Hang Wu

Hang Wu

Tongji University

Hi there! My name is Hang Wu (吴杭), you can also call me by my English name Laurent.

I am currently an incoming PhD student at University of California, Merced. My main research interests are in vision-language models and large multimodal models, with a focus on improving their performance and specific applications. During my undergraduate studies, I also worked on image processing tasks in the low-level vision field.

During my undergraduate studies, I had the privilege of joining Ni’s group at the School of Computer Science and Technology, Tongji University, as a research intern. Under Prof. Zhangkai Ni’s mentorship, I focused on research in the low-level vision field, primarily image processing and High Dynamic Range (HDR) reconstruction. Recently, I joined the UC Merced NLP Lab as a research intern, where I am working under the mentorship of Prof. Yiwei Wang on vision-language models.

You can find my CV here: Hang Wu’s Curriculum Vitae. If you are interested in my work, please feel free to drop me an email.

🔥 News

  • 2025.04: Thrilled to accept Ph.D offer from UC Merced. Looking forward to working and living in CA!
  • 2025.03: Join Vivo as an assistant NLP engineer!
  • 2024.11: One paper submitted to CVPR 2025!

📝 Publications

sym

DiMo-GUI: Advancing Test-time Scaling in GUI Grounding via Modality-Aware Visual Reasoning

Hang Wu, Hongkai Chen$^{\dagger}$, Yujun Cai, Chang Liu, Qingwen Ye, Ming-Hsuan Yang, Yiwei Wang

Arxiv 2025

  • We propose DiMo-GUI, a training-free framework that can be seamlessly integrated as a plug-and-play component into any GUI agent.
  • Without requiring additional training or external data, DiMo-GUI effectively enhances grounding performance across various GUI tasks.

🎖 Honors and Awards

  • 2022.09 Scholarship for Outstanding Students, Tongji University.

📖 Educations

  • 2025.08 - Present, PhD student, University of California, Merced.
  • 2021.09 - 2025.6, Undergraduate student, Tongji University.

📚 Projects

sym

Research on Perception-oriented High Dynamic Range Imaging Systems

Project | National-level Innovation Project

  • We treat artifacts in HDR images as detectable entities, explicitly detect and suppress them to enhance HDR quality.
  • National-level innovation project at Tongji University, with a funding of 10,000 RMB.

💻 Internships

  • 2025.03 - Present, Assistant NLP Engineer, Vivo@Shenzhen, China.
  • 2025.01 - 2025.07, Research Intern, UC Merced NLP Lab@University of California-Merced, Remote.
  • 2023.09 - 2025.03, Research Intern, Ni’s Group@Tongji University, Shanghai, China.