Xiaoxiao Sun | Homepage

Xiaoxiao Sun (孙晓晓)

Postdoctoral Researcher @ MARVL Lab, Stanford University

[email protected] · [email protected]

About Me

I am a Postdoctoral Researcher in the MARVL lab at Stanford University, advised by Prof. Serena Yeung-Levy. My research interests include computer vision and machine learning. I am currently exploring vision-language models for the automated interpretation of biological images, with the goal of developing new methods tailored to biomedical research.

I received my Ph.D. from the Australian National University in 2024, under the supervision of Prof. Liang Zheng, and was fortunate to also receive guidance from Prof. Hongdong Li. During the final six months of my Ph.D., I worked as a Research Associate at Nanyang Technological University, advised by Prof. Ying Wei. Before that, I was a Research Assistant at the Singapore University of Technology and Design from 2018 to 2019. I received my M.Sc from Nankai University in 2018, supervised by Prof. Jufeng Yang.

Recent News

• Three papers are accepted at CVPR 2026— Do VLMs Perceive or Recall? Probing Visual Perception vs. Memory with Classic Visual Illusions [Paper]; Incentivizing Generative Zero-Shot Learning via Outcome-Reward Reinforcement Learning with Visual Cues [Paper]; From Panel to Pixel: Zoom-In Vision-Language Pretraining from Biomedical Scientific Literature [Paper]; congrats to Wenjin Hou, Kun Yuan and other authors!
• Co-organizing the 5th DataCV Workshop & Challenge at CVPR 2026. Submissions welcome! [Workshop Website]. The challenge includes two tracks: (1): Classic Visual Illusions Understanding; (2): Real-World Visual Illusions and Anomalies Understanding.
• One paper is accepted by Machine Learning for Health Symposium 2025 — No tokens wasted: Leveraging long context in biomedical vision-language models [Paper]. Congrats to Min Woo Sun!
• Co-organizing the 4th DataCV Workshop & Challenge at ICCV 2025. Submissions welcome! [Workshop Website]
• One paper is accepted by ICLR 2025 — CLDyB: Towards Dynamic Benchmarking for Continual Learning with Pre-trained Models [Paper]
• Two papers are accepted by ICLR 2024 — Alice Benchmarks: Connecting Real World Object Re-Identification with the Synthetic [Paper]; CIFAR-10-Warehouse: Broad and More Realistic Testbeds in Model Generalization Analysis [Paper]
• One paper is accepted by NeurIPS 2023 for spotlight presentation — Privacy Assessment on Reconstructed Images: Are Existing Evaluation Metrics Faithful to Human Perception? [Paper] [Project]

Selected Publications All

Do VLMs Perceive or Recall? Probing Visual Perception vs. Memory with Classic Visual Illusions

Xiaoxiao Sun*, Mingyang Li*, Kun Yuan, Min Woo Sun, Mark Endo, Shengguang Wu, Changlin Li, Yuhui Zhang, Zeyu Wang, Serena Yeung-Levy

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2026

[Paper]

Seeing Is Believing? A Benchmark for Multimodal Large Language Models on Visual Illusions and Anomalies

Wenjin Hou, Wei Liu, Han Hu, Xiaoxiao Sun, Serena Yeung-Levy, Hehe Fan

arXiv:2602.01816, 2026

[Paper]

From Panel to Pixel: Zoom-In Vision-Language Pretraining from Biomedical Scientific Literature

Kun Yuan, Min Woo Sun, Zhen Chen, Alejandro Lozano, Xiangteng He, Shi Li, Nassir Navab, Xiaoxiao Sun, Nicolas Padoy, Serena Yeung-Levy

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2026

[Paper]

No tokens wasted: Leveraging long context in biomedical vision-language models

Min Woo Sun, Alejandro Lozano, Javier Gamazo Tejero, Vishwesh Nath, Xiaoxiao Sun, James Burgess, Yuhui Zhang, Kun Yuan, Robert Tibshirani, Sean Huver, Serena Yeung-Levy

Machine Learning for Health Symposium (ML4H), 2025

[Paper]

CLDyB: Towards Dynamic Benchmarking for Continual Learning with Pre-trained Models

Shengzhuang Chen, Yikai Liao, Xiaoxiao Sun, Kede Ma, Ying Wei

International Conference on Learning Representations (ICLR), 2025

[Paper] [Project]

Alice Benchmarks: Connecting Real World Object Re-Identification with the Synthetic

Xiaoxiao Sun, Yue Yao, Shengjin Wang, Hongdong Li, Liang Zheng

International Conference on Learning Representations (ICLR), 2024

[Paper] [Project]

CIFAR-10-Warehouse: Broad and More Realistic Testbeds in Model Generalization Analysis

Xiaoxiao Sun*, Xingjian Leng*, Zijian Wang*, Yang Yang*, Zi Huang, Liang Zheng

International Conference on Learning Representations (ICLR), 2024

[Paper] [Project]

Rendering-Refined Stable Diffusion for Privacy Compliant Synthetic Data

Kartik Patwari, David Schneider, Xiaoxiao Sun, Chen-Nee Chuah, Lingjuan Lyu, Vivek Sharma

arXiv:2412.06248, 2024

[Paper]

Privacy Assessment on Reconstructed Images: Are Existing Evaluation Metrics Faithful to Human Perception?

Xiaoxiao Sun, Nidham Gazagnadou, Vivek Sharma, Lingjuan Lyu, Hongdong Li, Liang Zheng

Neural Information Processing Systems (NeurIPS spotlight), 2023

[Paper] [Project]

Ranking Models in Unlabeled New Environments

Xiaoxiao Sun, Yunzhong Hou, Weijian Deng, Hongdong Li, Liang Zheng

International Conference on Computer Vision (ICCV), 2021

[Paper] [Project]

Label-free model evaluation with semi-structured dataset representations

Xiaoxiao Sun, Yunzhong Hou, Hongdong Li, Liang Zheng

arXiv:2112.00694, 2021

[Paper] [Project]

Dissecting Person Re-identification from the Viewpoint of Viewpoint

Xiaoxiao Sun, Liang Zheng

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019

[Paper] [Project]

Learning from Web Data using Adversarial Discriminative Neural Networks for Fine-Grained Classification

Xiaoxiao Sun, Liyi Chen, Jufeng Yang

AAAI Conference on Artificial Intelligence (AAAI), 2019

[Paper] [Project]

Self-Paced Balance Learning for Clinical Skin Disease Recognition

Jufeng Yang, Xiaoping Wu, Jie Liang, Xiaoxiao Sun, Ming-Ming Cheng, Paul L. Rosin and Liang Wang

IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2019

[Paper] [Project]

Recognition from Web Data: A Progressive Filtering Approach

Jufeng Yang, Xiaoxiao Sun, Yu-Kun Lai, Liang Zheng, Ming-Ming Cheng

IEEE Transactions on Image Processing (TIP), 2018

[Paper] [Project]

Clinical Skin Lesion Diagnosis using Representations Inspired by Dermatologist Criteria

Jufeng Yang, Xiaoxiao Sun, Jie Liang, Paul L. Rosin

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018

[Paper]

Historical Context-based Style Classification of Painting Images via Label Distribution Learning

Jufeng Yang, Liyi Chen, Le Zhang, Xiaoxiao Sun, Dongyu She, Shao-Ping Lu, Ming-Ming Cheng

ACM International Conference on Multimedia (ACM MM), 2018

[Paper]

Learning from Web Data: the Benefit of Unsupervised Object Localization

Xiaoxiao Sun, Liang Zheng, Yu-Kun Lai, Jufeng Yang

arXiv:1812.09232, 2018

[Paper] [Project]

Learning Visual Sentiment Distributions via Augmented Conditional Probability Neural Network

Jufeng Yang, Ming Sun, Xiaoxiao Sun

AAAI Conference on Artificial Intelligence (AAAI), 2017

[Paper] [Project]

A Benchmark for Automatic Visual Classification of Clinical Skin Disease Images

Xiaoxiao Sun, Jufeng Yang, Ming Sun, Kai Wang

European Conference on Computer Vision (ECCV), 2016

[Paper] [Project] [Dataset]