Presenting La-Proteina! A new model for scalable, all-atom protein design 🧬 Backbone + sequence + side-chains, indexed and unindexed atomistic motif scaffolding, scalable up to 800 residues, and more…
A thread 🧵
🚨 Thrilled to share Efficient Geometric Interatomic Potential (EGIP) - an efficient and accurate ML model for materials!
Even though non-conservative MLIPs are not physically grounded, they offer significant efficiency. This work demonstrates that they are quite accurate on…
Today we release TorchSim, a next-generation PyTorch-native atomistic simulation engine for the MLIP era. Our hope is that this open-source package ignites a materials simulation revolution.
🚨 Checkout our new MD simulation package!
✅ Completely written in PyTorch
✅ Handles batched simulations
✅ Easy to add new MLIPs
Led by @ganganabhijeet and @orionarcher_
Spoiler alert: New MLIP coming soon!
Code (MIT License): github.com/Radical-AI/tor…
🚨 Checkout our new MD simulation package!
✅ Completely written in PyTorch
✅ Handles batched simulations
✅ Easy to add new MLIPs
Led by @ganganabhijeet and @orionarcher_
Spoiler alert: New MLIP coming soon!
Code (MIT License): github.com/Radical-AI/tor…
1/ Machine learning force fields are hot right now 🔥: models are getting bigger + being trained on more data. But how do we balance size, speed, and specificity? We introduce a method for doing model distillation on large-scale MLFFs into fast, specialized MLFFs!
#ICLR2025 Do you know that explicit structure encoding is crucial not only for GNNs’ expressive power but also for graph-based retrieval-augmented generation (RAG)? We introduce SubgraphRAG, a lightweight yet powerful framework for knowledge-graph (KG)-based RAG.
Paper:…
Excited to finally announce the publication of MatterGen on Nature. MatterGen represents a new paradigm of materials design with generative AI. We are releasing the training and inference code of MatterGen under MIT license. Look forward to seeing how the community will use the…
Excited to finally announce the publication of MatterGen on Nature. MatterGen represents a new paradigm of materials design with generative AI. We are releasing the training and inference code of MatterGen under MIT license. Look forward to seeing how the community will use the…
📢📢📢 Happy to introduce Graph Generative Pre-trained Transformers (G2PT):
Can we tokenize graphs and train an autoregressive (AR) model with generative pre-trained transformers to generate graphs?
A new work led by @XiaohuiC16528, @YinkaiW, @jacksonleihao.
A thread 🧵1/6
We are excited to announce MatterTune, a unified platform for finetuning and running atomistic foundation models. It enables users to quickly swap models, modify training procedures, and perform arbitrary downstream tasks ranging from materials screening to molecular dynamics. 1/
Posting a call for help: does anyone know of a good way to simultaneously treat both POTS and Ménière’s disease? Please contact me if you’re either a clinician with experience doing this or a patient who has found a good solution. Context in thread
Excited to unveil OCx24, a two-year effort with @UofT and @VSPARTICLE! We've synthesized and tested in the lab hundreds of metal alloys for catalysis. With 685 million AI-accelerated simulations, we analyzed 20,000 materials to try and bridge simulation and reality.
Paper:…
My GT dynamical ML group is recruiting PhD students for Fall'25. Interested in ML theory or AI4Science with Math/Phys/CS background?
Plz apply at grad.gatech.edu/admissions to either Math, ML, CSE, or ACO PhD program, mention my name & choose Math as home unit.
RT is appreciated!
Does equivariance matter when you have lots of data and compute?
In a new paper with Sönke Behrends, @pimdehaan, and @TacoCohen, we collect some evidence.
arxiv.org/abs/2410.23179
1/7
1/ What are key design principles for scaling neural network interatomic potentials? Our exploration leads us to top results on the Open Catalyst Project (OC20, OC22), SPICE, and MPTrj, with vastly improved efficiency!
Accepted at #NeurIPS2024: arxiv.org/abs/2410.24169
Immensely grateful for the incredible learning experience and the opportunity to work with amazing people throughout my PhD journey. Special thanks to my advisors @johnkitchin and @zackulissi!
x.com/CMU_ChemE/stat…
Immensely grateful for the incredible learning experience and the opportunity to work with amazing people throughout my PhD journey. Special thanks to my advisors @johnkitchin and @zackulissi!
x.com/CMU_ChemE/stat…
🎥 Today we’re premiering Meta Movie Gen: the most advanced media foundation models to-date.
Developed by AI research teams at Meta, Movie Gen delivers state-of-the-art results across a range of capabilities. We’re excited for the potential of this line of research to usher in…
Super excited to release a set of models for computational chemistry - my last 2 years of work @OrbMaterials.
Post ELMo, I'm at some risk of becoming a "one trick pony" career wise, but we've managed to make pre-training work nicely for 3d crystal structures.
More below!
Quick update on my ongoing project #MLIPArena:
The surge in foundation ML interatomic potentials (#MLIPs) is hard to miss—many excel in energy/force error metrics. But have they truly captured the physics of fundamental atomic interactions?
The answer might surprise you.
718 Followers 1K FollowingResearcher @AIatMeta @OpenCatalyst | Pioneering materials from lab bench to the world with Al | alum @Sargent_Group @UofT @A3MD_UofT @CO2CERT
10K Followers 10K FollowingA multidisciplinary, #openaccess journal devoted to the application and development of #machinelearning for the sciences. Published by @IOPPublishing.
821 Followers 541 FollowingPhD @ MIT CSAIL. Geometric deep learning, especially learning with symmetries (equivariance). https://t.co/0XcSE5V8S2. Cofounder @bostonsymmetry.
4K Followers 978 FollowingAssociate Prof @AmlabUva @UvA_Amsterdam in Geometric Deep Learning 🧐 Disassociated Alter from Mind at Large🌿@ELLISforEurope Scholar & Director 🇪🇺
1.7M Followers 5K FollowingBritish-American journalist. Editor-in-chief and CEO of new media company @zeteo_news. Subscribe here: https://t.co/sEC1ETyGtn
287 Followers 1K Following(ex) tennis, (trying) ML. Research Scientist at NVIDIA, views are my own.
Previously, intern at DeepMind, VantAI, Microsoft research, and Amazon AWS.
517 Followers 385 FollowingScientist at @toyotaresearch, previously Harvard | materials science, machine learning | @UofR '16 | @harvardphysics PhD | he / him | All views my own
179 Followers 115 FollowingPh.D. Candidate at UC Berkeley in @persson_group. NSF Fellow. Active in computational materials discovery. Ask me about open source science.
8K Followers 679 FollowingPhD student @MIT • Research on Generative Models and Geometric Deep Learning for Biophysics • BA @CambridgeUni • Former @TwitterResearch, @DEShawGroup and @IBM
6K Followers 782 Followingreasoning research @OpenAI 🍓 | UCLA CS PhD (‘21-‘24) | Ex. Microsoft Research (AI Frontiers), Meta (FAIR), NVIDIA Research (LPR)
12.7M Followers 4K FollowingUS Congresswoman, NY-14. In a modern, moral, and wealthy society, no American should be too poor to live. People-Funded, takes no lobbyist💰. Personal account.
390 Followers 139 FollowingFaculty fellow at NYU working with @andrewgwils. Statistics & machine learning for proteins, RNA, DNA.
Prev: @jura_bio, PhD with @deboramarks
10K Followers 4K Followingsth new // ex Gemini RL+Inference @GoogleDeepMind // Chat AI @Meta // RL Agents @EA // ML+Information Theory @MIT+@Harvard+@GeorgiaTech // زن زندگی آزادی
346K Followers 1K FollowingDeepMind Research Scientist. Opinions my own. Inventor of GANs. Lead author of https://t.co/M6vl8pEQ4I Founding chairman of @pubhealthaction
1K Followers 536 FollowingMachine learner & physicist. At @cusp_ai, I teach machines to discover materials for carbon capture. Previously Qualcomm AI Research, NYU, Heidelberg U.