Couldn't have asked for better timing #NobelPrize Our new work on 'Molecular Simulations with a Pretrained Neural Network and Universal Pairwise Force Fields' is now out on @ChemRxiv! #MachineLearning #compchem

RT @jgreener64: That concludes my list of favourite papers 2001-2023. I plan to do another one in a couple of decades... The list is colle…

RT @ChengBingqing: Long-range ML potentials strike again! 🚀 We benchmarked LES on diverse systems—molecules, solutions, and interfaces. Lea…

RT @sciencebrush: Could the way amino acids break apart under polarized light in space be the key to understanding why life on Earth favour…

RT @marceldotsci: new work! we follow up on the topic of testing which physical priors matter in practice. this time, it seems that predict…

RT @fly51fly: [LG] Euclidean Fast Attention: Machine Learning Global Atomic Representations at Linear Cost J. T Frank, S Chmiela, K Müller,…

RT @_bunnech: How can we build an Al Virtual Cell 🔮🧬 that simulates all functions and interactions of a cell? How will it transform researc…

RT @FrankNoeBerlin: Super excited to preprint our work on developing a Biomolecular Emulator (BioEmu): Scalable emulation of protein equili…

RT @marceldotsci: New: Fast and flexible range-separated models for atomistic machine learning, spearheaded by Kevin and Philip, with many…

RT @ItaiYanai: Out today in Nature: "The Human Cell Atlas"! In my commentary, I compare the cell atlas to early naturalists exploring South…

@EricBoittier @AriWagen Nice initiative! Yeah, absolute energies in SO3LR are somewhat arbitrary (first 2 columns), but relative E should be fine. The performance might improve a bit if you set lr_cutoff to 100 and evaluate inter NCIs as outlined in our methods section (esp relevant for charged dimers).

@CorinWagen @olexandr SAPT10k?

RT @fchollet: When a product is 10x better, it doesn't matter if it starts from a small niche and has no marketing. It will grow steadily,…

@venkatkapil24 This seems relevant:

RT @ask1729: 1/ What are key design principles for scaling neural network interatomic potentials? Our exploration leads us to top results o…

RT @marceldotsci: Our (@spozdn & @MicheleCeriotti) recent work on testing the impacts of using approximate, rather than exact, rotational i…

RT @AlmazKhabi97: Our new work 'Noncovalent Interactions in Density Functional Theory: All the Charge Density We Do Not See' is now out on…

RT @GrantRotskoff: Many of us are doing a lot of transfer learning these days, but how well do we understand it? With @JavanTahir and @Sury…

RT @EtiennePalos: Here it is, folks! We @PaesaniLab published a "one-stop-shop" review on the MB-pol many-body model in @JCIM_JCTC ! It d…

The timing today might have been better! ahah I'm enthusiastic about what the future holds for the natural sciences & AI combo

@anmorgunov @ChemRxiv Thank you, Anton!