Zuchen Li

Zuchen Li李祖臣

Undergraduate Student · University of Michigan, Ann Arbor

Aiming for a PhD in HCI / AI.

about

I am an undergraduate at the University of Michigan, Ann Arbor, triple majoring in Computer Science, Data Science, and Statistics with a minor in History. Previously, I studied Statistics & Computer Science at the University of Illinois Urbana-Champaign, with a minor in Meteorology. I build and study systems where humans and AI meet — from real-time co-creation with generative models to sensing systems that understand their physical context.

Research interests: Human–AI Interaction · Context-Aware Intelligent Systems · Ubiquitous Sensing · AI4Science

research

* equal contribution

Preprint 2026 · CHI 2027 (under review)

Generative Tutorial: Towards Live Contextualized Visual Instructions for Physical Tasks

Muzhe Wu*, Zuchen Li*, Xu Wang, Anhong Guo

project arXiv PDF video

Visual instructions for physical tasks are typically authored in one context and followed in another, requiring users to translate demonstrated tools, materials, and spatial relationships into their own environment. We introduce Generative Tutorial, a conceptual framework for live visual instruction that depicts intended outcomes and actions within the user's environment and task flow. A formative evaluation of state-of-the-art image and video generation identifies failures and potential benefits across 15 physical tasks. Drawing on these findings, we build an augmented-reality prototype system that proactively generates goal images and demonstration videos using observed workspace context and predicted visual outcomes of preceding actions. A 24-participant lab study found higher task performance quality, greater perceived workspace correspondence, and shorter step-confirmation intervals with the system than with pre-authored guidance.

ACM MobiCom 2026 · Demo · Austin, TX

MoiréDeform: Towards Fine-Grained Deformation Sensing through Everyday Moiré

Linzhen Zhu*, Zuchen Li*, Weihao Jin, Hyunmin Park, Alanson Sample, Ke Sun

project interactive talk video

Every time we sit, lean, or breathe, we gently deform the surfaces that hold us. MoiréDeform turns the mesh of an unmodified office chair into a sensor: a low-cost camera behind the backrest compares each frame with a reference of the empty chair, so the weave acts as virtual moiré layers that amplify subtle deformation into large, visible fringes. From them, a lightweight network reconstructs the breathing waveform live, and the moiré envelope's centroid becomes a continuous lean-to-steer joystick — no markers, no wearables, and the person is never in frame. In a preliminary study (5 users, 100 minutes), respiratory-rate error fell from 2.07 to 0.71 breaths/min relative to physical-marker tracking.

Under double-blind review

A Mysterious AI Security & Privacy Project

Co-first author

details

What can today's AI models figure out about you from a single everyday photo — and how much of that can you take back? This project studies hidden privacy risks in visual AI and builds tools that help people see, and control, what leaks before they share. The paper is under double-blind review, so the name, details, and demo stay under wraps for now.

CHI 2027 · under review

RespiraFrame: On-Frame Respiratory Monitoring via Electrical Impedance Tomography and Bone-Conduction Acoustics

Experimental design & evaluation

project video

RespiraFrame is an eyeglass frame that monitors respiration through two complementary channels: a bone-conduction microphone beside the nose that hears breathing through the face rather than the air, and electrical impedance tomography from eight soft dry electrodes on the nose pads and temples. A two-branch network fused with attention recognizes five abnormal respiratory events and distinguishes nasal vs. oral, deep vs. shallow breathing, and breath holding — 92.5% for abnormal events in a 19-participant lab study, under 3 points of change at 80 dB of noise, and 87.6% over 30 hours of in-the-wild wear.

other projects

experience

  • Human Centered Computing Lab, UMich — Undergraduate Research Assistant 2025.09 → now
    • Generative Tutorial (co-first author; with Profs. Anhong Guo and Xu Wang): co-developed a conceptual framework and AR system for live contextualized visual instruction that grounds physical-task goals in users' workspaces and proactively generates workspace-specific goal images and demonstration videos by propagating observed and predicted visual states across task dependencies; co-led a formative evaluation of 176 generated artifacts across 15 tasks and a 24-participant comparative study, showing improved task quality, perceived workspace correspondence, and shorter step-confirmation intervals over pre-authored guidance.
    • MoiréDeform (co-first author, ACM MobiCom '26 Demo; with Profs. Alanson Sample and Ke Sun): developed a low-cost camera-based sensing approach that exploits naturally occurring woven textures as virtual moiré layers to amplify subtle surface deformation, enabling continuous body-lean interaction and respiratory waveform/rate sensing on an unmodified mesh chair without instrumenting the user or surface; reduced respiratory-rate MAE from 2.07 to 0.71 breaths/min relative to physical-marker tracking.
    • RespiraFrame (with Prof. Junyi Zhu): contributed to the experimental design and evaluation of an eyeglass-based multimodal respiratory sensing system combining bone-conduction acoustics and electrical impedance tomography (EIT); designed evaluation protocols spanning respiratory behaviors, motion and environmental interference, a three-day semi-wild study, and repeated wear over a four-week longitudinal study.
    • A Mysterious AI Security & Privacy Project (co-first author; under double-blind review): studies hidden privacy risks in visual AI — what today's models can infer from everyday photos — and builds tools that help people see and control what leaks before they share. Details withheld until the review is over.
  • Generative AI for Music and Audio, UMich — Research Assistant, advised by Prof. Herman Dong 2025.09 → now
    Investigating real-time human–GenAI co-creation for controllable music generation, focusing on interaction mechanisms that preserve user agency, expressive control, and iterative creative feedback; prototyping gesture-driven interaction techniques that connect embodied user input to real-time musical control and generative model behavior.
  • Energy Distance Dimension Reduction, UMich — Selected Researcher, Undergraduate Research Program in Statistics (URPS), advised by Prof. Kerby Shedden 2025.01 → 2025.05
    Developed engression and sufficient dimension reduction methods for multilevel, dyadic, and longitudinal wearable data from bone marrow transplant patients, addressing non-i.i.d. structure not handled by existing methodology; implemented SDR algorithms in JAX with GPU acceleration, achieving approximately 7,000× speedup over the original method for U-statistic computation on large sensor data series.
  • Lab of Atmospheric and Earth System Sciences, Nanjing University — Summer Research Intern, advised by Prof. Minghuai Wang 2024.05 → 2024.08
    Studied statistical machine learning methodologies for integrating real-world sensor observations with simulated atmospheric data, enabling inference and prediction of aerosol–cloud interactions across larger spatial and temporal scales.
  • E2-E Lab, UIUC — Undergraduate Research Assistant 2023.08 → 2024.05
    Conducted airflow experiments and processed PIV/camera data using Python, OpenCV, and OpenPIV for flow-field reconstruction and particle tracking; performed CFD simulations in ANSYS Fluent to analyze particle–airflow interactions in complex 3D geometries.

awards

  • UROP Summer Engineering Fellowship, University of Michigan 2026
  • University Honors, University of Michigan 2024 → 2026
  • Outstanding Research Paper Award, IMMC Greater China Round — top 1.875% of 800+ teams 2022
  • Finalist Research Paper Award, IMMC International Round — top 8.75% internationally 2022

etc

  • Waseda University, Tokyo — Summer Intern 2025.06 → 2025.08
    Researched postwar Japanese literature and history, analyzing literary works in relation to historical memory, identity, and social transformation in postwar Japan.
  • The Michigan Daily — Student Reporter, Photographer & Videographer 2025.08 → 2026.07
    Produced campus and local news coverage through interviews, field reporting, photography, and video, translating on-the-ground observations into written and multimedia stories. Some frames end up in the gallery.
  • Kendo Club at the University of Michigan — Member
    Regular kendo practice focused on footwork, striking technique, partner drills, and traditional Japanese swordsmanship.
  • Michigan Backpacking Club — Member
    Group hiking and backpacking trips — outdoor navigation, trip planning, and teamwork.
  • Illinois Student Organization of Meteorology (ISTORM) — Student Forecaster
    Student chapter of the American Meteorological Society, focused on severe and hazardous weather forecasting.