Pinned Met the great Don Norman and even got a selfie + a “To Sirui” signed “Yellow Book”! 
Research and design
Design notebook.
DesignWeaver, papers I return to, and a little La Jolla.
Selected work
Questions made tangible.
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.
My work with Steven P. Dow and conversations with Don Norman and many others keep shaping how I think about taste and design judgment.
Updates
Recent signals.
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! 
HotSpot got selected as a CVPR 25 Highlight!
Selected publications
Papers worth opening first.
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 an implicit-surface argument needs more than the usual eikonal condition—especially around convergence, stability, topology, or surface area.
This paper helps when you need a reproducible benchmark for asking whether a model predicts physical outcomes in human-like ways.
Research notes
Inside DesignWeaver.
Follow the design process and inspect the evidence from the study.
From the design brief to generated images, with the full system diagram.
Compare the study interfaces and inspect participant ratings and image-diversity results.
Making the miniature
A little La Jolla.
Generated studies, a reconstructed shape, and the architecture I built for the miniature.
See what the reconstruction recovered and which architectural details needed deliberate modeling.