AI for chemistry and material science @AIatMeta. Previously known as Open Catalyst Project.
Joined June 2021
- Tweets212
- Following19
- Followers2.8K
- Likes69
FAIR Chemistry retweeted
The Open Molecules 2025 dataset is out! With >100M gold-standard ωB97M-V/def2-TZVPD calcs of biomolecules, electrolytes, metal complexes, and small molecules, OMol is by far the largest, most diverse, and highest quality molecular DFT dataset for training MLIPs ever made 1/N
FAIR Chemistry retweeted
For existing MLIPs, lower test errors do not always translate to better performance in downstream tasks. We bridge this gap by proposing eSEN -- SOTA performance on compliant Matbench-Discovery (F1 0.831, κSRME 0.321) and phonon prediction.
arxiv.org/abs/2502.12147
1/6
FAIR Chemistry retweeted
I’m excited to share our latest work on generative models for materials called FlowLLM.
FlowLLM combines Large Language Models and Riemannian Flow Matching in a simple, yet surprisingly effective way for generating materials.
arxiv.org/abs/2410.23405
@bkmi13 @RickyTQChen @bwood_m
FAIR Chemistry retweeted
Our team at FAIR is looking for research interns in 2025. We work on a range of AI for chemistry topics from applied projects to machine learning potentials and generative models.
If you are interested please apply and don’t hesitate to reach out!
metacareers.com/jobs/1243659…
FAIR Chemistry retweeted
My postdoc Richard Tran led this incredible team project that leveraged the @OpenCatalyst framework to predict stable OER catalysts and was just published in @nanoscale_rsc doi.org/10.1039/D4NR01390E. Many thanks to all contributors and funding from @Shell & @uhoustonenergy.
FAIR Chemistry retweeted
Announcing our new model for materials!
FlowMM...
- Generates stable & novel materials efficiently
- Predicts crystal structure accurately
- Generalizes Riemannian Flow Matching to point clouds w/ periodic boundaries
arxiv.org/abs/2406.04713
@RickyTQChen @anuroopsriram @bwood_m
FAIR Chemistry retweeted
🚨 New work at the intersection of Diffusion x Catalysis x Optimization accepted at #ICML2024🎉!
Introducing AdsorbDiff: Adsorbate Placement via Conditional Denoising Diffusion ⚛️
Paper - arxiv.org/abs/2405.03962
Code - github.com/AdeeshKolluru/Ads…
1/n
FAIR Chemistry retweeted
Introducing DeNS, a scalable denoising objective enabling the use of equilibrium and non-equilibrium structures for learning atomistic representations.
High-capacity models (e.g. EquiformerV2) trained with DeNS improve in both training efficiency and accuracy.
Led by @yilunliao
🧵(1/9) Introducing DeNS, an auxiliary training objective that generalizes denoising to non-equilibrium atomistic structures, improving the performance of equivariant force fields such as Equiformer.
Joint work with @tesssmidt and @abhshkdz from @OpenCatalyst
Preprint: arxiv.org/abs/2403.09549
FAIR Chemistry retweeted
🧵(1/9) Introducing DeNS, an auxiliary training objective that generalizes denoising to non-equilibrium atomistic structures, improving the performance of equivariant force fields such as Equiformer.
Joint work with @tesssmidt and @abhshkdz from @OpenCatalyst
Preprint: arxiv.org/abs/2403.09549
FAIR Chemistry retweeted
Paper shared on arXiv showing catalyst AI/ML models trained on datasets like @OpenCatalyst can generalize to solid solutions like high entropy alloys (HEA)! This is exciting because the design space of HEAs (with >5 components) is combinatorially large.
arxiv.org/abs/2403.09811
FAIR Chemistry retweeted
EquiformerV2 was accepted at #ICLR2024!
EquiformerV2 is the result of (Yi-Lun's) careful empirical analysis of how to incorporate efficient equivariant convolutions into transformers, resulting in an architecture that scales surprisingly well across atomic datasets.
🧵(1/7) Excited to share that our work, EquiformerV2, has been accepted to #ICLR2024. EquiformerV2 is the state-of-the-art on large-scale atomistic benchmarks -- OC20, OC22, AdsorbML, and ODAC23.
Joint work with @bwood_m, @abhshkdz from @OpenCatalyst and @tesssmidt
Paper: arxiv.org/abs/2306.12059
Code: github.com/atomicarchitects/…
FAIR Chemistry retweeted
🧵(1/7) Excited to share that our work, EquiformerV2, has been accepted to #ICLR2024. EquiformerV2 is the state-of-the-art on large-scale atomistic benchmarks -- OC20, OC22, AdsorbML, and ODAC23.
Joint work with @bwood_m, @abhshkdz from @OpenCatalyst and @tesssmidt
Paper: arxiv.org/abs/2306.12059
Code: github.com/atomicarchitects/…
FAIR Chemistry retweeted
CrystalLLM is up on arxiv! In the paper, we show that LLMs can be fine-tuned to produce 3D structures that are stable according to density functional theory (DFT).
arxiv.org/abs/2402.04379
w/ @anuroopsriram, @AndreaMadotto, @andrewgwils, @zackulissi
1/6
FAIR Chemistry retweeted
The FAIR Chemistry team has multiple open summer intern positions across AI for chemistry/materials/etc. Apply here, and reach out if you have questions!
metacareers.com/jobs/9075993…
We had an amazing group last year (@gruver_nate , @yilunliao @HLawrenceCS @jmusiel_ and others)!
FAIR Chemistry retweeted
🌟 Looking forward to the workshop tomorrow! 🌟
📍 Location: Hall C2
⏰ Starting at 8:15AM
🎙️ 7 speakers + 🤝 panel with funding agencies + 🔬 @OpenCatalyst challenge + 🗣️10 oral talks + 🖼️140(!!) posters
neurips.cc/virtual/2023/work…
FAIR Chemistry retweeted
Excited to head to #NeurIPS2023 next week!✈️ I’ll be presenting the results of the 2023 Open Catalyst Challenge at the AI for Science Workshop along side @mshuaibii! Reach out if you’re around and would like to connect 😃
FAIR Chemistry retweeted
I'll be at #NeurIPS2023 this week! Reach out if you would like to chat about the @OpenCatalyst or AI+Science more broadly.
Also make sure to check out the @AI_for_Science workshop on 12/16.
FAIR Chemistry retweeted
We've updated the EquiformerV2 paper with new results on OC22 and QM9 (in addition to OC20).
See Yi-Lun's 🧵 for details! #compchem #AI4Science
🧵(1/6) We have updated the paper of EquiformerV2 to include more results. Currently, EquiformerV2 is the best model on the large-scale OC20 and OC22 datasets.
Joint work with @bwood_m, @abhshkdz from @OpenCatalyst and @tesssmidt.
Paper: arxiv.org/abs/2306.12059
Code: github.com/atomicarchitects/… and github.com/Open-Catalyst-Pro…
FAIR Chemistry retweeted
🧵(1/6) We have updated the paper of EquiformerV2 to include more results. Currently, EquiformerV2 is the best model on the large-scale OC20 and OC22 datasets.
Joint work with @bwood_m, @abhshkdz from @OpenCatalyst and @tesssmidt.
Paper: arxiv.org/abs/2306.12059
Code: github.com/atomicarchitects/… and github.com/Open-Catalyst-Pro…
