Hello, I am Chenxu Wu (chinese name: ไผๆ™จๆ—ญ), a student at the University of Science and Technology of China (USTC), currently in my first year at the MIRACLE Lab under the guidance of Prof. S. Kevin Zhou and Dr. Zihang Jiang. I have previously interned at Siemens and Huawei, gaining valuable industry experience.

My research interests lie in the application technologies of diffusion models, including image generation and diffusion posterior sampling. I am passionate about exploring the potential of these methods in various domains.

If you are interested in my work or would like to collaborate, please feel free to reach out to me via email at wuchenxu [at] mail [dot] ustc [dot] edu [dot] cn. Looking forward to connecting with you!

๐Ÿ”ฅ News

  • 2025.03: ย ๐ŸŽ‰๐ŸŽ‰ One paper is accepted by CVPR 2025.
  • 2025.01: ย ๐ŸŽ‰๐ŸŽ‰ My first paper (both first paper and first author paper) is accepted by ICLR 2025๐Ÿฅน.
  • 2024.09: ย ๐ŸŽ‰๐ŸŽ‰ The Siemens internship has ended; a wonderful time๐Ÿฅน.
  • 2024.06: ย ๐ŸŽ‰๐ŸŽ‰ I graduated from Xiโ€™an Jiaotong University๐Ÿ˜„.
  • 2024.06: ย ๐ŸŽ‰๐ŸŽ‰ I receive XJTU Outstanding Graduate Student Award.
  • 2024.05: ย ๐ŸŽ‰๐ŸŽ‰ I join the Siemens in Shanghai China as an intern๐Ÿ˜Š.
  • 2024.02: ย ๐ŸŽ‰๐ŸŽ‰ I join the MIRACLE lab as a master student๐Ÿ˜Š.

๐Ÿ“ Publications

ICLR 2025
sym

Self-Supervised Diffusion MRI Denoising via Iterative and Stable Refinement

Chenxu Wu, Qingpeng Kong, Zihang Jiang & S. Kevin Zhou

  • We present Di-Fusion, an self-supervised framework that utilizes diffusion models for denoising diffusion MRI.
CVPR 2025
sym

AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIP

Wenxin Ma, Xu Zhang, Qingsong Yao, Fenghe Tang, Chenxu Wu, Yingtai Li, Rui Yan, Zihang Jiang & S.Kevin Zhou

  • AA-CLIP enhances CLIPโ€™s anomaly discrimination ability in both text and visual spaces while preserving its generalization capability.
MIA submission
sym

Hi-End-MAE: Hierarchical encoder-driven masked autoencoders are stronger vision learners for medical image segmentation

Fenghe Tang, Qingsong Yao, Wenxin Ma, Chenxu Wu, Zihang Jiang & S. Kevin Zhou

  • We pre-train Hi-End-MAE on a large-scale dataset of 10K CT scans and evaluated its performance across seven public medical image segmentation benchmarks.

๐ŸŽ– Honors and Awards

  • 2024.10 USTC Graduate First-class Scholarship.
  • 2024.06 XJTU Outstanding Graduate Student Award.
  • 2024.06 XJTU Alumni Affinity Ambassador.
  • 2023.09 XJTU First-class Scholarship.
  • 2023.09 XJTU Outstanding Students.
  • 2022.09 XJTU First-class Scholarship.
  • 2022.09 XJTU Outstanding Students.
  • 2021.09 XJTU First-class Scholarship.
  • 2021.09 XJTU Outstanding Students.

๐Ÿ“– Educations

  • 2024.09 - 2025.02 (now), M.S, University of Science and Technology of China, Anhui, China.
  • 2020.09 - 2024.06, B.E., Xiโ€™an Jiaotong University, Shannxi, China.

๐Ÿ’ป Internships

  • 2024.06 - 2024.09, Siemens, China.