👋 About Me

Hello! I am a Ph.D. student in Artificial Intelligence at the School of Computer Science, Wuhan University. My current research focuses on image perception and reasoning for Multimodal Large Language Models.

I am interested in building AI systems that can perceive the visual world more precisely and reason about it more reliably. Despite recent progress in multimodal large language models (MLLMs), current AI systems still struggle with fine-grained visual details, high-resolution images, spatial reasoning in visual evidence. I believe that advancing visual intelligence requires more than recognizing objects or generating descriptions; AI systems should be able to identify critical visual evidence, understand complex visual structures, and reason over what they see.

To this end, my recent work explores spatial reasoning (coming soon), high-resolution image perception (RAP and HR-Bench), and AIGC detection. I have authored or co-authored more than ten papers in leading conferences and journals, including ICML, NeurIPS, CVPR, ACM MM, AAAI, Pattern Recognition. Previously, I interned at Tencent YouTu Lab and Hikvision.

My long-term goal is to develop AI systems with stronger, more reliable, and more efficient visual perception and reasoning capabilities.

🌟 Research Interests

• Multimodal Large Language Models

  8K image benchmark - HR-Bench (AAAI 2025).

  High-resolution image perception methods - $DC^2$ (AAAI 2025) & RAP (ICML 2025).

  AIGC Detection - TranX-Adapter (ICML 2026)

• Multimodal Sentiment Analysis

  Incorporating world knowledge for MSA - WisdoM (ACM MM 2024).

  MSA with Incomplete Data - LNLN (NeurIPS 2024)

• Facial Expression Recognition

  Multi-modal and compound affective database - MAFW (ACM MM 2022)

  Expression Snippet Transformer - EST (Pattern Recognition)

  Pose-disentangled contrastive learning - PCL (CVPR 2023).

📧 News

• [06/2026] One paper has been accepted by ECCV 2026! Congratulations to my collaborators! 🥳
• [05/2026] One paper has been accepted by ICML 2026! 🥳
• [12/2025] I was awarded the National Scholarship! 🎉
• [11/2025] Our HR-Bench was selected in the Qwen3-VL technical report for evaluating the “Perception with Tool” capability.🎉
• [08/2025] One paper has been accepted by EMNLP 2025! 🎉
• [07/2025] I was awarded the China Scholarship Council (CSC) scholarship to visit Singapore Management University as a Visiting Ph.D. Student, supervised by Prof. Pan Zhou. 🎉
• [06/2025] Our paper Retrieval-Augmented Perception: High-Resolution Image Perception Meets Visual RAG was accepted as an Oral (top 1%) at ICML 2025! 🎉
• [12/2024] One regular paper has been accepted by AAAI 2025! 🥳
• [10/2024] One paper has been accepted by NeurIPS 2024! 🥳
• [07/2024] One paper has been accepted by ACM MM 2024! 🥳

📗 Education

• Singapore Management University October 2025 – Present

  Visiting Ph.D. Student in School of Computing and Information Systems, Singapore.

  Supervised by Pan Zhou.

• Wuhan University, September 2023 – Present

  Ph.D. Student in School of Computer Science, Wuhan, China.

  Supervised by Yong Luo.

• China University of Geosciences, Wuhan September 2020 – June 2023

  Master Student in School of Computer Science, Wuhan, China.

  Supervised by Yuanyuan Liu.

• China University of Geosciences, Wuhan September 2016 – June 2020

  Bachelor, Wuhan, China.

🏆 Honors & Awards

• 2025 National Scholarship.
• 2020-2021 First-class Academic Scholarship for Graduate Students.
• 2021 The 4-th ZhongQing Cup Mathematical Modeling Contest, Special Prize.
• 2018 Principal Scholarship.
• 2018 School Outstanding Student in China University of Geosciences, Wuhan.
• 2018 The 9-th LanQiao Cup Programming Competition, Third Prize, China.
• 2018 The 9-th LanQiao Cup Programming Competition, First Prize, Hubei Province.