Liangwei Yang

Liangwei Yang

Research Scientist at Salesforce Research

Salesforce Research

Biography

Glad to meet you here. Currently I am a research scientist at Salesforce Research working on efficient modeling and agents. Previously I obtained my Ph.D. degree from University of Illinois Chicago, under the supervision of professor Philip S. Yu. Even before, I accomplish my Master degree under the supervision of professor Hui Gao and Tao Zhou from University of Electronic Science and Technology of China. I am always open to learn new things, and enjoy the procedure of every task. If you are an interesting person, and enjoy your life. Welcome to contact me~

Interests
  • Agent
  • Data Mining
  • Efficient Modeling
Education

  • Ph.D in Computer Science, 2024

    University of Illinois at Chicago

  • M.S. in Computer Science, 2020

    University of Electronic Science and Technology of China (UESTC)

  • B.S. in Electronic Science and Technology, 2017

    University of Electronic Science and Technology of China (UESTC)

Latest News

 
 
 
 
 
Paper accepted by ICLR
February 2026
Our paper Entropy-Based Block Pruning for Efficient Large Language Models has been accepted by ICLR2026 ! We firstly investigate the entropy dynamics within LLMs and observe interesting findings. See you in Brazil
 
 
 
 
 
Paper accepted by AAAI
January 2026
Our paper Benchmarking llms for political science: A united nations perspective has been accepted by AAAI2026 ! It is the first LLM benchmark based on United Nations data.
 
 
 
 
 
Paper accepted by EMNLP
October 2025
Our paper Llminit: A free lunch from large language models for selective initialization of recommendation has been accepted by EMNLP2025 !

Recent Publications

Quickly discover relevant content by filtering publications.
Weizhi Zhang, Liangwei Yang, Wooseong Yang, Henry Peng Zou, Yuqing Liu, Ke Xu, Sourav Medya, Philip S Yu (2025). Llminit: A free lunch from large language models for selective initialization of recommendation. In EMNLP 2025.

PDF Cite

Weizhi Zhang, Liangwei Yang, Zihe Song, Henry Peng Zou, Ke Xu, Yuanjie Zhu, Philip S. Yu (2025). Sgcl: Unifying self-supervised and supervised learning for graph recommendation. In RecSys 2025.

PDF Cite

Juntao Tan, Liangwei Yang, Zuxin Liu, Zhiwei Liu, Rithesh RN, Tulika Manoj Awalgaonkar, Jianguo Zhang, Weiran Yao, Ming Zhu, Shirley Kokane, Silvio Savarese, Huan Wang, Caiming Xiong, Shelby Heinecke (2025). Personabench: Evaluating ai models on understanding personal information through accessing (synthetic) private user data. In ACL 2025.

PDF Cite

Mingdai Yang, Zhiwei Liu, Liangwei Yang, Xiaolong Liu, Chen Wang, Hao Peng, Philip S. Yu (2025). Training Large Recommendation Models via Graph-Language Tokens Alignment. In WWW 2025.

PDF Cite

Yueqing Liang, Liangwei Yang, Chen Wang, Congying Xia, Rui Meng, Xiongxiao Xu, Haoran Wang, Ali Payani, Kai Shu (2025). Benchmarking llms for political science: A united nations perspective. In AAAI 2026.

PDF Cite

Yuwei Cao, Liangwei Yang, Zhiwei Liu, Yuqing Liu, Chen Wang, Yueqing Liang, Hao Peng, Philip S. Yu (2025). Graph-sequential alignment and uniformity: Toward enhanced recommendation systems. In WWW 2025.

PDF Cite

Chaoguang Luo, Liuying Wen, Yong Qin, Philip S. Yu, Liangwei Yang, Zhineng Hu (2025). Diversified recommendation with weighted hypergraph embedding: Case study in music. Neurocomputing.

PDF Cite

See all publications

Experience

 
 
 
 
 
Research Scientist
Salesforce Research
Jan 2024
Palo Alto
 
 
 
 
 
Research Intern
Salesforce Research
May 2023 – Nov 2023
Palo Alto
 
 
 
 
 
Research Intern
ByteDance Applied Machine Learning Group
May 2022 – Aug 2022
Chicago

Contact