☕️
Jeffrey Ma 马洁锋
Third-year PhD at NERC-SLIP lab, SPRAT team, USTC.
University of Science and Technology of China (USTC)
National Engineering Research Center of Speech and Language Information Processing (NERC-SLIP)
Signal Processing and Pattern Recognition Application Team (SPRAT)
My name is Jiefeng Ma, but you may also refer to me as Jeffrey. I am currently in my third year as a PhD candidate at the NERC-SLIP Lab, where I have the privilege of working under the guidance of Prof. Du. My research endeavors primarily revolve around document intelligence, multimodal learning, and AI Generated Content (AIGC).
As the field of AIGC continues to grow, it encompasses the creation and optimization of content using advanced artificial intelligence techniques. I am dedicated to contributing significantly to this area through rigorous investigation and innovative problem-solving as I progress in my academic pursuits.
Skills
Experience
Responsibilities include:
- PDF parser system
- Document reconstruction
- Mathematical reasoning
Collaborators and Friends: Jianshu Zhang (张建树), Zhenrong Zhang (张镇荣)
Responsibilities include:
- Document layout pretrain
- Document key information extraction
- Few-shot & zero-shot learning
Collaborators and Friends: Haoyu Cao (曹浩宇), Zhongzhong Li (李中中), Sheng Kang (康昇), Wenwen Yu (余文文)
Featured Publications
We built a large-scale dataset named HRDoc, which consists of 2,500 multi-page documents with nearly 2 million semantic units. Moreover, we proposed an encoder-decoder-based hierarchical document structure parsing system (DSPS) to tackle document structure reconstruction task. Code and dataset are available at https://github.com/jfma-USTC/HRDoc.
