Zachary W. Ulissi

zulissi@meta.com

zulissi@gmail.com

At Meta’s Fundamental AI Research lab I lead the FAIR Chemistry team where we work on AI/ML broadly applied to materials and chemistry, as well as internal Meta consumer electronics applications in the AR/VR space. I joined Meta’s Fundamental AI Research lab in 2023 to work on AI for chemistry and climate applications and am located in the SF bay area. I am extremely excited about how AI/ML methods can help many types of quantum chemistry simulations and lead to better materials to solve a range of societal scale challenges.

I am also an adjunct professor of chemical engineering at CMU since 2024. Prior to 2023 I was an assistant and then associate professor, and in 2023 I was on leave from my position at CMU. I joined Carnegie Mellon University in 2017, after doing my PhD at MIT and post-doc at Stanford. My PhD work at MIT focused on the applications of systems engineering methods to understanding selective nanoscale carbon nanotube devices and sensors under the supervision of Michael Strano and Richard Braatz. I did my postdoctoral work at Stanford with Jens Nørskov where I worked on machine learning techniques to simplify complex catalyst reaction networks, applied to the electrochemical reduction of N2 and CO2 to fuels. At CMU I continued these efforts to model, understand, and design nanoscale interfaces using machine learning and predictive methods to guide detailed molecular simulations.

In my free time, I enjoy the outdoors and used to be a competitive cyclist, though mostly I do bike trips for fun now. I also enjoy cooking, traveling, and exploring the beautiful SF Bay area with my family!

news

Aug 20, 2026	We launched the UMA Playground! You can now interactively explore Universal Model for Atoms (UMA) simulations, run structural relaxations, and test molecular and materials models directly in your browser.
Jun 20, 2026	We released UMA v1.2.1 with improved performance, updated checkpoints, and enhanced simulation stability across diverse chemical systems.
Apr 10, 2026	We released the OPoly26 dataset and benchmark, expanding our open datasets and models to polymer chemistry and soft matter simulations!
Sep 15, 2025	We released the OC25 dataset expanding our catalyst modeling efforts to explicit solvation layers and electrolyte mixtures!
Jul 15, 2025	We released the OMC25 dataset for molecular crystals, and showed that these methods also work really well for rigid molecule crystal structure prediction, which we call FastCSP!

selected publications

Small molecules/ML

UMA: A Family of Universal Models for Atoms

Brandon M. Wood, Misko Dzamba, Xiang Fu, and 15 more authors

2026

arXiv Bib HTML

@article{wood2025umafamilyuniversalmodels,
  title = {UMA: A Family of Universal Models for Atoms},
  author = {Wood, Brandon M. and Dzamba, Misko and Fu, Xiang and Gao, Meng and Shuaibi, Muhammed and Barroso-Luque, Luis and Abdelmaqsoud, Kareem and Gharakhanyan, Vahe and Kitchin, John R. and Levine, Daniel S. and Michel, Kyle and Sriram, Anuroop and Cohen, Taco and Das, Abhishek and Rizvi, Ammar and Sahoo, Sushree Jagriti and Ulissi, Zachary W. and Zitnick, C. Lawrence},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  volume = {38},
  pages = {129391--129427},
  url = {https://arxiv.org/abs/2505.08760},
  archiveprefix = {arXiv},
  primaryclass = {cs.LG}
}

Inorganic Materials/ML

The Open Materials 2024 (OMat24) inorganic materials dataset and models

Luis Barroso-Luque, Muhammed Shuaibi, Xiang Fu, and 6 more authors

Nature Computational Science, 2026

DOI Bib HTML

@article{barroso2024open,
  title = {The Open Materials 2024 (OMat24) inorganic materials dataset and models},
  author = {Barroso-Luque, Luis and Shuaibi, Muhammed and Fu, Xiang and Wood, Brandon M and Dzamba, Misko and Gao, Meng and Rizvi, Ammar and Zitnick, C Lawrence and Ulissi, Zachary W},
  journal = {Nature Computational Science},
  year = {2026},
  pages = {1--11},
  doi = {10.1038/s43588-026-00996-w},
  url = {https://doi.org/10.1038/s43588-026-00996-w},
}

ML/GNN

The Open Molecules 2025 (OMol25) Dataset, Evaluations, and Models

Daniel S. Levine, Muhammed Shuaibi, Evan Walter Clark Spotte-Smith, and 20 more authors

arXiv preprint arxiv:2505.08762, 2025

arXiv Bib HTML

@article{levine2025openmolecules2025omol25,
  title = {The Open Molecules 2025 (OMol25) Dataset, Evaluations, and Models},
  author = {Levine, Daniel S. and Shuaibi, Muhammed and Spotte-Smith, Evan Walter Clark and Taylor, Michael G. and Hasyim, Muhammad R. and Michel, Kyle and Batatia, Ilyes and Csányi, Gábor and Dzamba, Misko and Eastman, Peter and Frey, Nathan C. and Fu, Xiang and Gharakhanyan, Vahe and Krishnapriyan, Aditi S. and Rackers, Joshua A. and Raja, Sanjeev and Rizvi, Ammar and Rosen, Andrew S. and Ulissi, Zachary and Vargas, Santiago and Zitnick, C. Lawrence and Blau, Samuel M. and Wood, Brandon M.},
  journal = {arXiv preprint arxiv:2505.08762},
  year = {2025},
  volume = {2505},
  url = {https://arxiv.org/abs/2505.08762},
  archiveprefix = {arXiv},
  primaryclass = {physics.chem-ph}
}

Catalysis/ML

The Open Catalyst 2025 (OC25) Dataset and Models for Solid-Liquid Interfaces

Sushree Jagriti Sahoo, Mikael Maraschin, Daniel S. Levine, and 6 more authors

arXiv preprint arxiv:2509.17862, 2025

arXiv Bib HTML

@article{sahoo2025opencatalyst2025oc25,
  title = {The Open Catalyst 2025 (OC25) Dataset and Models for Solid-Liquid Interfaces},
  author = {Sahoo, Sushree Jagriti and Maraschin, Mikael and Levine, Daniel S. and Ulissi, Zachary and Zitnick, C. Lawrence and Varley, Joel B and Gauthier, Joseph A. and Govindarajan, Nitish and Shuaibi, Muhammed},
  journal = {arXiv preprint arxiv:2509.17862},
  year = {2025},
  url = {https://arxiv.org/abs/2509.17862},
  archiveprefix = {arXiv},
  primaryclass = {cond-mat.mtrl-sci}
}

Molecular Crystals/ML

FastCSP: Accelerated Molecular Crystal Structure Prediction with Universal Model for Atoms

Vahe Gharakhanyan, Yi Yang, Luis Barroso-Luque, and 21 more authors

arXiv preprint arxiv:2508.02641, 2025

arXiv Bib HTML

@article{gharakhanyan2025fastcspacceleratedmolecularcrystal,
  title = {FastCSP: Accelerated Molecular Crystal Structure Prediction with Universal Model for Atoms},
  author = {Gharakhanyan, Vahe and Yang, Yi and Barroso-Luque, Luis and Shuaibi, Muhammed and Levine, Daniel S. and Michel, Kyle and Bernat, Viachaslau and Dzamba, Misko and Fu, Xiang and Gao, Meng and Liu, Xingyu and Noori, Keian and Purvis, Lafe J. and Rao, Tingling and Wood, Brandon M. and Rizvi, Ammar and Uyttendaele, Matt and Ouderkirk, Andrew J. and Daraio, Chiara and Zitnick, C. Lawrence and Boromand, Arman and Marom, Noa and Ulissi, Zachary W. and Sriram, Anuroop},
  journal = {arXiv preprint arxiv:2508.02641},
  year = {2025},
  url = {https://arxiv.org/abs/2505.08763},
  archiveprefix = {arXiv},
  primaryclass = {physics.chem-ph}
}

Catalysis/ML

Open Catalyst Experiments 2024 (OCx24): Bridging Experiments and Computational Models

Jehad Abed, Jiheon Kim, Muhammed Shuaibi, and 17 more authors

2024

arXiv Bib HTML

@article{abed2024opencatalystexperiments2024,
  title = {Open Catalyst Experiments 2024 (OCx24): Bridging Experiments and Computational Models},
  author = {Abed, Jehad and Kim, Jiheon and Shuaibi, Muhammed and Wander, Brook and Duijf, Boris and Mahesh, Suhas and Lee, Hyeonseok and Gharakhanyan, Vahe and Hoogland, Sjoerd and Irtem, Erdem and Lan, Janice and Schouten, Niels and Vijayakumar, Anagha Usha and Hattrick-Simpers, Jason and Kitchin, John R. and Ulissi, Zachary W. and van Vugt, Aaike and Sargent, Edward H. and Sinton, David and Zitnick, C. Lawrence},
  year = {2024},
  url = {https://arxiv.org/abs/2411.11783},
  archiveprefix = {arXiv},
  primaryclass = {cond-mat.mtrl-sci}
}

Catalysis/ML

Open Catalyst 2020 (OC20) Dataset and Community Challenges

Lowik Chanussot, Abhishek Das, Siddharth Goyal, and 14 more authors

ACS Catalysis, Apr 2021

DOI Bib HTML

@article{doi:10.1021/acscatal.0c04525,
  title = {Open Catalyst 2020 (OC20) Dataset and Community Challenges},
  author = {Chanussot, Lowik and Das, Abhishek and Goyal, Siddharth and Lavril, Thibaut and Shuaibi, Muhammed and Riviere, Morgane and Tran, Kevin and Heras-Domingo, Javier and Ho, Caleb and Hu, Weihua and Palizhati, Aini and Sriram, Anuroop and Wood, Brandon and Yoon, Junwoong and Parikh, Devi and Zitnick, C. Lawrence and Ulissi, Zachary},
  journal = {ACS Catalysis},
  year = {2021},
  month = apr,
  volume = {11},
  number = {10},
  pages = {6059-6072},
  doi = {10.1021/acscatal.0c04525},
  url = {https://doi.org/10.1021/acscatal.0c04525},
}

Catalysis/ML
Accelerated discovery of CO2 electrocatalysts using active machine learning

Miao Zhong, Kevin Tran, Yimeng Min, and 19 more authors

Nature, May 2020

Abs DOI Bib HTML

The rapid increase in global energy demand and the need to replace carbon dioxide (CO2)-emitting fossil fuels with renewable sources have driven interest in chemical storage of intermittent solar and wind energy1,2. Particularly attractive is the electrochemical reduction of CO2 to chemical feedstocks, which uses both CO2 and renewable energy3-8. Copper has been the predominant electrocatalyst for this reaction when aiming for more valuable multi-carbon products9-16, and process improvements have been particularly notable when targeting ethylene. However, the energy efficiency and productivity (current density) achieved so far still fall below the values required to produce ethylene at cost-competitive prices. Here we describe Cu-Al electrocatalysts, identified using density functional theory calculations in combination with active machine learning, that efficiently reduce CO2 to ethylene with the highest Faradaic efficiency reported so far. This Faradaic efficiency of over 80 per cent (compared to about 66 per cent for pure Cu) is achieved at a current density of 400 milliamperes per square centimetre (at 1.5 volts versus a reversible hydrogen electrode) and a cathodic-side (half-cell) ethylene power conversion efficiency of 55 ± 2 per cent at 150 milliamperes per square centimetre. We perform computational studies that suggest that the Cu-Al alloys provide multiple sites and surface orientations with near-optimal CO binding for both efficient and selective CO2 reduction17. Furthermore, in situ X-ray absorption measurements reveal that Cu and Al enable a favourable Cu coordination environment that enhances C-C dimerization. These findings illustrate the value of computation and machine learning in guiding the experimental exploration of multi-metallic systems that go beyond the limitations of conventional single-metal electrocatalysts.
@article{zhong2020accelerated, title = {Accelerated discovery of CO2 electrocatalysts using active machine learning}, author = {Zhong, Miao and Tran, Kevin and Min, Yimeng and Wang, Chuanhao and Wang, Ziyun and Dinh, Cao-Thang and De Luna, Phil and Yu, Zongqian and Rasouli, Armin Sedighian and Brodersen, Peter and Sun, Song and Voznyy, Oleksandr and Tan, Chih-Shan and Askerka, Mikhail and Che, Fanglin and Liu, Min and Seifitokaldani, Ali and Pang, Yuanjie and Lo, Shen-Chuan and Ip, Alexander and Ulissi, Zachary and Sargent, Edward H.}, journal = {Nature}, year = {2020}, month = may, volume = {581}, number = {7807}, pages = {178--183}, doi = {10.1038/s41586-020-2242-8}, url = {https://doi.org/10.1038/s41586-020-2242-8}, issn = {1476-4687}, refid = {Zhong2020} }