Yuhan Wang

Yuhan Wang

Undergrad student at Sichuan University

👋 About Me

Hi, I’m Yuhan Wang, an undergraduate student at Sichuan University, majoring in software engineering. Currently, I’m presently serving as a research intern with Prof.Wei Shao from University of Florida. Before that, I worked as a research intern at Sichuan University under the guidance of Prof.Yan Wang.

Ph.D. Aspirations

I’m actively seeking a Ph.D. position for Fall 2024, and I’m dedicated to developing efficient medical AI systems with nice theoretical guarantees and practical values.

Research Interests

I am presently engrossed in extensive research that centers around enhancing the efficiency and controllability of DPMs within the realm of medical imaging. In light of the swift evolution of generation models (LLMs, DPMs, etc.), high quality generations frequently coincide with inaccurate or nonsensical outcomes. This facet becomes particularly untenable when applied to healthcare fields. My long-term research aspiration is committed to enhancing the explainability and efficiency of these models to establish AI-driven medical systems which can tackle intricate real-world clinical issues.

Presently, my primary focus encompasses, yet is not confined to, these research subjects (Feel free to get in touch for any prospective opportunities for collaboration!😋😋):

  • Practical applications of generative models (Stable Diffusion, image reconstruction, AI healthcare, etc.)
  • Dense prediction and image segmentation
  • Knowledge distillation and model compression

🔥 News

  • 2023.08.04:  🎉🎉 My personal website was established today!
  • 2023.05.28:  🎉🎉 My first paper is early accepted by MICCAI 2023.(top14%)

📝 Publications

(* indicates equal contribution; # indicates corresponding authorship.)

MICCAI 2023
sym

Contrastive Diffusion Model with Auxiliary Guidance for Coarse-to-Fine PET Reconstruction (MICCAI 2023)

Ze Han*, Yuhan Wang* , Luping Zhou, Peng Wang, Binyu Yan, Jiliu Zhou, Yan Wang#, and Dinggang Shen#

code

  • This paper presents a coarse-to-fine PET reconstruction framework using diffusion models. The coarse-to-fine design can significantly improve the overall sampling speed of our method. Furthermore, two additional strategies, i.e., an auxiliary guidance strategy and a contrastive diffusion strategy, are proposed and integrated into the reconstruction process, which can enhance the correspondence between the LPET image and the RPET image, further improving clinical reliability.

🎖 Honors and Awards

  • 2023.3, 3th, The 9th China International College Students’ ‘Internet+’ Innovation and Entrepreneurship Competition(National Final)
  • 2022.12, 1th, National College Students’ Research Training Program
  • 2022.9 , 1th, National Encouragement Scholarship
  • 2021.9 , 1th, National Scholarship
  • 2020.12, 1th, The Sichuan University First Prize Scholarship

📖 Educations

  • 2019.09 - 2024.06, Undergraduate, Sichuan University, China

🐝 Academic Services

Reviewer

  • International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2023)