Xiao Liu

I am currently a fourth-year Ph.D. student in the Department of Computer Science at the University of California, Davis, under the supervision of Prof. Jiawei Zhang. Before joining UC Davis, I completed my B.S. degree in Software Engineering at Southeast University. My research is focused on natural language processing, particularly in the areas of text summarization, graph-based NLP techniques, multimodal learning, and large language models.

Research Interests

• Natural Language Processing
  • Text Summarization
  • Graph-based NLP
  • Large Language Models
• Multimodal Learning
  • Visual Question Answering
  • Vision Language Models

News

• [2025-04] Passed my Ph.D. Qualifying Exam. Becoming a Ph.D. Candidate!
• [2025-03] Our Toolkit, AIGVE-Tool: AI-Generated Video Evaluation Toolkit with Multifaceted Benchmark is available on arXiv.
• [2024-10] Our Survey, A Survey of AI-Generated Video Evaluation is available on arXiv.
• [2024-07] Our paper, Beyond Text: Unveiling Multimodal Proficiency of Large Language Models with MultiAPI Benchmark is accepted by KnowledgeLM@ACL 2024.
• [2024-06] I started my internship at Amazon Web Services (AWS) as an applied scientist intern. Mentored by Dr. Yoshinari Fujinuma, Dr. Shuaichen Chang, and Dr. Yogarshi Vyas.
• [2024-04] RoastPic is online!
• [2024-03] Our paper, GPTA: Generative Prompt Tuning Assistant for Synergistic Downstream Neural Network Enhancement with LLMs is available on arXiv.