Adji Bousso Dieng 2022 Early Career Fellow
Hard Problem Leverage AI to address humanity’s greatest challenges and deliver positive benefits for all

Adji Bousso Dieng is an Assistant Professor of Computer Science at Princeton University where she leads Vertaix on research at the intersection of artificial intelligence and the natural sciences. She is affiliated with the High Meadows Environmental Institute (HMEI). She is also a Research Scientist at Google AI and the founder and President of the nonprofit The Africa I Know. She’s recently been named the Annie T. Randall Innovator of 2022 for her research and advocacy. Dieng received her Ph.D. from Columbia University where she was advised by David Blei and John Paisley. Her doctoral work received many recognitions, including a Google Ph.D. Fellowship in Machine Learning, a rising star in Machine Learning nomination, and the Savage Award. She hails from Kaolack, Senegal.

AI2050 Project

Through this fellowship, Adji will be using AI to design novel materials that can be used in healthcare, for carbon capture, and in other applications requiring the ability to selectively capture and release small molecules. She will use techniques from Bayesian statistics which allow for more flexible incorporation of expert knowledge. This will advance Hard Problem 4 (Opportunities) by using AI to realize scientific applications that are not possible today and apply them to climate change, drug discovery, and other pressing problems.

Project Artifacts

Q. Nguyen and A. B. Dieng. Quality-weighted vendi scores and their application to diverse experimental design. ICML. 2024.

T. Liu, Q. Nguyen, A. B. Dieng, and D. Gomez-Gualdron. Diversity-driven, efficient exploration of a MOF design space to optimize MOF properties: application to NH3 adsorption. ChemRxiv. 2024.

A.N. Rubungo, C. Arnold, B. Rand, and A.B. Dieng. LLM-Prop: predicting physical and electronic properties of crystalline solids from their text descriptions. arXiv. 2023.

A. Pasarkar and A.B. Dieng. Cousins of the vendi score: a family of similarity-based diversity metrics for science and machine learning. arXiv. 2023.

A. Pasarkar, G. Bencomo, S. Olsson, and A.B. Dieng. Vendi sampling for molecular simulations: diversity as a force for faster convergence and better exploration. ChemRxiv. 2023.

AI2050 Community Perspective — Adji Bousso Dieng (2023)