Xin Ye(叶忻)

  My name is Xin Ye. I was a student studying at Beijing University of Posts and Telecommunications, where I studied jointly for undergraduate and postgraduate studies in Beijing, China. During my graduate studies, I studied under Professor Xiao Bo, and my research direction was mainly natural language processing.

  After I graduated, I worked in the algorithm business of search and recommendation in Alibaba Artificial Intelligence Laboratory. I am currently engaged in the research and development of natural language processing and large language model bases at Kuaishou Technology.

Email  /  Github  /  Github Campus  /  CSDN

profile photo
Research

My research interests and directions mainly focus on multi-modal search, natural language processing and large language models.The representative papers are highlighted.

Speech2Slot: A Limited Generation Framework with Boundary Detection for Slot Filling from Speech
Pengwei Wang ,Yinpei Su , Xiaohuan Zhou , Xin Ye, , Liangchen Wei , Ming Liu ,Yuan You ,Feijun Jiang
Interspeech, 2022
Paper

We propose a new encoder-decoder framework for slot filling, named Speech2Slot, leveraging a limited generation method with boundary detection.

Temporal Scaling Law for Large Language Models
Yizhe Xiong, Xiansheng Chen, Xin Ye, Hui Chen, Zijia Lin, Haoran Lian, Jianwei Niu, Guiguang Ding
Arxiv, 2024

We propose the novel concept of Temporal Scaling Law and study the loss of LLMs from the temporal dimension.

Experience
Others

Design and source code from Jon Barron's website