Zongyu Wu
About Me
I am a second-year PhD student in the College of Information Sciences and Technology at Penn State University. I am co-advised by Prof. Suhang Wang and Prof. Xiang Zhang. Previously, I obtained my Bachelor's degree in Computer Science and Technology at Chongqing University in 2023. My recent research interests focus on large language models, multimodal learning, and AI agents, with particular emphasis on:
- Develop trustworthy (multimodal) language models and AI agents, such as safe content generation.
- Enhance foundation models and agents through techniques like retrieval-augmented generation and reinforcement learning.
News
- [05/2025] One paper was accepted to ACL Findings 2025.
- [05/2025] One paper was accepted to KDD 2025.
- [05/2025] Start a new position as an Applied Scientist Intern at Amazon Web Services.
- [05/2025] One paper was accepted by ICML 2025.
- [02/2025] Check out our benchmark about the positive role of language prior in large vision-language models.
- [01/2025] Two papers were accepted by ICLR 2025 (One Oral).
- [11/2024] Check out our survey about small language models in the era of large language models.
- [10/2024] One paper was accepted by WSDM 2025 (Oral).
- [09/2024] One paper was accepted by NeurIPS 2024 (Spotlight).
- [07/2024] Our survey about graph counterfactual learning is accepted by Machine Intelligence Research.
- [03/2024] One paper was accepted by NAACL 2024.
- [08/2023] Started my Ph.D. journey at Penn State University.
Experience
-
Applied Scientist Intern, Amazon Web Services, 05/2025 - Present
Work with Dr. Haibo Ding, Dr. Zhichao Xu and Dr. Yun Zhou
Santa Clara, California, United States
Selected Publications [Full Papers]
(* indicates equal contribution)
Conference Papers
-
Divide-Verify-Refine: Can LLMs Self-align with Complex Instructions?
Xianren Zhang, Xianfeng Tang, Hui Liu, Zongyu Wu, Qi He, Dongwon Lee, Suhang Wang
Accepted by 63rd Annual Meeting of the Association for Computational Linguistics (Findings of ACL), 2025
[Paper] [Code]
-
Are You Using Reliable Graph Prompts? Trojan Prompt Attacks on Graph Neural Networks
Minhua Lin*, Zhiwei Zhang*, Enyan Dai, Zongyu Wu, Yilong Wang, Xiang Zhang, Suhang Wang
Accepted by 31st SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2025
[Paper] [Code]
-
Test-Time Multimodal Backdoor Detection by Contrastive Prompting
Yuwei Niu*, Shuo He*, Qi Wei, Zongyu Wu, Feng Liu, Lei Feng
Accepted by 42nd International Conference on Machine Learning (ICML), 2025
[Paper]
-
Robustness Inspired Graph Backdoor Defense
Zhiwei Zhang, Minhua Lin, Junjie Xu, Zongyu Wu, Enyan Dai, Suhang Wang
In proceedings of the 13th International Conference on Learning Representations (ICLR, Oral), 2025
[Paper] [Code]
-
Catastrophic Failure of LLM Unlearning via Quantization
Zhiwei Zhang, Fali Wang, Xiaomin Li, Zongyu Wu, Xianfeng Tang, Hui Liu, Qi He, Wenpeng Yin, Suhang Wang
In proceedings of the 13th International Conference on Learning Representations (ICLR), 2025
[Paper] [Code]
-
Bridging Source and Target Domains via Link Prediction for Unsupervised Domain Adaptation on Graphs
Yilong Wang, Tianxiang Zhao, Zongyu Wu, Suhang Wang
In Proceedings of the 18th ACM International Conference on Web Search and Data Mining (WSDM, Oral), 2025
[Paper]
-
Leveraging Catastrophic Forgetting to Develop Safe Diffusion Models against Malicious Finetuning
Jiadong Pan*, Hongcheng Gao*, Zongyu Wu, Taihang Hu, Li Su, Qingming Huang, Liang Li
In Proceedings of the 38th Conference on Neural Information Processing Systems (NeurIPS, Spotlight), 2024
[Paper] [Code]
-
Universal Prompt Optimizer for Safe Text-to-Image Generation
Zongyu Wu*, Hongcheng Gao*, Yueze Wang, Xiang Zhang, Suhang Wang
In Proceedings of the North American Chapter of the Association for Computational Linguistics (NAACL), 2024
[Paper] [Code]
Journal Papers
-
Counterfactual Learning on Graphs: A Survey
Zhimeng Guo, Zongyu Wu, Teng Xiao, Charu Aggarwal, Hui Liu, Suhang Wang
Machine Intelligence Research, 2025
[Paper] [Project Page]
Preprints
-
LanP: Rethinking the Impact of Language Priors in Large Vision-Language Models
Zongyu Wu*, Yuwei Niu*, Hongcheng Gao, Minhua Lin, Zhiwei Zhang, Zhifang Zhang, Qi Shi, Yilong Wang, Sike Fu, Junjie Xu, Junjie Ao, Enyan Dai, Lei Feng, Xiang Zhang, Suhang Wang
Arxiv'2502.12359
[Paper] [Code] [Project Page]
-
A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness
Fali Wang, Zhiwei Zhang, Xianren Zhang, Zongyu Wu, Tzuhao Mo, Qiuhao Lu, Wanjing Wang, Rui Li, Junjie Xu, Xianfeng Tang, Qi He, Yao Ma, Ming Huang, Suhang Wang
Arxiv'2411.03350
[Paper] [Project Page]
-
Decoding Time Series with LLMs: A Multi-Agent Framework for Cross-Domain Annotation
Minhua Lin, Zhengzhang Chen, Yanchi Liu, Xujiang Zhao, Zongyu Wu, Junxiang Wang, Xiang Zhang, Suhang Wang, Haifeng Chen
Arxiv'2410.17462
[Paper]
-
LLM and GNN are Complementary: Distilling LLM for Multimodal Graph Learning
Junjie Xu, Zongyu Wu, Minhua Lin, Xiang Zhang, Suhang Wang
Arxiv'2406.01032
[Paper] [Code]
Honors & Award
First-class Scholarship in Chongqing University (top3%)
Outstanding Student in CQU, 2022
Outstanding Undergraduate Graduate of Chongqing University
Academic Service
Conference Program Committee/Reviewer
NeurIPS (2024, 2025), ICLR (2025), ICML (2025), KDD (2025), CVPR (2025), AISTATS (2025), AAAI (2025), LoG (2024), CIKM (2024), ECCV (2024), ACL (2024, 2025), EMNLP (2024)
Conference External Reviewer
SIGIR (2024), RecSys (2024), ICDM (2024), BigData (2024)
Journal Reviewer
ACM TKDD, IEEE TKDE, IEEE TNNLS, ACM TIST, TMLR
Teaching
Teaching Assistant, DS 220: Data Management for Data Sciences, PSU, Spring 2025
Teaching Assistant, DS 220: Data Management for Data Sciences, PSU, Fall 2024
Miscellaneous
Sports: I enjoy working out in my free time. I am also obsessed with soccer.
Travel: I love traveling and exploring new places.
Photography: I like capturing beautiful moments with my camera.
Games: I enjoy playing games such as CS2 (2000 hours+, plus CS GO) and Teamfight Tactics.