Weize Liu

prof_pic.png

I am a first-year Ph.D. student in Computer Science at the University of Maryland, College Park, advised by Prof. Furong Huang.

My research interests lie in Large Language Models (LLMs) and Vision-Language Models (VLMs), specifically focusing on synthetic data, reasoning, and agents. My previous research has primarily focused on enhancing the diverse capabilities of LLMs (especially reasoning) and on synthetic data. I am currently working on improving the agent capabilities of LLMs.

news

Sep 2025 Started the Computer Science Ph.D. program at the University of Maryland, College Park.
Jun 2025 Completed the M.Eng. in Computer Technology at Zhejiang University.
May 2025 Started a research internship at Alibaba Group (Future Life Lab, Taobao & Tmall Group).

selected publications

  1. arXiv
    DESIGNER: Design-Logic-Guided Multidisciplinary Data Synthesis for LLM Reasoning
    Weize Liu, Yongchi Zhao, Yijia Luo, and 8 more authors
    arXiv preprint 2025
  2. NAACL
    Mind’s Mirror: Distilling Self-Evaluation Capability and Comprehensive Thinking from Large Language Models
    Weize Liu, Guocong Li, Kai Zhang, and 6 more authors
    NAACL 2024
  3. EMNLP
    Unraveling Babel: Exploring Multilingual Activation Patterns of LLMs and Their Applications
    Weize Liu, Yinlong Xu, Hongxia Xu, and 3 more authors
    EMNLP 2024
  4. ACL
    From Misleading Queries to Accurate Answers: A Three-Stage Fine-Tuning Method for LLMs
    Guocong Li, Weize Liu, Yihang Wu, and 4 more authors
    ACL 2025