Welcome to my personal website!
I am Huichi Zhou (周辉池)
💡 Research Interest
- Adversarial Attack and Defense
- Natural Language Processing
- Multimodal Large Language Model
- Medical AI
🔥 News
- 2024.11.17: One paper gets accepted to SIGKDD 2025.
- 2024.06.01: One paper gets accepted ICML 2024 Oral.
- 2024.05.17: One paper gets accepted ACL 2024 Findings.
📝 Publications
💉 Medical AI
Revisiting Medical Image Retrieval via Knowledge Consolidation [PDF]
Yang Nan, Huichi Zhou, Xiaodan Xing, Giorgos Papanastasiou, Lei Zhu, Zhifan Gao, Alejandro F Frangi, Guang Yang
Beyond the Hype: A dispassionate look at vision-language models in medical scenario [PDF]
Yang Nan *, Huichi Zhou *, Xiaodan Xing, Guang Yang
😈 Adversarial Machine Learning
Evaluating and Defending Code Language Models Against Adversarial Attacks Using LLM-as-a-Judge [PDF]
Wenhan Mu, Huichi Zhou, Ling Xu, Dongping Chen, Yao Wan, Hongyu Zhang
Can Large Language Models Improve the Adversarial Robustness of Graph Neural Networks? [PDF]
Zhongjian Zhang, Xiao Wang, Huichi Zhou, Yue Yu, Mengmei Zhang, Cheng Yang, Chuan Shi
MPAT: Building Robust Deep Neural Networks against Textual Adversarial Attacks [PDF]
Fangyuan Zhang, Huichi Zhou, Shuangjiao Li, Hongtao Wang
📊 Benchmark
GUI-World: A Dataset for GUI-oriented Multimodal LLM-based Agents [PDF] [Github] [Website]
Dongping Chen *, Yue Huang *, Siyuan Wu *, Jingyu Tang *, Liuyi Chen, Yilin Bai, Zhigang He, Chenlong Wang, Huichi Zhou, Yiqiang Li, Tianshuo Zhou, Yue Yu, Chujie Gao, Qihui Zhang, Yi Gui, Zhen Li, Yao Wan, Pan Zhou, Jianfeng Gao, Lichao Sun
Knowledge Graph
RCE: Shifting Focus from Entities to Relations for Knowledge Graph Embedding [PDF]
Heng Yu, Huichi Zhou, Zhongyu He, Jianyong Zhu, Hongtao Wang,
Self-Rewarding Model
Verifiable Format Control for Large Language Model Generations [PDF]
Zhaoyang Wang*, Jinqi Jiang*, Huichi Zhou*, Huaxiu Yao
🎖 Honors and Awards
- 2023 National Scholarship (Top 1%)
⚖️ Services
- EMNLP 2024, NeurIPS 2024, ICLR 2025, AISTATS 2025, COLING 2025, ISBI 2025, ICASSP 2025, ACL ARR October 2024 Conference Reviewer
🗡️ Invited Talks
- 2024.05.24 Invited Talk at Datawhale: Evaluating the Validity of Word-level Adversarial Attacks with Large Language Models. @[Datawhale]
📖 Educations
- 2020.09 - 2024.06, BEng., North China Electric Power University.
- 2017.09 - 2020.06, QuanZhou NO.5 High School.
💻 Internships
- 2024.11 - Present, MindRank
- 2024.04 - 2024.06, Huaxiu Yao, Research Intern, University of North Carolina at Chapel Hill.