Hangzhou He (何航舟)

About

Hi! I’m Hangzhou He (何航舟) from Peking University. I’m a Ph.D. student at the Molecular Imaging and Machine Intelligence Lab (MILab), under the supervision of assistant professor Yanye Lu (卢闫晔) and professor Qiushi Ren (任秋实).

My research focuses on the intersection of artificial intelligence and biomedical applications, with a particular emphasis on the trustworthiness of deep learning models, including explainability, generalization, and building interpretable models. Feel free to email me for any questions or interesting ideas.

Selected Publications

#: Equal contribution · *: Corresponding author

Preprints

  • Chat-CBM: Towards Interactive Concept Bottleneck Models with Frozen Large Language Models
    Hangzhou He, Lei Zhu, Kaiwen Li, Xinliang Zhang, Jiakui Hu, Ourui Fu, Zhengjian Yao, Yanye Lu*
    arXiv, September 2025
    PDF

  • Beyond Visual Generation: Frontiers, Challenges, and Future Directions in Agentic Visual Creation
    Hefei Mei#, Hangzhou He#, Haiyi Qiu#, Longrong Yang#, Lunhao Duan#, Shanshan Zhao*, Pengxin Zhan, Qing-Guo Chen, Zhao Xu, Weihua Luo
    PDF Repository

Journal

  • Test-Time Scaling for Video Diffusion Models via Diagnosis-Guided Candidate Recycling
    Hangzhou He, Lunhao Duan, Shanshan Zhao*, Kaiwen Li, Qing-Guo Chen, Weihua Luo, Yanye Lu*
    ACM Transactions on Graphics (SIGGRAPH Asia 2026)
    PDF DOI Code

  • Assessing Response in Endoscopy Images of Esophageal Cancer Treated with Total Neoadjuvant Therapy via Hybrid-Architecture Ensemble Deep Learning
    Peng Yuan#, Meichen Liu#, Hangzhou He#, Liang Dai#, Ya-Ya Wu, Ke-Neng Chen*, Qi Wu*, Yanye Lu*
    Frontiers in Oncology
    PDF DOI Code

Conference

  • Training-free Test-time Improvement for Explainable Medical Image Classification
    Hangzhou He#, Jiachen Tang#, Lei Zhu, Kaiwen Li, Yanye Lu*
    MICCAI 2025 · Spotlight
    PDF DOI Code

  • V2C-CBM: Building Concept Bottlenecks with Vision-to-Concept Tokenizer
    Hangzhou He, Lei Zhu, Xinliang Zhang, Shuang Zeng, Qian Chen, Yanye Lu*
    AAAI 2025 (main track poster and oral at workshop)
    PDF DOI Code

  • On the Duality Between Sharpness-Aware Minimization and Adversarial Training
    Yihao Zhang#, Hangzhou He#, Jingyu Zhu#, Huanran Chen, Yifei Wang, Zeming Wei*
    ICML 2024 · Poster
    PDF DOI Code

Research & Internships

  • AI Business / ATH MaaS, Alibaba Group
    Jan. – Sep. 2026
    Test-time scaling and agentic AIGC.
    Mentor: Dr. Shanshan Zhao

  • Beijing United Imaging Research Institute of Intelligent Imaging
    Jul. – Sep. 2023
    Medical MLLMs.
    Mentor: Dr. Pei Dong

Education

  • 2024.09 - Present, Ph.D. student, Department of Biomedical Engineering, College of Future Technology, Peking University
  • 2020.09 - 2024.07, B.S. in Theoretical and Applied Mechanics, minor in Biomedical Engineering, College of Engineering, Peking University

Honors & Awards

  • Grand Prize, the 34th Challenge Cup, Peking University, 2026
  • National Scholarship, Ministry of Education of China, 2025
  • Academic Exchange Fund for Graduate Students, Peking University, 2025
  • AAAI-25 Student Scholarship, AAAI, 2025
  • Merit Student Award, Peking University, 2025
  • Dean’s scholarship, College of Future Technology, Peking University, 2024, 2025
  • Excellent Graduate, Peking University, 2024
  • Honours Degrees, College of Engineering, Peking University, 2024
  • Grand Challenges Scholar, the Grand Challenges Scholar, Grand Challenges Scholars Program & Peking University, 2024 (Top 5 undergraduates university-wide)
  • Outstanding Project Award for Undergraduate Research, Peking University, 2024
  • Award for Academic Excellents, Peking University, 2023

Academic Service

  • Conference Reviewer: ICLR, NeurIPS, ICCV, CVPR, ECCV, BMVC, AAAI, MICCAI, IPMI
  • Workshop Reviewer: MKLM @ IJCAI, {iMIMIC, CARE} @ MICCAI
  • Journal Reviewer: Biomedical Optics Express, Optics Express
  • Conference Volunteer: AAAI 2025

Invited Talks

Software & Patents

  • PyTorch Attribution Toolbox
    Robust feature attribution methods for explaining image classification models, Chinese Invention Patent (ZL 2024 1 0941326.8)
    GitHub