Mr Yichao Cai
Higher Degree by Research Candidate
PhD Student
School of Computer and Mathematical Sciences
Faculty of Sciences, Engineering and 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.
-
Language Competencies
Language Competency Chinese (Mandarin) Can read, write, speak, understand spoken and peer review English Can read, write, speak, understand spoken and peer review -
Education
Date Institution name Country Title 2016 - 2019 Wuhan University of Technology China M.S. 2012 - 2016 Wuhan University of Technology China B.Eng. -
Research Interests
-
Journals
Year Citation 2018 Cai, Y., Li, D., Zhou, X., & Mou, X. (2018). Robust Drivable Road Region Detection for Fixed-Route Autonomous Vehicles Using Map-Fusion Images. SENSORS, 18(12), 15 pages.
WoS11 Europe PMC3 -
Conference Papers
Year Citation 2024 Cai, Y., Liu, Y., Zhang, Z., & Shi, J. Q. (2024). CLAP: Isolating Content from Style Through Contrastive Learning with Augmented Prompts. In Lecture Notes in computer science Vol. 15079 (pp. 130-147). Milan, Italy: Springer Nature Switzerland.
DOI -
Preprint
Year Citation 2025 Cai, Y., Liu, Y., Gao, E., Jiang, T., Zhang, Z., Hengel, A. V. D., & Shi, J. Q. (2025). On the Value of Cross-Modal Misalignment in Multimodal Representation
Learning.
Connect With Me
External Profiles
