Ziqiao Weng
Scholar

Ziqiao Weng

Google Scholar ID: lwyU9_IAAAAJ
Sichuan University, The Hong Kong University of Science and Technology (Guangzhou)
Deep LearningMultimodalVision-Language model
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
18
 
H-index
2
 
i10-index
1
 
Publications
3
 
Co-authors
4
list available
Contact
Emailkatie312@gmail.comCVOpen ↗GitHubOpen ↗
Publications
1 items
StruVis: Enhancing Reasoning-based Text-to-Image Generation via Thinking with Structured Vision
2026
Cited
0
Resume (English only)
Academic Achievements
  • 1. Attended the NUS SOC workshop in Singapore; won second prize and received an A+, June 26, 2023
  • 2. National Second Prize in the Chinese Collegiate Computing Competition, May 27, 2023
  • 3. Sichuan University Huawei Smart Base Scholarship, September 27, 2023
  • 4. Jiangsu Wujiang High-tech Industrial Park College Student Innovation Scholarship, June 26, 2023
  • 5. EdgeX China Challenge Technology Award, September 27, 2022
  • 6. Sichuan University First-Class Student Scholarship, September 22, 2021
Research Experience
  • 1. Research Intern at HKUST(GZ), NLP lab, starting February 27, 2025
  • 2. Intern at Midea Group, AI Research Institute, working on multimodal large language models for OCR and RAG systems, starting August 23, 2024
  • 3. Research Intern at West China Hospital & SenseTime Lab, starting September 27, 2023
Education
  • 1. MPhil in Artificial Intelligence, The Hong Kong University of Science and Technology (Guangzhou), Guangdong, China, starting September 22, 2025
  • 2. Bachelor of Engineering in Computer Science, Sichuan University (SCU), Sichuan, China, starting September 22, 2021
Background
  • She is currently pursuing her MPhil degree at The Hong Kong University of Science and Technology, Guangzhou campus, expected to graduate in 2027. Previously, she graduated from Sichuan University and conducted research under Prof. Kang Li at Huaxi & SenseTime Lab. She is now a researcher at the HKUST(GZ) NLP Lab under the guidance of Xuming Hu, focusing on multimodal retrieval, panoramic spatial reasoning, and omni-directional scene understanding. Her research interests center on computer vision and multimodal learning, with a particular focus on large-scale vision models, multi-view spatial reasoning, and retrieval-augmented generation. She aims to improve the practicality of AI-generated contexts in real-world applications by exploring strategies for effectively leveraging imperfect and heterogeneous data.
Miscellany
  • She is currently seeking intern opportunities! Feel free to contact her.
Co-authors
4 total
Xu Zheng
Xu Zheng
PhD Candidate, HKUST(GZ) | Resident Doctoral Researcher, INSAIT, Sofia University | NEU
Xuming Hu
Xuming Hu
Assistant Professor, HKUST(GZ) / HKUST
Luc Van Gool
Luc Van Gool
professor computer vision INSAIT Sofia University, em. KU Leuven, em. ETHZ, Toyota Lab TRACE
Yuanhuiyi Lyu
Yuanhuiyi Lyu
PhD Student, The Hong Kong University of Science and Technology (Guangzhou)