Now I work at Alibaba Token Hub (ATH) Group. I received my Ph.D degree at Artificial Intelligence and Biomedical Image Analysis Lab, School of Engineering, Westlake University (Hangzhou, China), affiliated with a joint-supervision program with Zhejiang University, supervised by Prof. Lin Yang. Before that, I received my B.Eng Degree from School of Automation Science and Electrical Engineering, Beihang University (Beijing, China) in June 2021.
Currently, my research is centered on Visual-Language Model for Spatial Intelligence.
π₯ News
- 2025.9: Β ππ One paper was accepted by NeurIPS 2025!
- 2024.11: Β ππ Awarded as Zhejiang University 2024 National Scholarship!
- 2024.10: Β ππ Awarded as MICCAI Young Scientist Award (Top 5)!
- 2024.10: Β ππ One paper was accepted by NeurIPS 2024!
- 2024.09: Β ππ One MICCAI 2024 paper was invited as oral presentation!
- 2024.07: Β ππ One paper was accepted by European Conference on Computer Vision (ECCV 2024)!
- 2024.05: Β ππ One paper was Early Accepted by International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2024)!.
- 2023.12: Β ππ Awarded as Zhejiang University 2023 Outstanding Graduates!
- 2023.05: Β ππ One paper was Early Accepted by International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2023)!.
- 2022.12: Β ππ Awarded as Zhejiang University 2022 Outstanding Graduates!
- 2022.01: Β ππ One paper was accepted by IEEE International Symposium on Biomedical Imaging (ISBI 2022)!
π Publications
SD-VLM: Spatial Measuring and Understanding with Depth-Encoded Vision-Language Models (NeurIPS 2025)
Pingyi Chen, Yujing Lou, Shen Cao, Jinhui Guo, Lubin Fan, Yue Wu, Lin F. Yang, Lizhuang Ma, Jieping Ye
- Propose Massive Spatial Measuring and Understanding (MSMU) dataset with precise spatial annotations.
- Introduce a plug-in depth positional encoding method strengthening VLMsβ spatial awareness.
WSI-VQA: Interpreting Whole Slide Images by Generative Visual Question Answering European Conference on Computer Vision (ECCV 2024)
Pingyi Chen, Chenglu Zhu, Sunyi Zheng, Honglin Li, Lin Yang
- Establish a scalable pipeline to curate slide-level VQA datasets.
- Propose a WSI-VQA framework to reframe previous WSI-related tasks into a QA pattern.
WsiCaption: Multiple Instance Generation of Pathology Reports for Gigapixel Whole-Slide Images International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2024 Oral/Best Paper Candidate)
Pingyi Chen, Honglin Li, Chenglu Zhu, Sunyi Zheng, Zhongyi Shui, Lin Yang
- Establish a pathology report dataset with GPT.
- Propose a multiple instance generation (MI-Gen) framework to generate text based on gigapixel inputs.
-
Exploring Unsupervised Cell Recognition with Prior Self-activation Maps. Pingyi Chen, Chenglu Zhu, Zhongyi Shui, Jiatong Cai, Sunyi Zheng, Shichuan Zhang, Lin Yang MICCAI 2023
-
Category Separation For Weakly Supervised Multi-Class Cell Counting. Jiatong Cai, Chenglu Zhu, Pingyi Chen, Shichuan Zhang, Honglin Li, Yuxuan Sun, Lin Yang IEEE ISBI 2022
π Honors and Awards
- 2024.11 Zhejiang University 2024 National Scholarship.
- 2024.10 MICCAI Young Scientist Award.
- 2023.12 Zhejiang University 2023 Outstanding Graduates.
- 2022.12 Zhejiang University 2022 Outstanding Graduates.
- 2022.06 Westlake University Outstanding Cadres of the Graduate Student Union.
π Educations
- 2021.09 - 2026.06, Ph.D at Westlake University & Zhejiang University, Hangzhou, China.
- 2017.09 - 2021.06, Bachelor of Engineering, Automation, Beihang University, Beijing, China.
π¬ Talks
π» Internships
- 2024.12 - 2025.10, Tongyi Lab, Alibaba, Hangzhou, China.
- 2021.03 - 2021.08, SenseTimeοΌεζ±€οΌResearch, Beijing, China.