Chenshuang Zhang

I am currently a Postdoc advised by Professor Tae-Hyun Oh, School of Computing, KAIST. My current research interest lies in the interaction of computer vision and machine learning, including but not limited to:

Large-language Models
Multi-modality learning
Generative models
Adversarial machine learning

I got my Ph.D. degree in KAIST, advised by Professor In So Kweon and Professor Junmo Kim. Before joining KAIST, I worked as a Senior Machine Learning Engineer at Alibaba Group, Beijing, China.

I obtained my master's degree from Tsinghua University, working on deep learning in medical applications.

I'm always open to collaborations on various research topics. If you are interested in my work, please feel free to contact me.

Email / Google Scholar / LinkedIn

News

Feb 2026: Two papers accepted at CVPR 2026.
Oct 2025: Selected as a Top Reviewer for NeurIPS 2025.
Sep 2025: Joined KAIST as a Postdoctoral Researcher.
Sep 2025: One paper accepted at NeurIPS 2025.
Aug 2025: Received my Ph.D.
Mar 2024: One paper accepted at TMLR.
Feb 2024: One paper accepted at CVPR 2024 (Highlight, top 2.8%).

Selected Publications

* indicates equal contributions

	SVHalluc: Benchmarking Speech–Vision Hallucination in Audio-Visual Large Language Models Chenshuang Zhang, Kyeong Seon Kim, Chengxin Liu, Tae-Hyun Oh IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026.
	Aligning What Vision-Language Models See and Perceive with Adaptive Information Flow Chengxin Liu, Wonseok Choi, Chenshuang Zhang, Tae-Hyun Oh IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026.
	Video Diffusion Models Excel at Tracking Similar-Looking Objects Without Supervision Chenshuang Zhang, Kang Zhang, Joon Son Chung, In So Kweon, Junmo Kim, Chengzhi Mao 39th Conference on Neural Information Processing Systems (NeurIPS), 2025.
	ImageNet-D: Benchmarking Neural Network Robustness on Diffusion Synthetic Object Chenshuang Zhang, Fei Pan, Junmo Kim, In So Kweon, Chengzhi Mao IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024. CVPR Highlight (2.8%)
	Towards Understanding Dual BN In Hybrid Adversarial Training Chenshuang Zhang, Chaoning Zhang, Kang Zhang, Axi Niu, Junmo Kim, In So Kweon Transactions on Machine Learning Research (TMLR), 2024
	Text-to-image Diffusion Models in Generative AI: A Survey Chenshuang Zhang, Chaoning Zhang, Mengchun Zhang, Junmo Kim, In So Kweon Under review, 2024
	A global and updatable ECG beat classification system based on recurrent neural networks and active learning Guijin Wang, Chenshuang Zhang (First student author), Yongpan Liu, Huazhong Yang, Dapeng Fu, Haiqing Wang, Ping Zhang Information Sciences (Impact factor 8.23), 2019
	Patient-specific ECG classification based on recurrent neural networks and clustering technique Chenshuang Zhang, Guijin Wang, Jingwei Zhao, Pengfei Gao, Jianping Lin, Huazhong Yang 2017 13th IASTED International Conference on Biomedical Engineering (BioMed), 2017
	A survey on masked autoencoder for visual self-supervised learning Chaoning Zhang, Chenshuang Zhang, Junha Song, John Seon Keun Yi, In So Kweon International Joint Conference on Artificial Intelligence (IJCAI), 2023
	Decoupled Adversarial Contrastive Learning for Self-supervised Adversarial Robustness Chaoning Zhang, Kang Zhang, Chenshuang Zhang, Axi Niu, Jiu Feng, Chang D Yoo, In So Kweon European Conference on Computer Vision (ECCV), 2022 ECCV Oral (2.3%)
	How does simsiam avoid collapse without negative samples? a unified understanding with self-supervised contrastive learning Chaoning Zhang, Kang Zhang, Chenshuang Zhang, Trung X Pham, Chang D Yoo, In So Kweon International Conference on Learning Representations (ICLR), 2022
	Bidirectional recurrent neural network and convolutional neural network (BiRCNN) for ECG beat classification Pengwei Xie, Guijin Wang, Chenshuang Zhang, Ming Chen, Huazhong Yang, Tingting Lv, Zhenhua Sang, Ping Zhang 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2018

Thanks to Jon Barron for sharing the code of the nice website.