Sirui Tao - HCI Researcher at UC San Diego

Thesis thread

Scaffolding taste in an age of generative abundance.

Scaffolding for Taste asks a simple question: when AI can make ten plausible options in a minute, how do people learn to notice the difference that matters? I study interfaces that support reflective practice: making a move, seeing what changed, comparing alternatives, and building better reasons for choosing one direction over another.

I am testing this frame across creative tools, learning environments, mixed reality, everyday robotics, and community or civic design settings: places where tools can help people notice viable options, weigh tradeoffs, and choose the next move.

My work with Steven P. Dow and conversations with Don Norman and many others keep shaping how I think about taste and design judgment.

Notes from Don Norman's talk ↗

Research focus

Design, Evaluate, Situate.

I keep testing the same loop: how to make alternatives comparable, let evidence sharpen the next question, and fit assistance to the situation where judgment happens.

Design lens

Human-AI for design thinking

I study interfaces that support design thinking beyond artifact generation: dimensional scaffolds that make the design space visible, variation mechanisms that expose alternatives, structured comparison that helps people reason across options, and staged fidelity that lets ideas mature from rough intent to defensible direction.

See DesignWeaver

Moves

01
Externalize useful dimensions so people can see what matters.
02
Use variation and structured comparison to reason across alternatives.
03
Move from coarse ideas to committed artifact choices through staged fidelity.

Exploring

Adjacent contexts for the same loop

These threads are places I test the same concern with judgment, agency, and evidence in context.

Situate Everyday robotics Integrating intelligence into robots so they can better assist people in everyday living and working contexts. Design Learner-centered AI Scalable support that keeps agency and the learning process visible. Evaluate Post-deployment iteration Using traces from real use to improve benefit and catch harm. Situate Community-centered tools Coordination and sensemaking for groups with shared ownership.

Motion note Inspired by motion craft from Stripe's design team and Katie Dill at Stripe Sessions. Interaction rules grounded by Jeffrey Heer and collaborators on animated transitions and CMU's Data Interaction Group .

Live field The visible Dot Orbit layer uses Paper Shaders by Paper; the restraint also follows the founder's design walkthrough.

Selected publications

Papers worth opening first.

CVPR
Full paper Coauthor 19 cites

HotSpot: Signed Distance Function Optimization with an Asymptotically Sufficient Condition

Zimo Wang, Cheng Wang, Taiki Yoshino, Sirui Tao, Ziyang Fu, and Tzu-Mao Li

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2025

Highlight
HotSpot: Signed Distance Function Optimization with an Asymptotically Sufficient Condition: When this paper helps. This paper helps when an implicit-surface argument needs more than the usual eikonal condition—especially around convergence, stability, topology, or surface area.
This paper helps when an implicit-surface argument needs more than the usual eikonal condition—especially around convergence, stability, topology, or surface area.

Look for

You are comparing objectives for reconstructing signed distance functions from unoriented points.

You need theoretical and experimental evidence about a screened-Poisson alternative.

It adds
A heat-loss objective with convergence and stability analysis, plus 2D and 3D reconstruction evidence and a natural surface-area penalty.
Its limit
The reported gains belong to the evaluated reconstruction settings; sparse boundaries and parameter choices can still produce failure modes.

I checked this against the paper and its official record on 2026-07-13.
Read the full evidence and citation context
DOI arXiv Bib PDF Video Code Website
@inproceedings{wang2025hotspot, title = {HotSpot: Signed Distance Function Optimization with an Asymptotically Sufficient Condition}, author = {Wang, Zimo and Wang, Cheng and Yoshino, Taiki and Tao, Sirui and Fu, Ziyang and Li, Tzu-Mao}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, pages = {1276--1286}, publisher = {IEEE}, doi = {10.1109/CVPR52734.2025.00127}, arxiv = {2411.14628}, url = {https://openaccess.thecvf.com/content/CVPR2025/html/Wang_HotSpot_Signed_Distance_Function_Optimization_with_an_Asymptotically_Sufficient_Condition_CVPR_2025_paper.html}, note = {Highlight}, month = {jun}, year = {2025} }
CHI
Full paper First author 48 cites

DesignWeaver: Dimensional Scaffolding for Text-to-Image Product Design

Sirui Tao, Ivan Liang, Cindy Peng, Zhiqing Wang, Srishti Palani, and Steven P. Dow

In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems, Apr 2025
DesignWeaver: Dimensional Scaffolding for Text-to-Image Product Design: When this paper helps. This paper helps when a blank prompt box is asking novices to supply design vocabulary they have not had a chance to learn.
This paper helps when a blank prompt box is asking novices to supply design vocabulary they have not had a chance to learn.

Look for

You are designing dimensional scaffolds for text-to-image exploration.

You want evidence about prompt language, visual diversity, novelty, and rising expectations.

It adds
A palette that externalizes product-design dimensions, grounded in expert practice and evaluated with 52 novice designers.
Its limit
The study used one chair-design task with novices, and richer prompts did not reliably improve satisfaction or expectation alignment.

I checked this against the paper and its official record on 2026-07-13.
Read the full evidence and citation context
DOI arXiv Bib PDF Video Code Website
@inproceedings{tao2024designweaver, title = {DesignWeaver: Dimensional Scaffolding for Text-to-Image Product Design}, author = {Tao, Sirui and Liang, Ivan and Peng, Cindy and Wang, Zhiqing and Palani, Srishti and Dow, Steven P.}, booktitle = {Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems}, series = {CHI '25}, pages = {1--26}, publisher = {ACM}, doi = {10.1145/3706598.3714211}, arxiv = {2502.09867}, month = {apr}, year = {2025} }
NeurIPS
Full paper Coauthor 213 cites

Physion: Evaluating Physical Prediction from Vision in Humans and Machines

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
Physion: Evaluating Physical Prediction from Vision in Humans and Machines: When this paper helps. This paper helps when you need a reproducible benchmark for asking whether a model predicts physical outcomes in human-like ways.
This paper helps when you need a reproducible benchmark for asking whether a model predicts physical outcomes in human-like ways.

Look for

You are comparing object-centric and non-object-centric visual models with human judgments.

You need a common contact-prediction task across several simulated physical scenarios.

It adds
Eight scenario families, matched human and model evaluation, and released data and code for systematic comparison.
Its limit
Synthetic scenes and binary contact prediction do not establish broad real-world physical understanding.

I checked this against the paper and its official record on 2026-07-13.
Read the full evidence and citation context
arXiv Bib PDF Video Code Website
@inproceedings{bear2021physion, title = {Physion: Evaluating Physical Prediction from Vision in Humans and Machines}, author = {Bear, Daniel and Wang, Elias and Mrowca, Damian and Binder, Felix and Tung, Hsiao-Yu and RT, Pramod and Holdaway, Cameron and Tao, Sirui and Smith, Kevin and Sun, Fan-Yun and Li, Fei-Fei and Kanwisher, Nancy and Tenenbaum, Josh and Yamins, Dan and Fan, Judith}, booktitle = {Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks}, editor = {Vanschoren, J. and Yeung, S.}, volume = {1}, arxiv = {2106.08261}, url = {https://datasets-benchmarks-proceedings.neurips.cc/paper/2021/hash/d09bf41544a3365a46c9077ebb5e35c3-Abstract-round1.html}, month = {dec}, year = {2021} }

Open full publication list

Updates

Recent signals.

Full timeline

Mar 04, 2026

Pinned Met the great Don Norman and even got a selfie + a “To Sirui” signed “Yellow Book”!

Feb 25, 2026

Our CHI 2026 workshop position paper, What Happened and Why? Trace-Guided Micro-Episodes with Elicited User Explanations for Product Iteration, was accepted to Herding CATs - easily one of the best workshop names ever! The whole ProtoLab is going to Spain! Might be a UCSD party!

Apr 04, 2025

HotSpot got selected as a CVPR 25 Highlight!

Research opportunities

For students who like messy questions.

I like working with curious, motivated, and kind undergraduate and master's students, especially people who have a question they cannot stop poking at.

You do not need to show up as a polished researcher. It helps if you like reading carefully, making small prototypes, testing claims, looking honestly at evidence, and writing clearly about what changed.

The best fit is someone with real stake in a domain or problem, plus enough patience to turn that interest into a concrete study.

Reading closely Prototyping Evaluation Analysis Communication

Start here

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

Read the post Email interest

Connect

Find me around the web.

Advisor Lineage & Past Collaborations

Ph.D. Steven P. Dow HCI

Master's Steven P. Dow HCI Tzu-Mao Li Graphics

Undergrad Judith E. Fan Cognition & Intuitive Physics

Making AI tools that sharpen design judgment.