Yichao Cai

蔡逸超

71257158.png

"A good half of the art of living is resilience." — Alain de Botton

I am a second-year PhD candidate at the Australian Institute for Machine Learning (AIML), University of Adelaide, under the supervision of Prof. Javen Qinfeng Shi, Dr. Zhen Zhang, and Dr. Yuhang Liu. I received my M.S. and B.Eng. degrees in Instrument Science from Wuhan University of Technology.

My research lies at the intersection of representation learning, multimodal modeling, and causality. I aim to develop principled machine learning systems that can faithfully capture semantic structure—even in the presence of noise, bias, or missing supervision.

At the core of my work is a simple question: What makes a representation meaningful, controllable, and aligned with how humans understand the world? I believe that building reliable and interpretable AI requires more than scale—it demands a deeper engagement with human conceptual frameworks. Looking ahead, I envision machine learning systems that reason with structure, embrace changes, and remain accountable to the values we encode in data.

news

Apr 16, 2025 Check out our new preprint—Negate or Embrace: On How Misalignment Shapes Multimodal Representation Learning !
Jul 02, 2024 Our work, CLAP: Isolating Content from Style through Contrastive Learning with Augmented Prompts, is accepted to appear at ECCV 2024.

latest posts

selected publications

  1. A Preprint
    negate_or_embrace.png
    Negate or Embrace: On How Misalignment Shapes Multimodal Representation Learning
    Yichao Cai, Yuhang Liu, Erdun Gao, Tianjiao Jiang, Zhen Zhang, Anton Hengel, and Javen Qinfeng Shi
    2025
  2. ECCV 2024
    clap_preview.png
    CLAP: Isolating Content from Style through Contrastive Learning with Augmented Prompts
    Yichao Cai, Yuhang Liu, Zhen Zhang, and Javen Qinfeng Shi
    arXiv, 2023