Hulingxiao   He  [中文版]

Ph.D. Candidate （Supervisor: Prof. Yuxin Peng）

Multimedia Information Processing Lab

Wangxuan Institute of Computer Technology

Peking University

No. 128, Zhong-Guan-Cun North Street

Beijing 100080, China

E-mail: hehulingxiao@stu.pku.edu.cn

Research Directions

• Fine-graind Large Multi-modal Models

Education

• Ph.D. Candidate, Computer Science and Technology (Intelligence Science and Technology), Wangxuan Institute of Computer Technology, Peking University, 2023 - Now
• B.S., Automation (teaching in English), School of Automation, Beijing Institute of Technology, 2019-2023
• Double Bachelor Degree of Business Administration, School of Management and Economics, Beijing Institute of Technology, 2020-Now

Awards

• 2023     Outstanding Graduate in Beijing Institute of Technology
• 2022     Outstanding League Cadres
• 2021     National Scholarship
• 2021     Pacemaker to Merit Student in Beijing Institute of Technology
• 2021     Finalist Award in Mathematical Contest in Modeling
• 2021     First Prize in the Beijing Division in Contemporary Undergraduate Mathematical Contest in Modeling
• 2021     National Winner Award in HUAWEI Cloud AI competition - Unmanned Vehicle Challenge Cup

Publication

1. Hulingxiao He, Zhi Tan and Yuxin Peng*, "Taxonomy-Aware Representation Alignment for Hierarchical Visual Recognition with Large Multimodal Models", The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2026 (CVPR), Denver CO, USA, Jun. 3-7, 2026. (Accept)
2. Tianxiang Du, Hulingxiao He and Yuxin Peng*, "Venus: Benchmarking and Empowering Multimodal Large Language Models for Aesthetic Guidance and Cropping", The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2026 (CVPR), Denver CO, USA, Jun. 3-7, 2026. (Accept)
3. Hulingxiao He, Zijun Geng and Yuxin Peng*, "Fine-R1: Make Multi-modal LLMs Excel in Fine-Grained Visual Recognition by Chain-of-Thought Reasoning", The Fourteenth International Conference on Learning Representations (ICLR), Rio de Janeiro, Brazil, Apr. 23-27, 2026. (Accept)
4. Yuxin Peng*, Zishuo Wang, Geng Li, Xiangtian Zheng, Sibo Yin and Hulingxiao He, "A Survey on Fine-Grained Multimodal Large Language Models", Chinese Journal of Electronics (CJE), 2026. (Accept)【pdf】
5. Hulingxiao He, Geng Li, Zijun Geng, Jinglin Xu and Yuxin Peng*, "Analyzing and Boosting the Power of Fine-Grained Visual Recognition for Multi-modal Large Language Models", The Thirteenth International Conference on Learning Representations (ICLR), Singapore, Apr. 24-28, 2025. (Accept)【pdf】【source code】【model】【机器之心报道】
6. Hulingxiao He, Yaqi Zhang, Jinglin Xu and Yuxin Peng*, "CountMamba: Exploring Multi-directional Selective State-Space Models for Plant Counting", The 7th Chinese Conference on Pattern Recognition and Computer Vision (PRCV), Urumqi, China, Oct. 18-20, 2024. 【pdf】
7. Hulingxiao He, Xiangteng He*, Yuxin Peng, Zifei Shan and Xin Su, "Firzen: Firing Strict Cold-Start Items with Frozen Heterogeneous and Homogeneous Graphs for Recommendation", 40th IEEE International Conference on Data Engineering (ICDE), Utrecht, Netherlands, May 13 - 16th, 2024.【pdf】【source code】
8. Hulingxiao He, Wu Yuan, Yidian Huang, Shilong Zhao, Wen Yuan and Hanqing Li, "Learning Unified Representations for Multi-Resolution Face Recognition", 34th British Machine Vision Conference (BMVC), Aberdeen, UK, Nov.20 - 24, 2023. 【pdf】【source code】

Personal Interests

• Classical Guitar
• Calligraphy
• Hiking