UC San Diego HCI Ph.D. student

Making AI tools that sharpen design judgment.

I study how interfaces help designers compare options, reason through tradeoffs, and decide what is worth making.

Cognitive Science Ph.D. student at UC San Diego, advised by Prof. Steven P. Dow in ProtoLab.

Thesis thread Compare, choose
Home base UCSD ProtoLab
Methods Build, test, iterate
Sirui Tao portrait
Research question How can interfaces make better design decisions visible?
Design loop Vibes -> variables -> value

Thesis thread

Taste is a research problem.

When AI can generate ten options in a minute, the hard part is not getting more options. It is learning what differs, what matters, and why one direction is worth pursuing.

Design principle

Good interfaces should make comparison easier: show what changed, what evidence exists, and which decision comes next.

Why now

Why this work matters now

AI makes it easy to produce variants; my question is how people learn to choose well.

01

More output does not mean more taste.

When generation is cheap, the scarce work is comparison: seeing dimensions, tradeoffs, and evidence across options.

02

Everyone is closer to the prototype.

Designers, researchers, PMs, and engineers all shape early artifacts now. Interfaces need to support shared reasoning before decisions harden.

03

Speed still needs reflection.

Fast cycles are useful only if teams keep room for critique, incubation, and explaining why a direction is better.

Research focus

Where I study judgment in practice.

Design judgment

Human-AI for Design

Interfaces for exploring generated options with visible dimensions, constraints, and consequences.

Build -> measure

Evaluation and Measurement

Studies and metrics for diversity, verification cost, calibration, reliance, and iteration that actually changes the artifact.

In-situ intelligence

Embodied and Mixed Reality

Systems that bring context-aware assistance into spatial tasks, mixed reality, and everyday environments.

Featured work

Things I built and tested.

All projects

Recent signal

Recent signals.

All news

HotSpot got selected as a CVPR 25 Highlight!

Selected publications

Papers worth opening first.

  1. Sirui Tao, William P. McCarthy, and Steven P. Dow
    In Herding CATs: Making Sense of Creative Activity Traces (CHI 2026 Workshop), Feb 2026
    Workshop Position Paper
  2. CVPR
    hotspot.png
    Zimo Wang, Cheng Wang, Taiki Yoshino, Sirui Tao, Ziyang Fu, and Tzu-Mao Li
    In Conference on Computer Vision and Pattern Recognition (Highlight), Jun 2025
  3. CHI
    designweaver.png
    Sirui Tao, Ivan Liang, Cindy Peng, Zhiqing Wang, Srishti Palani, and Steven Dow
    In Conference on Human Factors in Computing Systems, Apr 2025
  4. NeurIPS
    physion.gif
    Daniel Bear, Elias Wang, Damian Mrowca, Felix Binder, Hsiao-Yu Tung, Pramod RT, Cameron Holdaway, Sirui Tao, Kevin Smith, Fan-Yun Sun, Fei-Fei Li, Nancy Kanwisher, Josh Tenenbaum, Dan Yamins, and Judith Fan
    In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, Dec 2021
Open full publication list

Research opportunities

For students who like messy questions.

I like working with undergraduate and master's students who can stay curious about a messy question long enough to make it sharper.

You do not need to arrive as an expert. It helps if you enjoy reading closely, making prototypes, testing claims, and explaining what changed your mind.

When reaching out

  1. Read the research-start post.
  2. Email s1tao@ucsd.edu with subject "UCSD Research Interest".
  3. Include a 1-page CV or resume and a 3-5 sentence note on the questions or domains you care about.
Read the post

Connect

Find me around the web.