Jiawen Li
Jiawen Li is a Ph.D. student in Biomedical Engineering at the Institute of Biopharmaceutical and Health Engineering, Tsinghua Shenzhen International Graduate School (SIGS), Tsinghua University, advised by Prof. Yonghong He and Prof. Tian Guan. He received his Bachelor's degree from Cuiying Honors College, Lanzhou University, and his Master's degree from Open FIESTA at Tsinghua SIGS. He has internships and collaborations with Teksqray (Shenzhen Shengqiang Technology Co, Ltd.), the Research Institute of Tsinghua University in Shenzhen, and the DSAIL lab led by Prof. Jia Li at HKUST(GZ). He also closely collaborates with Prof. Anjia Han and Prof. Huijuan Shi at the First Affiliated Hospital of Sun Yat-sen University.
Jiawen is a recipient of the China National Scholarship for two consecutive years (2025 and 2026), the Second Prize of the China Graduate Mathematical Contest in Modeling, and the Outstanding Undergraduate Thesis Award at Lanzhou University.
His research interests broadly lie in digital medical imaging, computer vision, and deep learning, with a focus on pathology foundation models (self-supervised, weakly supervised pretraining and distillation), gigapixel whole-slide image representation (graph neural networks and multiple instance learning), multimodal learning (vision-language alignment and multimodal LLMs for pathology images), and medical image analysis (3D pathology, polarization imaging, and fundus imaging).
- Foundation models: ALICE, PathOrchestra, StainNet.
- Whole-slide representation: WiKG, E2E-ViT, RetMIL.
- Multimodal learning: PathTree, ProAlign, QPath.
- Medical image analysis: DeepTree, Myopic Maculopathy, Vectorial Optics.
I am currently seeking research positions in digital and computational pathology, medical multimodal learning, or computer vision for healthcare. Feel free to email me.
News
Publications
* equal contribution. # corresponding author.
Preprints
DeCo-MIL: Debiased Counterfactual Reasoning for Long-Tailed Whole Slide Image Analysis
Pretraining Multiple Instance Learning Networks with Multi-Teacher Distillation from Pathology Slide Foundation Models
ALICE: Learning a General-Purpose Pathology Foundation Model from Vision, Vision-Language, and Slide-Level Experts
A Digital Pathology Resource for Liver Cancer Quantification with Datasets, Benchmarks, and Tools
To What Extent Do Token-Level Representations from Pathology Foundation Models Improve Dense Prediction?
HookMIL: Revisiting Context Modeling in Multiple Instance Learning for Computational Pathology
Unlocking adaptive digital pathology through dynamic feature learning
Conference Papers
Beyond ViT Tokens: Masked-Diffusion Pretrained Convolutional Pathology Foundation Model for Cell-Level Dense Prediction
Turning Pre-Trained Vision Transformers into End-to-End Histopathology Whole Slide Image Models for Survival Prediction
StainNet: Scaling Self-Supervised Foundation Models on Immunohistochemistry and Special Stains for Computational Pathology
Jiawen Li*, Jiali Hu*, Xitong Ling*, Yongqiang Lv, Yuxuan Chen, Yizhi Wang, Tian Guan#, Yifei Liu#, Yonghong He#
Medical Imaging with Deep Learning (MIDL), 2026
Preprint Code
ViT-S ViT-B
Multimodal Distillation-Driven Ensemble Learning for Long-Tailed Histopathology Whole Slide Images Analysis
Rethinking Slide-Level Adaptation of Pathology Foundation Models
QPath: A Question-Aware Multi-Resolution Vision Language Framework for Computational Pathology
Deformable Attention Graph Representation Learning for Histopathology Whole Slide Image Analysis
Cross-Modal Prototype Allocation: Unsupervised Slide Representation Learning via Patch-Text Contrast in Computational Pathology
Leveraging Pre-trained Models for FF-to-FFPE Histopathological Image Translation
RetMIL: Retentive Multiple Instance Learning for Histopathological Whole Slide Image Classification
NcIEMIL: Rethinking Decoupled Multiple Instance Learning Framework for Histopathological Slide Classification
Dynamic Graph Representation with Knowledge-aware Attention for Histopathology Whole Slide Image Analysis
HIQ: One-Shot Network Quantization for Histopathological Image Classification
Classification of Myopic Maculopathy Images with Self-supervised Driven Multiple Instance Learning Network
Journal Papers
Artificial intelligence-assisted histopathological diagnosis of endocervical gastric-type adenocarcinoma: a multicenter model development and validation study
DiagR1: A Vision-Language Model Trained via Reinforcement Learning for Digestive Pathology Diagnosis
From Generic to Specialized: A Subspecialty Diagnostic System Powered by Self-Supervised Learning for Cervical Histopathology
Diagnostic text-guided representation learning in hierarchical classification for pathological whole slide image
PathOrchestra: A comprehensive foundation model for computational pathology with over 100 diverse clinical-grade tasks
Fang Yan*#, Jianfeng Wu*, Jiawen Li*, Wei Wang*, Yirong Chen, Linda Wei, Jiaxuan Lu, Wen Chen, Zizhao Gao, Jianan Li, Heng Li, Hong Yan, Jiabo Ma, Minda Chen, Yang Lu, Qing Chen, Yizhi Wang, Xitong Ling, Xuenian Wang, Zihan Wang, Qiang Huang, Shengyi Hua, Mianxin Liu, Lei Ma, Tian Shen, Xiaofan Zhang#, Yonghong He#, Hao Chen#, Shaoting Zhang#, Zhe Wang#
NPJ Digital Medicine (NPJ Digit. Med.), 2025
Paper Code Weights
Dynamic hypergraph representation for bone metastasis analysis
Using optical skyrmions to assess vectorial adaptive optics capabilities in the presence of complex aberrations
Comprehensive benchmark dataset for pathological lymph node metastasis in breast cancer sections
A reconfigurable arbitrary retarder array as complex structured matter
A deep learning method for predicting the origins of cervical lymph node metastatic cancer on digital pathological images
DeepTree: Pathological image classification through imitating tree-like strategies of pathologists
Education
Tsinghua University
Tsinghua University
Lanzhou University
Experience
Internships
- Jul 2023 - Present, Deep Learning Algorithm Engineer, Research Institute of Tsinghua University in Shenzhen, Greater Bay Area National Center of Technology Innovation
- Jul 2024 - Jul 2025, Research Assistant, DSAIL lab led by Prof. Jia Li at HKUST(GZ)
Reviewing
- Conference Reviewer: CVPR、NeurIPS、ICLR、AAAI、ACM MM、MICCAI
- Journal Reviewer: IEEE Transactions on Medical Imaging (TMI)、Pattern Recognition (PR)、Expert Systems with Applications (ESWA)
Awards
- 2026, China National Scholarship (国家奖学金)
- 2025, China National Scholarship (国家奖学金)
- 2023, Institute-Level Second-Class Scholarship, Tsinghua University
- 2022, Second Prize, 19th China Graduate Mathematical Contest in Modeling
- 2021, Outstanding Undergraduate Thesis, Lanzhou University
- 2018, Provincial Third Prize in Mathematics, 10th Chinese Mathematics Competitions
- 2017, University Third-Class Scholarship, Lanzhou University
Teaching
Teaching Assistant
- Interdisciplinary Innovation Practice Course - Digital Healthcare (数字医疗), SIGS, THU, 2026 Spring
- Artificial Intelligence and Innovative Design Capstone Project (人工智能与创新设计), SIGS, THU, 2025 Autumn
- Interdisciplinary Innovation Practice Course - Digital Healthcare (数字医疗), SIGS, THU, 2025 Spring
- Advanced Numerical Analysis (高等数值分析), SIGS, THU, 2024 Autumn