I am a second-year Ph.D. student (D2) in the Natural Language Processing Laboratory at the Nara Institute of Science and Technology (NAIST), advised by Yusuke Sakai, Hidetaka Kamigaito, and Taro Watanabe.
I am actively seeking internship opportunities.
My research lies at the intersection of natural language processing, vision-language models, and trustworthy AI. I am particularly interested in evaluating and improving multimodal and large language models across cultural, scientific, and high-stakes settings. My recent work covers LLM bias and evaluation, Chinese art understanding, tool-augmented remote sensing, and clinical AI.
You can find my latest work on Google Scholar.
News
- 🎆 Sep. 2026: Three papers have been accepted to EMNLP 2026: one main conference paper and two Findings papers.
Publications
-
Where Do Vision-Language Models Fail on Abstract Reasoning? An Information Processing Analysis of ARC
Xuan Zhou, Xuefeng Wei, Zhi Qu, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe
EMNLP 2026, Main Conference (to appear) -
CArtBench: A Museum-Grounded Benchmark for Evidence-Faithful Chinese Art Understanding
Xuefeng Wei, Wang Zhixuan, Xuan Zhou, Zhi Qu, Hongyao Li, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe
Findings of EMNLP 2026 (to appear) -
ARTKGC: Leakage-Controlled Multimodal Knowledge Graph Completion for Artwork Explanation
Xuan Zhou, Xuefeng Wei, Yuta Kato, Shintaro Ozaki, Kazuki Hayashi, Yusuke Sakai, Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe
Findings of EMNLP 2026 (to appear) -
“Yuki Gets Sushi, David Gets Steak?”: Uncovering Gender and Racial Biases in LLM-Based Meal Recommendations
Xuefeng Wei, Xuan Zhou, Yusuke Sakai, Taro Watanabe
EACL 2026, Long Papers
-
A Cross-Domain Tool-Augmented Vision-Language Framework for Remote Sensing Image Understanding
Xuan Zhou, Xuefeng Wei, Zhi Qu, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe
Remote Sensing, 18(10), 1613, 2026
-
Large Language Models Are Poor Clinical Decision-Makers: A Comprehensive Benchmark
Fenglin Liu, Zheng Li, Hongjian Zhou, Qingyu Yin, Jingfeng Yang, Xianfeng Tang, Chen Luo, Ming Zeng, Haoming Jiang, Yifan Gao, Priyanka Nigam, Sreyashi Nag, Bing Yin, Yining Hua, Xuan Zhou, Omid Rohanian, Anshul Thakur, Lei Clifton, David A. Clifton
EMNLP 2024, Main Conference, pp. 13696–13710
-
FLDNet: A Foreground-Aware Network for Polyp Segmentation Leveraging Long-Distance Dependencies
Xuefeng Wei, Xuan Zhou
ICONIP 2023
-
Feature Aggregation Network for Building Extraction from High-Resolution Remote Sensing Images
Xuan Zhou, Xuefeng Wei
PRICAI 2023
Education
Nara Institute of Science and Technology (NAIST), Japan
- Ph.D. Student in Computer Science, 2024.10 - present
- Research: Computational Linguistics and Multimodal Large Language Models
- Supervisors: Yusuke Sakai, Hidetaka Kamigaito, and Taro Watanabe
Institut Polytechnique de Paris, France
- Master's degree in Electronic Information, 2021.10 - 2023.10
Chongqing Three Gorges University, China
- Bachelor's degree in Electronic Information Engineering, 2018.09 - 2020.06
Research Experience
Centrale Méditerranée, France
- Research Internship, 2023.02 - 2023.08
- Worked on visual explanation methods and developed Sim-CAM based on Opti-CAM.