Jiayun (Peter) Wang

Postdoc, California Institute of Technology | peterw at caltech dot edu

prof.jpg

I am a postdoctoral researcher in the Anima AI + Science Lab and the Computing + Mathematical Sciences Department at California Institute of Technology. Prior to joining Caltech, I completed my Ph.D. in Vision Science and Berkeley AI Research (BAIR) at UC Berkeley, where I worked with Stella Yu on fundamental machine learning and computer vision models and Meng Lin on applying them to healthcare.

I am on the 2024-2025 job market looking for full-time positions. Please feel free to reach out!

Research Interest: My research lies at the intersection of machine learning, computer vision and AI for healthcare. My research highlights (more details):

  1. Self-Supervised Learning. SSL beyond semantic classification: SSL for geometry (ECCV’24) and for physics (arXiv’24).
  2. Efficient AI Algorithms. AI models as duality to the data. Models can be made efficient if they are aware of data structures, such as orthogonality (CVPR’20) and recurrence (WACV’23).
  3. Healthcare Applications. Efficient AI4Health methods with reduced human supervision. Applications include medical imaging (arXiv’24) and assistive diagnosis (MICCAI’24).

news

Aug 01, 2024 Pose-Aware Self-Supervised Learning accepted to ECCV 2024 as an oral presentation! 🎊
Apr 29, 2024 INSIGHT accepted to MICCAI 2024!
Dec 19, 2023 Deep Multimodal Fusion won the best paper at ML4H 2023! 🏆

selected publications

  1. CVPR
    orth.png
    Orthogonal Convolutional Neural Networks
    Jiayun WangYubei ChenRudrasis Chakraborty, and Stella Yu
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020
  2. WACV
    rpg.png
    Compact and Optimal Deep Learning with Recurrent Parameter Generators
    Jiayun WangYubei ChenStella YuBrian Cheung, and Yann LeCun
    In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2023
  3. ECCV
    traj.png
    Pose-Aware Self-Supervised Learning with Viewpoint Trajectory Regularization
    Jiayun WangYubei Chen, and Stella Yu
    In European Conference on Computer Vision, 2024