Alexander Tong

Alexander Tong is a Principal Investigator at Aithyra in Vienna, Austria. His research sits at the intersection of machine learning and biology, with a focus on generative modeling, flow matching, and optimal transport. He applies these techniques to problems in protein design and single-cell developmental dynamics. Previously, Tong was a postdoctoral researcher at Mila in Montreal, where he worked with Yoshua Bengio, following a PhD in Computer Science from Yale University. He also co-founded Dreamfold, a company focused on generative protein design, and now aims to make biological systems as designable as software.

AI2050 Project

While artificial intelligence excels at generating images and text, it struggles to design functional molecules. Current models learn molecular structures from static data, omitting the physical laws that govern how molecules move and interact — a key reason many computationally designed molecules fail in wet-lab testing.

Tong’s project addresses this limitation by embedding physical dynamics directly into generative AI. Using flow matching and optimal transport, his models estimate the likelihood of how a molecule changes shape over time, rather than producing static snapshots. The goal is to move molecular design toward a predictable engineering discipline, accelerating the development of targeted therapeutics and sustainable enzymes.