CV

Research Interest

• Visual Document Retrieval, focusing on enhancing retrieval performance through visual perception and reasoning capabilities, as well as achieving low storage costs via token compression.
• Reinforcement Learning of Multimodal Large Language Models, focusing on aligning visual and textual representations through reinforcement learning to improve multimodal understanding and generation capabilities.

Education

• Research Focus: Visual Document Retrieval, Multimodal Large Language Models
• Supervisors: Prof. Fuli Feng and Prof. Fengbin Zhu(NUS).

• Honors: Zhejiang Provincial Government Scholarship
• Research Focus: Dual Self-Attention Mechanisms
• Supervisors: Prof. Hua Zhang

Internship

• Research Focus: Agent

Skills

• Programming & Tools: Python, Java, PyTorch, Linux, Git
• Languages: Chinese