Hello! I am Yujia Cai, a third-year undergraduate student majoring in Computer Science at Xidian University. I am currently a research intern at Stony Brook University, advised by Prof. Chenyu You, and I also collaborate closely with Qin Ren. Previously, I worked on Style-adaptive Retrieval with Jiexi Yan. My research experience spans Multimodal Learning and Medical image analysis, with prior work on Retrieval, Domain adaptation, and Parameter-efficient fine-tuning.

I am particularly interested in learning robust and efficient representations that generalize across domains and modalities, with the goal of building practical models for vision, multimodal understanding, and scientific discovery.

🔥 News

  • 2026.01: 🎉 Our paper Hystar: Hypernetwork-Driven Style-Adaptive Retrieval via Dynamic SVD Modulation was accepted to ICLR 2026.

📝 Publications

ICLR 2026
Hystar framework

Hystar: Hypernetwork-Driven Style-Adaptive Retrieval via Dynamic SVD Modulation

Yujia Cai, Boxuan Li, Chenghao Xu, Jiexi Yan

International Conference on Learning Representations (ICLR), 2026

Paper

  • We propose Hystar, a hypernetwork-driven style-adaptive retrieval framework that dynamically modulates the singular values of attention layers via hypernetworks to improve robustness under diverse visual styles. The method introduces an OT-weighted StyleNCE loss to reweight hard negatives and mitigate cross-style semantic confusion. Experiments on DomainNet and DSR demonstrate consistent improvements in cross-style retrieval and zero-shot classification.

📖 Educations

  • 2023.09 – Present, B.S. in Computer Science, National Top-Notch Student Training Program 2.0 in Basic Disciplines, Xidian University, Xi’an, China. Expected Jun. 2027.

📝 Academic Service

  • Journal Reviewer, Pattern Recognition.
  • Journal Reviewer, IEEE Transactions on Neural Networks and Learning Systems.

💻 Internships

  • Oct 2024 – Present, Research Intern, OPTIC Lab, Xidian University, China.
  • Oct 2025 – Present, Research Intern, Stony Brook University, USA.