Shizhan Gong

Macao Polytechnic University Ph.D. student, the Chinese University of Hong Kong

I am Shizhan Gong, currently a quantitative researcher at Jump Trading. I received my Ph.D. in Computer Science and Engineering from The Chinese University of Hong Kong (CUHK). My research interests include trustworthy AI and multimodal learning. Please feel free to connect if you are interested in collaboration.

Google Scholar GitHub
Education
  • The Chinese University of Hong Kong

    The Chinese University of Hong Kong

    Ph.D. in Computer Science and Engineering Sep. 2022 - Jul. 2026

  • New York University

    New York University

    M.S. in Data Science Sep. 2018 - Jul. 2020

  • Tsinghua University

    Tsinghua University

    B.Eng. in Industrial Engineering & Statistics Sep. 2014 - Jul. 2018

Service
  • Reviewer of NeurIPS, ICLR, CVPR, AAAI, WACV, BMVC, AISTATS, RECOMB.
  • Reviewer of Transactions on Pattern Analysis and Machine Intelligence (TPAMI), International Journal of Computer Vision (IJCV), Transactions on Machine Learning Research (TMLR), IEEE Transactions on Medical Imaging (TMI), Medical Image Analysis (MedIA), Journal of Biomedical and Health Informatics (JBHI), Transaction on Biomedical Engineering (TBME).
Experience
  • Jump Trading

    Jump Trading

    Quantitative Researcher Aug.2026 - Current

  • Tencent

    Tencent

    Machine Learning Engineer Jul.2020 - March 2022

Honors & Awards
Selected Publications (view all )
Saliency-R1: Enforcing Interpretable and Faithful Vision-language Reasoning via Saliency-map Alignment Reward
Saliency-R1: Enforcing Interpretable and Faithful Vision-language Reasoning via Saliency-map Alignment Reward

Shizhan Gong, Minda Hu, Qiyuan Zhang, Chen Ma, Qi Dou

The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026 ConferencePoster

[Paper]

Saliency-R1: Enforcing Interpretable and Faithful Vision-language Reasoning via Saliency-map Alignment Reward
Saliency-R1: Enforcing Interpretable and Faithful Vision-language Reasoning via Saliency-map Alignment Reward

Shizhan Gong, Minda Hu, Qiyuan Zhang, Chen Ma, Qi Dou

The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026 ConferencePoster

[Paper]

Concepts from Representations: Post-hoc Concept Bottleneck Models via Sparse Decomposition of Visual Representations
Concepts from Representations: Post-hoc Concept Bottleneck Models via Sparse Decomposition of Visual Representations

Shizhan Gong, Xiaofan Zhang, Qi Dou

AAAI Conference on Artificial Intelligence (AAAI) 2026 ConferencePoster

[Paper]

Concepts from Representations: Post-hoc Concept Bottleneck Models via Sparse Decomposition of Visual Representations
Concepts from Representations: Post-hoc Concept Bottleneck Models via Sparse Decomposition of Visual Representations

Shizhan Gong, Xiaofan Zhang, Qi Dou

AAAI Conference on Artificial Intelligence (AAAI) 2026 ConferencePoster

[Paper]

Kernel-based Unsupervised Embedding Alignment for Enhanced Visual Representation in Vision-language Models
Kernel-based Unsupervised Embedding Alignment for Enhanced Visual Representation in Vision-language Models

Shizhan Gong, Yankai Jiang, Qi Dou, Farzan Farnia

International Conference on Machine Learning (ICML) 2025 ConferencePoster

[Paper]

Kernel-based Unsupervised Embedding Alignment for Enhanced Visual Representation in Vision-language Models
Kernel-based Unsupervised Embedding Alignment for Enhanced Visual Representation in Vision-language Models

Shizhan Gong, Yankai Jiang, Qi Dou, Farzan Farnia

International Conference on Machine Learning (ICML) 2025 ConferencePoster

[Paper]

Boosting the Visual Interpretability of CLIP via Adversarial Fine-tuning
Boosting the Visual Interpretability of CLIP via Adversarial Fine-tuning

Shizhan Gong, Haoyu Lei, Qi Dou, Farzan Farnia

International Conference on Learning Representations (ICLR) 2025 ConferencePoster

[Paper]

Boosting the Visual Interpretability of CLIP via Adversarial Fine-tuning
Boosting the Visual Interpretability of CLIP via Adversarial Fine-tuning

Shizhan Gong, Haoyu Lei, Qi Dou, Farzan Farnia

International Conference on Learning Representations (ICLR) 2025 ConferencePoster

[Paper]

3DSAM-Adapter: Holistic Adaptation of SAM from 2D to 3D for Promptable Tumor Segmentation
3DSAM-Adapter: Holistic Adaptation of SAM from 2D to 3D for Promptable Tumor Segmentation

Shizhan Gong, Yuan Zhong, Wenao Ma, Jinpeng Li, Zhao Wang, Jingyang Zhang, Pheng-Ann Heng, Qi Dou

Medical Image Analysis 2024 Journal

[Paper]

3DSAM-Adapter: Holistic Adaptation of SAM from 2D to 3D for Promptable Tumor Segmentation
3DSAM-Adapter: Holistic Adaptation of SAM from 2D to 3D for Promptable Tumor Segmentation

Shizhan Gong, Yuan Zhong, Wenao Ma, Jinpeng Li, Zhao Wang, Jingyang Zhang, Pheng-Ann Heng, Qi Dou

Medical Image Analysis 2024 Journal

[Paper]

All publications