Cher-Tian Ser

Hello! I am broadly interested in using computational methods and machine learning techniques to help scientists design and develop new catalytic and energy materials more efficiently. I am currently supervised by Alán Aspuru-Guzik.

I was an intern at Osmo with the Machine Learning team where I designed models to predict olfactory properties. Before that, I was a Research Engineer at the Institute of High Performance Computing in the Agency for Science, Technology and Research (A*STAR) in Singapore.

I graduated with a B.Sc (Hons) in Chemistry from the National University of Singapore. I was also part of the University Scholars Programme, a selective interdisciplinary and multidisciplinary academic program.

I currently volunteer with Pueblo Science, an organization based in Toronto that helps underprivileged communities have greater access to STEM education.

selected publications

Bulky phosphine ligands promote palladium-catalyzed protodeboronation

Cher Tian Ser, Han Hao, Sergio Pablo-Garcı́a, and 4 more authors

Journal of the American Chemical Society, 2025

Abs HTML

Bulky phosphine ligands can accelerate protodeboronation of arylboronic acids within the context of the Suzuki-Miyaura cross-coupling.
Does this smell the same? Learning representations of olfactory mixtures using inductive biases

Gary Tom, Cher Tian Ser, Ella M Rajaonson, and 4 more authors

Machine Learning: Science and Technology, 2025

Abs HTML

We use molecular representations to generate mixture representations for predicting olfactory similarity.
El Agente: An autonomous agent for quantum chemistry

Yunheng Zou, Austin H Cheng, Abdulrahman Aldossary, and 8 more authors

Matter, 2025

Abs HTML

We use LLMs to run complex quantum chemistry calculations using plain-text prompts.
Efficient Evolutionary Search Over Chemical Space with Large Language Models

Haorui Wang, Marta Skreta, Cher Tian Ser, and 8 more authors

In The Thirteenth International Conference on Learning Representations, 2025

Abs HTML

We use LLMs as genetic operators in evolutionary algorithms to generate high-performing molecules.