Biography

I am a first-year Ph.D. student at the University of Hong Kong (HKU), supervised by Prof. Ping Luo at MMLAB@HKU. I previously received my B.Eng. with Outstanding Graduate Honors from Nanjing University (NJU).

My research interests lie in agent-centric post-training of large vision–language models and their practical applications, with a current emphasis on LLM-based agents in GUI and trading domains.

News

• [06/2025] GUIOdyssey was accepted to ICCV’25, with 100+ GitHub stars and 500K+ Hugging Face downloads!
• [04/2025] PhyGenBench was accepted to ICML’25.
• [03/2025] MM-EUREKA received 700+ GitHub stars.
• [01/2025] MMIU was accepted to ICLR’25.
• [05/2024] ChartAssistant was accepted to ACL’24.
• [05/2024] MMT-Bench was accepted to ICML’24.
• [03/2024] OmniMedVQA was accepted to CVPR’24.
• [10/2022] Awarded the National Scholarship.

Selected Publications

• TVWorld: Foundations for Remote-Control TV Agents,
  Zhantao Ma^*, Quanfeng Lu^*, Shuai Zhong, Dahai Yu, Ping Luo, Michael K. Ng
  arXiv, 2026. Paper, Code, Hugging Face
• SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control,
  Quanfeng Lu, Zhantao Ma, Shuai Zhong, Jin Wang, Dahai Yu, Michael K Ng, Ping Luo
  arXiv, 2025. Paper, Code
• UniFork: Exploring Modality Alignment for Unified Multimodal Understanding and Generation,
  Teng Li, Quanfeng Lu, Lirui Zhao, Hao Li, Xizhou Zhu, Yu Qiao, Jun Zhang, Wenqi Shao
  Paper, Code
• GUIOdyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices,
  Quanfeng Lu, Wenqi Shao, Zitao Liu, Lingxiao Du, …, Ping Luo
  ICCV, 2025. Paper, Code, Hugging Face
• MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning,
  Fanqing Meng, Lingxiao Du, Zongkai Liu, Zhixiang Zhou, Quanfeng Lu, …, Wenqi Shao
  arXiv, 2025. Paper, Code
• OmniMedVQA: A New Large-Scale Comprehensive Evaluation Benchmark for Medical LVLM,
  Yutao Hu^*, Tianbin Li^*, Quanfeng Lu^*, Wenqi Shao, Junjun He, Yu Qiao, Ping Luo
  CVPR, 2024. Paper, Code
• ChartAssisstant: A Universal Chart Multimodal Language Model via Chart-to-Table Pre-training and Multitask Instruction Tuning,
  Fanqing Meng, Wenqi Shao, Quanfeng Lu, Peng Gao, Kaipeng Zhang, Yu Qiao, Ping Luo
  ACL, 2024. Paper

Education

• Sept. 2025 - June. 2029 (expected) Ph.D., The University of Hong Kong.
• Sept. 2020 - June. 2024 B.Eng., Nanjing University.
• Sept. 2017 - July. 2020 The Affiliated High School of South China Normal University.

Selected Honors

• [2024] Outstanding Graduate of Nanjing University
• [2022] National Scholarship

Services

Conference Reviewers:

• CVPR: 2025, 2026
• ICCV: 2025
• ECCV: 2024, 2026
• ICLR: 2026
• ICML: 2026
• ACL: 2026
• ACM MM: 2025