Our paper on predicting the emergence of crystals from amorphous precursors with deep learning potentials is now published in Nature Computational Science! 🎉 @GoogleDeepMind.

RT @ganganabhijeet: Here is the code where you can use any ASE calculator to run the workflow.

Generate videos in just a few seconds. Try Grok Imagine, free for a limited time.

RT @ganganabhijeet: Running the a2c workflow with MACE-MPA-0 + Cell relaxation. Animation shows the steps.- Soft sphere relaxation.- Melt-Q….

A very nice perpective on our recent approach to predicting crystal structures from amorphous precursors using deep learning potentials, by Prof. Schön.

RT @NatComputSci: @draykol @ekindogus @GoogleDeepMind An accompanying News & Views for this paper by J. C. Schön is now available! https://….

RT @tfgg2: We're looking for Research Engineers to work at the intersection of LLMs and impactful scientific problems! Applications close n….

RT @lmthang: Excited to share details of AlphaGeometry2 (AG2), part of the system that achieved silver-medal standard at IMO 2024 last July….

RT @sundarpichai: 1/ New Gemini 2.0 updates, here we go! . Gemini 2.0 Flash is now GA, so devs can now build production applications. Find….

RT @GoogleDeepMind: We’re putting our most advanced AI for weather forecasting into more people’s hands. ☁️🌐. Scientists can now access @Go….

RT @JeffDean: @demishassabis, James Manyika, and I wrote up a (lengthy and illustrated!) overview of the AI research work and advances acro….

RT @ML_Chem: Predicting emergence of crystals from amorphous precursors with deep learning potentials #machinelearning #compchem https://t.….

RT @bravo_abad: Predicting metastable crystals from amorphous precursors with deep learning. Identifying which crystalline phases emerge fi….

Work done together with @ekindogus @simonbatzner @amilmerchant and Jennifer Wei.

We expect a2c to complement the existing global crystal structure prediction techniques, as it focuses on finding a small set of crystals that have a potential synthesis pathway from amorphous precursors in the laboratory.

We validated a2c across a diverse array of materials, including oxides, nitrides, carbides, and metal alloys, demonstrating its ability to identify both stable and metastable crystallization products.

Here we introduce a2c, a computational method that can identify the likely crystallization products of amorphous materials by sampling the local structural motifs in the amorphous atomic configurations using deep learning interatomic potentials.

RT @demishassabis: An incredible experience beyond imagining to get to sign the great Nobel book, alongside many of my all-time scientific….

RT @m__dehghani: Gemini2 Flash on the challenge of what the internet has been asking for: breaking down "draw the rest of the owl" into act….

RT @JeffDean: We've released an early version of Project Mariner to trusted testers. Project Mariner is an early research prototype built….

RT @sundarpichai: Here’s a peek at the future: Project Astra, our prototype showing glimmers of a universal AI assistant. We showed an earl….