![Muhammed Shuaibi Profile](https://pbs.twimg.com/profile_images/1301888889955774464/xawV5cKn_x96.jpg)
Muhammed Shuaibi
@mshuaibii
Followers
350
Following
553
Statuses
182
Research Engineer at FAIR, @AIatMeta @OpenCatalyst
Joined September 2020
Excited to share OMat24 - the latest dataset to join our team's family of open datasets: OC20, OC22, ODAC23 Accelerating progress in the field should be a community effort. Without access to large, diverse datasets this becomes increasingly prohibitive. We hope OMat helps!
Introducing Meta’s Open Materials 2024 (OMat24) Dataset and Models! All under permissive open licenses for commercial and non-commercial use! Paper: Dataset: Models: 🧵1/x
1
5
44
Excited to be part of this release! How we connect computational models to real experiments is essential to making real world impact. Here we introduce OCx24 as a first step to what it would take to bridge this gap and make it a reality. Paper:
OCx24 bridges the gap between computational models and experimental results with a dataset of diverse materials, featuring both positive and negative outcomes, tested under industrial conditions. We focus on metal alloy nanoparticles, requiring precise synthesis control.
0
3
23
@AlanBoyce47 @OpenCatalyst The primary difference is users must also accept the "FAIR Acceptable Use Policy" outlined here - i.e. using the research for non illegal activities, etc.
1
0
0
RT @OpenCatalyst: Come work with us on the FAIR Chemistry team! Roles: - Postdoc: - Research interns: https://t.co…
0
8
0
Many have asked about tighter convergence settings for OC20. Here we showcase how a cancellation of errors results in similar adsorption energies and ML performance between the original OC20 and a more tightly converged variant.
Interestingly, they also show that the performance of models trained on data with the tighter DFT settings is comparable to those trained with the original OC20 settings.
0
4
19
RT @ylecun: Data generation through simulation is one reason why the whole idea of ML for science is so exciting.
0
162
0
RT @OpenCatalyst: A few of us will be at the AC conference this week. We will be sharing some of our ongoing computational-experimental eff…
0
7
0
RT @bkmi13: Announcing our new model for materials! FlowMM... - Generates stable & novel materials efficiently - Predicts crystal structu…
0
68
0
The ocp repo has now rebranded to fairchem. As part of the upgrade, we have made installation, models, data, and tutorials a lot more accessible to new users. Check it out here:
Introducing fairchem - our revamped codebase consolidating our AI modeling efforts in chemistry and materials science. fairchem makes it easy to interface with our data, models, demos, and applications - including an easy to use ASE calculator:
0
0
11
@newplatonism @OpenCatalyst @andrewwhite01 If you want to interface with ASE's MD tooling - the calculator here will work as is. We currently don't have support for LAMMPS but that is certainly something on our radar for the near future.
0
0
1
RT @OpenCatalyst: Introducing fairchem - our revamped codebase consolidating our AI modeling efforts in chemistry and materials science. fa…
0
26
0
RT @OpenCatalyst: Wrapping up the Open Catalyst Intro Series (for now) - how do we evaluate models and address open problems that still rem…
0
13
0
One of the most common questions we receive is whether OC20 models can be used for transition-state calculations. In this new work we demonstrate that indeed, even without training on transition-state data, OC20 models can accelerate these calculations out of the box!
We are excited to share CatTSunami: We show that a zero-shot application of machine learning models trained only on OC20 can calculate a transition state with 91% accuracy in less than a minute.
0
0
16
RT @AdeeshKolluru: 🚨 New work at the intersection of Diffusion x Catalysis x Optimization accepted at #ICML2024🎉! Introducing AdsorbDiff:…
0
22
0
RT @AdeeshKolluru: 🌟 Make sure to check out the new webpage of our work with interactive visualization and additional results demonstrating…
0
4
0
RT @OpenCatalyst: Equivariant models have become a natural choice for modeling atomic systems. Check out our latest video to learn more! h…
0
25
0