Alicia Zeng

Co-founder and CTO, Erised AIPhD Biophysics, UC Berkeley

I build AI that explains how complex physical and biological systems work.

NeurIPS 2026 oral, sole author NeurIPS 2025 Nature Biomedical Engineering 2026 Thesis

Where number, time and space are represented in one listener’s cortex. Explore the brain viewer yourself

As the brain works, the blood flowing through it changes its magnetism by a hair. An MRI scanner can follow that change across the whole cortex, and from the pattern it records we can now tell what a person is listening to, and something of what they are imagining. A thought can be read from the magnetism of blood.

That fact leads back to the question that first drew me to science. Atoms are cold and interchangeable, yet assemblies of them make cells, sentences, and the minds that read them. How does meaning arise from matter? That has been my question ever since. After two years in the business school at Peking University, it took me to philosophy and physics at Vanderbilt, then to the physics of living matter in Vijay Balasubramanian’s laboratory at the University of Pennsylvania, and then to the biophysics program at UC Berkeley. There I joined Jack Gallant’s lab and found a second intellectual home at the Redwood Center for Theoretical Neuroscience with Bruno Olshausen, who later served on my thesis committee.

At Berkeley the question became an empirical one, and that scanner was the instrument. Its recordings are noisy, high-dimensional, and only indirectly related to the activity of neurons. The method for reading them came from the Redwood Center: sparse coding, which assigns each learned axis a single meaning. With it, I used machine learning to map how abstract concepts such as number, space, and time are represented across the human cortex. A second project went the other way. Drawing on the understanding such models provide, we built closed-loop deep brain stimulation that decodes a patient’s movement from the brain itself and adjusts therapy for Parkinson’s disease in real time.

Both projects point to the same conclusion. The main constraint on scientific progress is seldom the quality of our models. We overestimate our own ingenuity: the hypotheses we are able to write down form a measure-zero subset of what is possible, and progress has come more often from new and better measurements, made in the environments where the systems of interest operate, than from new ideas. This is a hopeful conclusion, because instruments can be built. That is what Erised is for. Understanding the world at its smallest scales is a way to help the world and the living things in it.

Erised AI builds AI-native systems and world models for nanoscience and metrology: instruments that get smarter with every measurement, because the measurement and the model are designed together. I co-founded it and am its CTO, leading the AI, data and computational microscopy side.

The argument above is the one in my thesis introduction; the note makes it at length.

All research

aliciaxiaozeng@gmail.com

If you are building, buying or backing nanoscale measurement, or want to work on the models behind it, I would like to hear from you.

Google Scholar LinkedIn GitHub Erised AI

Outside work: philosophy, ballet, hiking, and hosting friends for dinner.