomic Orbits in Molecules and Materials for Improving Machine Learning Force Fields #machinelearning #compchem

Pretraining graph transformers with atom-in-a-molecule quantum properties for improved ADMET modeling https://t.co/aiCLg2Vrl0 #chemoinformatics #feedly

Congrats to @SuperFalla!

Alexandre Tkatchenko, from the University of Luxembourg, is giving the 40th NCCR MARVEL Distinguished Lecture today at 4 pm CET (online and at EPFL) on "Realizing Schrödinger's dream with AI-enabled molecular simulations". More info and link 👉 https://t.co/SsCZbbMQkx

Learn how to calculate diffusion pathways with FHI-aims and aimsChain with our new 5-min video and accompanying written tutorial: https://t.co/wpCGURWzUs Based on the work of @TCPUniLu 🥳

Now published! The paper that was the topic of our recent FHI-aims webinar. In case you missed it, you can see the recordings on our YouTube channel https://t.co/UTSlpkTgAt and follow our tutorial to see how these calculations were performed in FHI-aims

Non-local interactions determine local structure and lithium diffusion in solid electrolytes

New paper just out in @NatureComms! Non-local interactions determine local structure and lithium diffusion in solid electrolytes link: https://t.co/koe7vL0gCr

🚀Submit your abstract and discover the experts who will be sharing their insights on AI for Physics! As AI advances, it could unlock breakthroughs in dark matter research and fusion energy, pushing the boundaries of human knowledge and exploration.

The first part of the ☕️TEA Challenge, featuring Model Analysis, has now also been published in @ChemicalScience! This concludes the Crash Testing Machine Learning Force Fields TEA Challenge. Congratulations to everyone involved! link: https://t.co/BzeICSXXk5

The recordings of our recent FHI-aims webinar and hands-on session are now online: https://t.co/2YvNSZLYTz Thank you to our great speakers, Mariana Rossi and Alexandre Tkatchenko (@TCPUniLu), as well as everyone who joined and participated in the Q&A and hands-on session!