Chang Xiao (肖昶)

changxiao0731 at gmail.com

prof_pic.jpg

Presentation at Adobe Summit 2024.

I’m a Research Scientist at Adobe Research. I received my Ph.D. in Computer Science from Columbia University. I am a recipient of the Snap Research Fellowship (2019) and the Cheung-Kong Innovation Doctoral Fellowship.

My research lie at the intersection of Human-Computer Interaction, Generative AI, Visual Computing and AR/VR. I am particularly interested in developing human-centered interaction techniques that are intuitive, immersive, and natural. This work spans three key areas: (1) Enablement: Leveraging computational design and developing AI-driven sensing methods to make passive physical object/environment interactive, as if they were digital. (2) Creation: Empowering users to design interactive experiences with ease and creativity by building new GenAI systems. (3) Evaluation: Studying human factors to ensure our techniques align with human values, needs, and perceptions.

My research outcomes have had various impacts beyond academia. At Adobe, I have presented my research twice during Adobe’s annual event, Summit Sneaks (2022, 2024). These features have also been integrated into Adobe’s product. My past work has received more than 50 media interviews and coverages, including by CNN, Adweek, CACM, and IEEE Spectrum. I also hold 10+ US patents.

Here is my CV.

news

Oct, 2024 Attending UIST 2024 in Pittsburgh. Come talk to me if you’re interested in Summer 2025 internship at Adobe Research!
Aug, 2024 Serve as an Associate Chair (AC) for CHI 2025.
Jul, 2024 One paper by my intern Monde accepted at SIGGRAPH Asia 2024 (Journal Track)!
Jul, 2024 One paper by my intern Xia accepted at UIST 2024!
Mar, 2024 I have presented my research on Generative AI at Adobe Summit Sneaks 2024, with basketball legend Shaquille O’Neal! Check out video here.

selected publications

  1. HCIVision
    reactfold.png
    ReactFold: Towards Camera-based Tangible Interaction on Passive Paper Artifacts
    Chang Xiao
    ACM International Conference on Tangible, Embedded, and Embodied Interaction, TEI, 2025
  2. motion.png
    Evaluating Visual Perception of Object Motion in Dynamic Environments
    Budmonde Duinkharjav, Jenna Kang, Gavin Miller, Chang Xiao, and Qi Sun
    ACM Transactions on Graphics, SIGGRAPH Asia (Journal Track), 2024
  3. sonifyar.png
    SonifyAR: Context-Aware Sound Effect Generation in Augmented Reality
    Xia Su, Jon Froehlich, Eunyee Koh, and Chang Xiao
    ACM Symposium on User Interface Software and Technology, UIST, 2024
  4. HCIAR/VRVision
    moirewidgets.png
    MoiréWidgets: High-Precision, Passive Tangible Interfaces via Moiré Effect
    Daniel Campos Zamora, M. Doga Dogan, Alexa F. Siu, Eunyee Koh, and Chang Xiao
    ACM Conference on Human Factors in Computing Systems, CHI, 2024
  5. imarker.jpg
    iMarker: Instant and True-to-scale AR with Invisible Markers
    Chang Xiao, Ryan A. Rossi, and Eunyee Koh
    ACM Symposium on User Interface Software and Technology, UIST Poster (Technology behind Adobe’s Summit Sneaks Presentation), 2022
  6. AI/MLSecurity
    snooping.png
    Can one hear the shape of a neural network?: Snooping the GPU via Magnetic Side Channel
    Henrique Teles Maia, Chang Xiao, Dingzeyu Li, Eitan Grinspun, and Changxi Zheng
    USENIX Security, 2022
  7. HCIAR/VRVision
    moire.png
    MoiréBoard: A Stable, Accurate and Low-cost Camera Tracking Method
    Chang Xiao, and Changxi Zheng
    ACM Symposium on User Interface Software and Technology, UIST, 2021
  8. deepcad.png
    DeepCAD: A Deep Generative Network for Computer-Aided Design Models
    Rundi Wu, Chang Xiao, and Changxi Zheng
    International Conference on Computer Vision, ICCV, 2021
  9. backtrack.png
    BackTrack: 2D Back-of-device Interaction through Front Touchscreen
    Chang Xiao, Karl Bayer, Changxi Zheng, and Shree K. Nayar
    ACM Conference on Human Factors in Computing Systems, CHI, 2021
  10. rp2k.png
    RP2K: A Large-Scale Retail Product Dataset for Fine-Grained Image Classification
    Jingtian Peng, Chang Xiao, and Yifan Li
    arxiv preprint, 2006.12634, 2021
  11. AI/MLVision
    one.jpg
    One Man’s Trash is Another Man’s Treasure: Resisting Adversarial Examples by Adversarial Examples
    Chang Xiao, and Changxi Zheng
    Conference on Computer Vision and Pattern Recognition, CVPR, 2020
  12. kwta.png
    Enhancing Adversarial Defense by k-Winners-Take-All
    Chang Xiao, Peilin Zhong, and Changxi Zheng
    International Conference on Learning Representations, ICLR (Spotlight, top 3%), 2020
  13. mwu.png
    Rethinking Generative Mode Coverage: A Pointwise Guaranteed Approach
    Peilin Zhong*, Yuchen Mo*, Chang Xiao*, Pengyu Chen, and Changxi Zheng
    (*equal contribution) Neural Information Processing Systems, NeurIPS, 2019
  14. vidgets.jpg
    Vidgets: Modular Mechanical Widgets for Mobile Devices
    Chang Xiao, Karl Bayer, Changxi Zheng, and Shree K. Nayar
    ACM Transactions on Graphics, SIGGRAPH (50K+ views on Youtube), 2019
  15. mech.png
    Mechanics-Aware Modeling of Cloth Appearance
    Montazerim Zahra, Chang Xiao, Raymond Yun Fei, Changxi Zheng, and Shuang Zhao
    IEEE Transactions on Visualization and Computer Graphics, TVCG, 2019
  16. bourgan.png
    BourGAN: Generative Networks with Metric Embeddings
    Chang Xiao, Peilin Zhong, and Changxi Zheng
    Neural Information Processing Systems, NeurIPS (Spotlight, top 3%), 2018
  17. fontcode.png
    Fontcode: Embedding Information in Text Documents Using Glyph Perturbation
    Chang Xiao, Cheng Zhang, and Changxi Zheng
    ACM Transactions on Graphics, SIGGRAPH (100K+ Views on Youtube), 2018
  18. PhysicsGraphics
    cleo.png
    Two-color and 3d Phase-amplitude Modulation Holograms
    Adam Overvig, Sajan Shrestha, Chang Xiao, Changxi Zheng, and Nanfang Yu
    Conference on Lasers and Electro-Optics, CLEO, 2018