🔥Telegram İfşa

We have two openings in quantum algorithms with a strong interest in chemical problems. These come with strong startup support. Please share widely. 1/n jobs.smartrecruiters.com/GriffithUniver…

The long-anticipated g-xTB paper was just released on ChemRxiv. g-xTB is the next semiempirical method from Grimme and co-workers at Rheinische Friedrich-Wilhelms-Universität Bonn. (I've heard rumors about this work for almost two years.) Here's some quick thoughts upon an initial read:

Our new ChemRxiv preprint: AIMNet2-rxn: A #MachineLearning Potential for Generalized Reaction Modeling on a Millions-of-Pathways Scale! #compchem Collaboration with Brett Savoie group. Funded by Office of Naval Research (ONR) under #MURI program chemrxiv.org/engage/chemrxi…

Great stuff!

I am very happy to share Orbformer, a foundation model for wavefunctions using deep QMC that offers a route to tackle strongly correlated quantum states! arxiv.org/abs/2506.19960

1/ Generating transition pathways (e.g., folded ↔ unfolded protein) is a huge challenge: we tackle this by combining the scalability of pre-trained, score-based generative models and statistical mechanics insights-—no training required! To appear at #ICML2025

🧘 Orb v3 is now available as a relaxation API on Ouro 📎 Input a CIF and get a relaxed CIF back ouro.foundation/routes/mmoderw… What used to take many hours with DFT can now be done in seconds with ML potentials like Orb. Though it's not a complete replacement for DFT, it is an

AlphaGenome is (rightly) being hailed as a step change and exciting moment for genomics! One random thought: usually GDM Science reserves the PR push for 'Alpha' projects when they are on the cover of Nature -- I wonder what pushed them to release AlphaGenome as a preprint?

youtu.be/rw1ewLJUgOg lots of interesting ideas in here, one: physicists and philosophers should interact more. I agree but wonder if it’s is a legacy of Feynman’s dislike of philosophy.

Excellent post! Thanks for getting a great conversation going.

We’re excited to introduce Chai-2, a major breakthrough in molecular design. Chai-2 enables zero-shot antibody discovery in a 24-well plate, exceeding previous SOTA by >100x. Thread👇

Need to quickly view XYZ coordinates without opening heavy software? Here's a simple online tool: just paste your xyz coordinates and see the 3D molecule A perfect resource for students, educators, and chemists 👉 labinitio.org/xyzview/ #CompChem #ChemEd #AcademicTwitter

🚀 Benchmark paper out! How well do DFT, semiempirical & ML methods model proton transfer? ✅ DFT performs well, except with N-groups ❌ Pure ML struggles (though ORB v3 shows big gains) 🔥 PM6-ML Δ-learning excels, even in QM/MM setups! Check it out: pubs.acs.org/doi/10.1021/ac…

⚛️ Phase-diagram and energy-above-hull endpoint is live! 🔎 This new endpoint compares your structure to other known materials in the chemical system - all the other materials that it may be competing with during synthesis. The key value we are looking for is the

🚀Exciting news! We are releasing new UMA-1.1 models (Small and Medium) today and the UMA paper is now on arxiv! UMA represents a step-change in what’s possible with a single machine learning interatomic potential (short overview in the post below). The goal was to make a model

Time’s running out! Lead generative AI research for molecular dynamics in our lab AIMLeNS. - Scale our NeurIPS/ICLR-published implicit transfer operators to revolutionize simulations. Postdoc position closes 10. July. Apply now: chalmers.se/en/about-chalm…

Best not to lie to ourselves in materials discovery. The last thing you want is to have a good candidate material you can't synthesize. The formation energy and energy-above-hull endpoint I added tell one part of the stability story. Next, we look to phonon dispersions to tell

We investigated the formation of graphite and diamond from liquid carbon under high pressure. There are some surprises... nature.com/articles/s4146…

A new evaluation shows our AI simulation model, Orb, stands out in many tests. 👏 In this paper (arXiv:2506.01860) by Bowen Han & Yongqiang Cheng, Orb v3 was benchmarked against ~5,000 inorganic crystals and outperformed other MLIPs such as MatterSim and SevenNet-MF-ompa. Take

will start posting blogs about my journey as I learn through my PhD here :) piyushmaharanacats.blogspot.com/?m=1