Header Image
Brian Cheung

Brian Cheung

I study intelligence in many forms: natural, artificial and collective. How does it emerge? Where is it going?

Assistant Professor leading the Discovery Lab in the Department of Bioengineering and Therapeutic Sciences at the University of California, San Francisco.

bcheung@ucsf.edu google scholar @thisismyhat briancheung

Papers I'm thinking about lately (all of my papers)

  • The Platonic Representation Hypothesis Minyoung Huh*, Brian Cheung*, Tongzhou Wang*, Phillip Isola*, ICML 2024 Oral

    TLDR: As all models continue to improve, the representations they use are converging.

    Paper Code Blog
  • Words That Make Language Models Perceive Sophie L. Wang, Phillip Isola, Brian Cheung, arXiv 2025

    TLDR: Asking the model to 'see' or 'hear' can push a purely text-trained language model towards the representations of purely image-trained or purely-audio trained encoders.

    Paper Code Blog
  • What if Eye...? Computationally Recreating Vision Evolution Kushagra Tiwary*, Aaron Young*, Zaid Tasneem, Tzofi Klinghoffer, Akshat Dave, Tomaso Poggio, Dan-Eric Nilsson, Brian Cheung**, Ramesh Raskar**

    TLDR: We trained an eyeball. Lensed eyes, scaling laws and more emerge from our simulation of visual evolution.

    Paper Website Blog