Xinnian Liang (梁新年)

Welcome to my homepage!

I am a final-year Ph.D. student studying at Beihang University, supervised by Prof. Zhoujun Li and Dr. Shuangzhi Wu. I obtained my B.S. degree at Nanjing University of Information Science & Technology. My research interest includes Large Language Models, Text Summarization, Information Extraction. I am currently mainly focusing on research related to large language model agents and their reasoning and planning capabilities.

In my spare time, I have diverse interests and enjoy activities such as football, cycling, 王者荣耀, coffee, whiskey, cocktails, and more. I welcome anyone with common interests to engage in discussions and exchange thoughts. If you have any questions and would like to communicate with me, you can reach me through the email address xnliang19@163.com.

Selected Publications

Google Scholar

  • Xinnian Liang, Shuangzhi Wu, Chenhao Cui, Jiaqi Bai, Chao Bian, Zhoujun Li: Enhancing Dialogue Summarization with Topic-Aware Global- and Local- Level Centrality. EACL 2023: 27-38. paper, code
  • Xinnian Liang, Zefan Zhou, Hui Huang, Shuangzhi Wu, Tong Xiao, Muyun Yang, Zhoujun Li, Chao Bian: Character, Word, or Both? Revisiting the Segmentation Granularity for Chinese Pre-trained Language Models. CoRR abs/2303.10893 (2023)
  • Xinnian Liang, Bing Wang, Hui Huang, Shuangzhi Wu, Peihao Wu, Lu Lu, Zejun Ma, Zhoujun Li: Unleashing Infinite-Length Input Capacity for Large-scale Language Models with Self-Controlled Memory System. CoRR abs/2304.13343 (2023)
  • Xinnian Liang, Jing Li, Shuangzhi Wu, Mu Li, Zhoujun Li: Improving Unsupervised Extractive Summarization by Jointly Modeling Facet and Redundancy. IEEE ACM Trans. Audio Speech Lang. Process. 30: 1546-1557 (2022)
  • Xinnian Liang, Jing Li, Shuangzhi Wu, Jiali Zeng, Yufan Jiang, Mu Li, Zhoujun Li: An Efficient Coarse-to-Fine Facet-Aware Unsupervised Summarization Framework Based on Semantic Blocks. COLING 2022: 6415-6425
  • Xinnian Liang, Shuangzhi Wu, Mu Li, Zhoujun Li: Modeling Multi-Granularity Hierarchical Features for Relation Extraction. NAACL-HLT 2022: 5088-5098
  • Xinnian Liang, Shuangzhi Wu, Mu Li, Zhoujun Li: Unsupervised Keyphrase Extraction by Jointly Modeling Local and Global Context. EMNLP (1) 2021: 155-164
  • Xinnian Liang, Shuangzhi Wu, Mu Li, Zhoujun Li: Unsupervised Keyphrase Extraction by Jointly Modeling Local and Global Context. CoRR abs/2109.07293 (2021)

Experience

  • Intern@ByteDance AI Lab, 2023.03-Present.
  • Intern@ByteDance Lark AI, 2022.04-2023.03.
  • Intern@Tencent CSIG-SPPD, 2020.08-2022.04.