DU Yao   杜尧

I am a Ph.D. candidate at The Hong Kong University of Science and Technology, supervised by Prof. Xiaomeng LI. I am interested in computer vision, medical image analysis and AI for science.

I obtained BEng from Northwestern Polytechnical University, and MPhil from The Hong Kong Polytechnic University, supervised by Prof. Yong XIA.

我是香港科技大学电子与计算机工程系的博士研究生,导师为李小萌教授。研究方向涵盖计算机视觉、医学图像分析与AI for Science。

本科毕业于西北工业大学,硕士毕业于香港理工大学,导师为夏勇教授

profile photo

Email  /  Google Scholar  /  GitHub  /  Twitter  /  CV   

News动态

[2025–10] One paper accepted to BIBM 2025 一篇论文被 BIBM 2025 录用
[2025–06] Two papers accepted to MICCAI 2025 两篇论文被 MICCAI 2025 录用
[2025–03] Recognized as Outstanding Reviewer at CVPR 2025 荣获 CVPR 2025 优秀审稿人称号
[2024–07] One paper accepted to ECCV 2024 一篇论文被 ECCV 2024 录用
[2023–09] One paper accepted to NeurIPS 2023 一篇论文被 NeurIPS 2023 录用

Selected Publications & Preprints 代表性论文

Deep Regression: From CNNs to VLMs and MLLMs 深度回归:从CNN到VLM与MLLM

Regression and number understanding are fundamental for precise physical perception.
We aim to develop rigorous evaluation frameworks for measuring the quantitative reasoning and numerical understanding capabilities of MLLMs.
回归与数值理解是精确物理感知的基础。
我们致力于构建严谨的评估框架,用于衡量多模态大语言模型的定量推理与数值理解能力。

Teach CLIP to Develop a Number Sense for Ordinal Regression
Yao Du, Qiang Zhai, Weihang Dai, Xiaomeng Li†
European Conference on Computer Vision (ECCV), 2024

Semi-Supervised Contrastive Learning for Deep Regression with Ordinal Rankings from Spectral Seriation
Weihang Dai, Yao Du, Hanru Bai, Kwang-Ting Cheng, Xiaomeng Li†
Neural Information Processing Systems (NeurIPS), 2023

Injecting Distributional Awareness into MLLMs via Reinforcement Learning for Deep Imbalanced Regression
Yao Du, Shanshan Song, Xiaomeng Li†
Under Review, 2026

Medical Image Analysis: Echocardiography and Computational Pathology 医学图像分析:超声心动图与计算病理学

Parameter-efficient fine-tuning and multimodal representation learning for medical imaging.
We aim to develop data-efficient and clinically reliable AI systems for analyzing complex medical imaging data.
面向医学影像的参数高效微调与多模态表示学习。
我们致力于构建数据高效、临床可靠的AI系统,用于分析复杂医学影像数据。

CardiacCLIP: Video-based CLIP Adaptation for LVEF Prediction in a Few-shot Manner
Yao Du, Jiarong Guo, Xiaomeng Li† (early accept)
International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2025

Beyond H&E: Unlocking Pathological Insights with Polarization Imaging
Yao Du, Jiaxin Zhuang, Xiaoyu Zheng, Jing Cong, Limei Guo, Chao He, Lin Luo, Xiaomeng Li†
IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2025

Diffusion-based Virtual Staining from Polarimetric Mueller Matrix Imaging
Xiaoyu Zheng, Jing Wen, Jiaxin Zhuang, Yao Du, Jing Cong, Limei Guo, Chao He, Lin Luo, Hao Chen
International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2025

CardioInfuser: Multi-scale Semantic Infusion for Few-shot Echocardiogram Video Assessment
Yao Du, Marawan Elbatel, Jiewen Yang, Xiaomeng Li†
Under Review, 2026

MUST: MUlti-Style virtual STaining with incomplete pairs
Jiaxin Zhuang, Yao Du, ..., Hao Chen†
Under Review, 2026

CardiacPULSE: Frequency-Aware Self-Supervised Cardiac Phase Detection in Echocardiography
Jiarong Guo, Jiewen Yang, Yao Du, Yi Qin, Xiaomeng Li†
Under Review, 2026

SAMotion: A Generalizable Anatomical Structure-aware Unsupervised Framework for Cardiac Motion Tracking
Jiewen Yang, Jiarong Guo, Yao Du, Xiaomeng Li†
Under Review, 2026

Artificial Intelligence of Things (AIoT) / Structural Health Monitoring (SHM) 人工智能物联网(AIoT)/ 结构健康监测(SHM)

Infrastructure Sensor Anomaly Detection, Edge Computing, and AIoT Systems.
We aim to integrate AI with large-scale infrastructure sensing systems to enable intelligent monitoring and smart city applications.
基础设施传感器异常检测、边缘计算与AIoT系统。
我们致力于将人工智能与大规模基础设施感知系统深度融合,实现智能监测与智慧城市应用。

Wireless IoT Monitoring System in Hong Kong-Zhuhai-Macao Bridge and Edge Computing for Anomaly Detection
Xiaoyou Wang, Wanglin Wu, Yao Du, Jiannong Cao, Qianyi Chen, Yong Xia†
IEEE Internet of Things Journal, 2023

Data Anomaly Detection through Semisupervised Learning Aided by Customized Data Augmentation Techniques
Xiaoyou Wang*, Yao Du*, Xiaoqing Zhou, Yong Xia†
Structural Control and Health Monitoring, 2023

Convolutional Neural Network-based Data Anomaly Detection Considering Class Imbalance with Limited Data
Yao Du, Lingfang Li, Rongrong Hou, Xiaoyou Wang, Wei Tian, Yong Xia†
Smart Structures and Systems, 2022

Anomaly Detection of Sensor Faults and Extreme Events based on Support Vector Data Description
Yuxuan Zhang, Xiaoyou Wang, Zhenghao Ding, Yao Du, Yong Xia†
Structural Control and Health Monitoring, 2022

Unsupervised One-class Classification for Condition Assessment of Bridge Cables Using Bayesian Factor Analysis
Xiaoyou Wang, Lingfang Li, Wei Tian, Yao Du, Rongrong Hou, Yong Xia†
Smart Structures and Systems, 2022

Professional Service 学术服务

Reviewer:审稿人:

  • Conference Reviewer: CVPR, ICCV, NeurIPS, ICML, BMVC, MICCAI 会议审稿人:CVPR、ICCV、NeurIPS、ICML、BMVC、MICCAI
  • Journal Reviewer: TNNLS 期刊审稿人:TNNLS

Awards:荣誉奖项:

  • Outstanding Reviewer, CVPR 2025 CVPR 2025 优秀审稿人
  • National Scholarship (Top 1%), Ministry of Education, China — 2016, 2017, 2018 国家奖学金(前1%),中国教育部 — 2016、2017、2018年




© Yao DU
credits