Conghao XIONG

PhD Candidate

Department of Computer Science and Engineering
The Chinese University of Hong Kong
Gigapixel Image Understanding · Multimodal Learning · Computational Pathology

Email: chxiong21@cse.cuhk.edu.hk

Conghao Xiong

Biography

I am a fifth-year PhD candidate in Computer Science at The Chinese University of Hong Kong (CUHK), supervised by Prof. Irwin King, Prof. Joseph J. Y. Sung, and Prof. Hao Chen. Before CUHK, I was a visiting/research student at Johns Hopkins University with Prof. Philipp Koehn and a visiting student at the University of Cambridge. I received my B.Eng. in Computer Science from Harbin Institute of Technology (HIT).

My research focuses on gigapixel image understanding and multimodal learning, primarily on computational pathology, including whole-slide image representation, pathology foundation model feature adaptation/evaluation, visual compression, and WSI-genomics fusion. My earlier work in NLP/MT studied low-resource word alignment and cross-lingual representation learning.

I welcome collaborations on computational pathology, gigapixel image understanding, multimodal learning, and biomedical AI. Feel free to reach out by email.

News

Selected Publications [Google Scholar]

* joint first authors

MR-Block framework overview Exploiting Low-Dimensional Manifold of Features for Few-shot Whole Slide Image Classification
Conghao Xiong, Zhengrui Guo, Zhe Xu, Yifei Zhang, Raymond Kai-yu Tong, Si Yong Yeo, Hao Chen, Joseph J. Y. Sung, Irwin King
ICLR, 2026.

Topics: gigapixel image understanding, few-shot learning, pathology foundation model feature adaptation, representation geometry.

[Codes][Wechat Article(Chinese)]

 
ConSurv framework overview ConSurv: Multimodal Continual Learning for Survival Analysis
Dianzhi Yu, Conghao Xiong, Yankai Chen, Wenqian Cui, Xinni Zhang, Yifei Zhang, Hao Chen, Joseph J. Y. Sung, Irwin King
AAAI, 2026.

Topics: multimodal learning, continual learning, WSI-genomics fusion, survival analysis.

[Codes]

 
Pathology foundation model survey overview A Survey of Pathology Foundation Model: Progress and Future Directions
Conghao Xiong, Hao Chen, Joseph J. Y. Sung
IJCAI Survey Track, 2025 (19.6%).

Topics: pathology foundation models, pretraining, evaluation, biomedical AI.

[Codes][Wechat Article(Chinese)]

 
FOCUS framework overview FOCUS: Knowledge-enhanced Adaptive Visual Compression for Few-shot Whole Slide Image Classification
Zhengrui Guo, Conghao Xiong, Jiabo Ma, Qichen Sun, Lishuang Feng, Jinzhuo Wang, Hao Chen
CVPR, 2025.

Topics: visual compression, gigapixel image understanding, language-guided patch selection, data-efficient learning.

[Codes]

 
MoME framework overview MoME: Mixture of Multimodal Experts for Cancer Survival Prediction
Conghao Xiong, Hao Chen, Hao Zheng, Dong Wei, Yefeng Zheng, Joseph J. Y. Sung, Irwin King
MICCAI, 2024 (Early Accepted, 11%).

Topics: multimodal fusion, mixture-of-experts, WSI-genomics learning, cross-modal interactions.

[Codes][Wechat Article(Chinese)]

 
TAKT framework overview TAKT: Target-Aware Knowledge Transfer for Whole Slide Image Classification
Conghao Xiong*, Yi Lin*, Hao Chen, Hao Zheng, Dong Wei, Yefeng Zheng, Joseph J. Y. Sung, Irwin King
MICCAI, 2024.

Topics: transfer learning, weak supervision, whole-slide image classification, computational pathology.

[Codes]

 
HAG-MIL framework overview Diagnose Like a Pathologist: Transformer-Enabled Hierarchical Attention-Guided Multiple Instance Learning for Whole Slide Image Classification
Conghao Xiong, Hao Chen, Joseph J. Y. Sung, Irwin King
IJCAI, 2023 (14.8%).

Topics: multiple instance learning, transformer attention, hierarchical WSI modeling, interpretability.

[Codes]

 
Gastric cancer prediction overview Mo1243 Prediction of Gastric Cancer Development from Intestinal Metaplasia Using Deep Learning Model in Gastric Biopsies
Conghao Xiong, Ronald C. K. Chan, Hao Chen, Louis H. S. Lau, Irwin King, Joseph J. Y. Sung
Gastroenterology, 2023.

Topics: clinical AI, gastric cancer risk prediction, biopsy image analysis, computational pathology.

 
Embedding-enhanced GIZA++ overview Embedding-Enhanced GIZA++: Improving Low-Resource Word Alignment Using Embeddings
Kelly Marchisio, Conghao Xiong, Philipp Koehn
Biennial conference of the Association for Machine Translation in the Americas, 2022.

Topics: NLP, machine translation, word alignment, cross-lingual representation learning.

[Codes]

 

Academic Services

Talks and Presentations

PuzzleLogic 2026Exploiting Structure Beyond Labels for Data-Efficient Computational Pathology [Video]

Teaching

CUHK 2022SpringComputers and Society (CSCI3250)
CUHK 2021FallIntroduction to Python (CSCI2040)