Zeyu Liu (Latest updates 2025/08)

🤗 About me

• I am a first-year PhD student in the Department of Computing of Hong Kong Polytechnic University, advised by Prof. Hongxia Yang.
• My current research interests are mainly in Applications of MLLMs and MLLM Reasoning Enhancement.

🤯 Research Interests

• Multimodal Large Language Model: Downstream Applications (Medical and Mathematics) and Reasoning Enhancement of Multimodal Large Language Models.
• Machine Learning, especially Multi-Task Learning and Curriculum Learning.

📝 Publications and Manuscripts

(*Equal contribution)

• Adaptive Data and Task Joint Scheduling for Multi-task Learning.
  ICDE 2025
  Keywords: Multi-task Learning, Curriculum learning, Task conflicts
  👥: Zeyu Liu, Heyan Chai, Chaoyang Li, Lingzhi Wang, and Qing Liao.

• Joint Scheduling of Causal Prompts and Tasks for Multi-Task Learning.
  CVPR 2025
  Keywords: Multi-task Learning; Prompt Learning; Causal Learning
  👥: Chaoyang Li, Jianyang Qin, Jinhao Cui, Zeyu Liu, Ning Hu, and Qing Liao.

• InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization.
  2025 Under Review
  Keywords: MLLM; GUI Agent; Reinforcement Learning
  👥: Yuhang Liu*, Zeyu Liu*, Shuanghe Zhu, Pengxiang Li, Congkai Xie, Jiasheng Wang, Xavier Hu, Xiaotian Han, Jianbo Yuan, Xinyao Wang, Shengyu Zhang, Hongxia Yang, Fei Wu.

• Infi-MMR: Curriculum-based Unlocking Multimodal Reasoning via Phased Reinforcement Learning in Multimodal Small Language Models
  2025 Under Review
  Keywords: MLLM; Reasoning; Reinforcement Learning
  👥: Zeyu Liu*, Yuhang Liu*, Guanghao Zhu, Congkai Xie, Zhen Li, Jianbo Yuan, Xinyao Wang, Qing Li, Shing-Chi Cheung, Shengyu Zhang, Fei Wu, Hongxia Yang

• Infi-Med: Low-Resource Medical MLLMs with Robust Reasoning Evaluation.
  2025 Under Review
  Keywords: MLLM; Medical
  👥: Zeyu Liu*, Zhitian Hou*, Yining Di, Kejing Yang, Zhijie Sang, Congkai Xie, Jingwen Yang, Siyuan Liu, Jialu Wang, Chunming Li, Ming Li, Hongxia Yang

• InfiR: Crafting Effective Small Language Models and Multimodal Small Language Models in Reasoning.
  2025 arXiv
  Keywords: Pre-train; Post-train; Low Resource
  👥: Congkai Xie, Shuo Cai, Wenjun Wang, Pengxiang Li, Zhijie Sang, Kejing Yang, Yiming Zhang, Zhen Li, Guanghao Zhu, Zeyu Liu, Yang Yu, Yuhang Liu, Su Lu, Baoyi He, Qi Zhou, Xiaotian Han, Jianbo Yuan, Shengyu Zhang, Fei Wu, Hongxia Yang

• Learning from Easy to Hard: Multi-Task Learning with Data Scheduling.
  ICASSP 2024
  Keywords: Multi-task Learning, Data Scheduling, Task conflicts
  👥: Zeyu Liu, Heyan Chai, and Qing Liao.

• Towards Task-Conflicts Momentum-Calibrated Approach for Multi-task Learning.
  ICDE 2024
  Keywords: Multi-task Learning, Gradient Manipulation, Task Conflicts
  👥: Heyan Chai, Zeyu Liu, Yongxin Tong, Ziyi Yao, Binxing Fang, and Qing Liao.