Zongyu Wu

I am a Ph.D. candidate in the College of Information Sciences and Technology at The Pennsylvania State University, where I am co-advised by Dr. Suhang Wang and Dr. Xiang Zhang. I was an Applied Scientist Intern at Amazon Web Services (AWS) in California. I received my Bachelor's degree in Computer Science and Technology from Chongqing University in 2023. My recent research interests lie in multimodal learning, graph learning, and their intersections.

Email  /  Google Scholar  /  Github

Research

* indicates equal contribution. Please see my Google Scholar profile for a more complete list.

Selected Publications
  • Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation [Paper]
    Zhichao Xu*, Zongyu Wu*, Yun Zhou, Aosong Feng, Kang Zhou, Sangmin Woo, Kiran Ramnath, Yijun Tian, Xuan Qi, Weikang Qiu, Lin Lee Cheong, Haibo Ding
    TMLR, 2026
  • Image Corruption-Inspired Membership Inference Attacks against Large Vision-Language Models [Paper]
    Zongyu Wu, Minhua Lin, Zhiwei Zhang, Fali Wang, Xianren Zhang, Xiang Zhang, Suhang Wang
    In EACL 2026 (Oral)
  • Decoding Time Series with LLMs: A Multi-Agent Framework for Cross-Domain Annotation [Paper]
    Minhua Lin, Zhengzhang Chen, Yanchi Liu, Xujiang Zhao, Zongyu Wu, Junxiang Wang, Xiang Zhang, Suhang Wang, Haifeng Chen
    In Finding of EACL 2026 (Oral)
    • Decoding Time Series with LLMs: A Multi-Agent Framework for Cross-Domain Annotation
  • Universal Prompt Optimizer for Safe Text-to-Image Generation [Paper]
    Zongyu Wu*, Hongcheng Gao*, Yueze Wang, Xiang Zhang, Suhang Wang
    In NAACL 2024
  • GPR: Empowering Generation with Graph-Pretrained Retriever [Paper]
    Xiaochen Wang, Zongyu Wu, Yuan Zhong, Xiang Zhang, Suhang Wang, Fenglong Ma
    In WWW 2026
  • Bradley-Terry and Multi-Objective Reward Modeling Are Complementary [Paper]
    Zhiwei Zhang, Hui Liu, Xiaomin Li, Zhenwei Dai, Jingying Zeng, Fali Wang, Minhua Lin, Ramraj Chandradevan, Linlin Wu, Zhen Li, Chen Luo, Zongyu Wu, Xianfeng Tang, Qi He, Suhang Wang
    In ICLR 2026
  • AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks [Paper]
    Fali Wang, Hui Liu, Zhenwei Dai, Jingying Zeng, Zhiwei Zhang, Zongyu Wu, Chen Luo, Zhen Li, Xianfeng Tang, Qi He, Suhang Wang
    In NeurIPS 2025
  • Divide-Verify-Refine: Can LLMs Self-align with Complex Instructions? [Paper, Code]
    Xianren Zhang, Xianfeng Tang, Hui Liu, Zongyu Wu, Qi He, Dongwon Lee, Suhang Wang
    In Findings of ACL 2025
  • Are You Using Reliable Graph Prompts? Trojan Prompt Attacks on Graph Neural Networks [Paper, Code]
    Minhua Lin*, Zhiwei Zhang*, Enyan Dai, Zongyu Wu, Yilong Wang, Xiang Zhang, Suhang Wang
    In KDD 2025
  • Test-Time Multimodal Backdoor Detection by Contrastive Prompting [Paper, Code]
    Yuwei Niu*, Shuo He*, Qi Wei, Zongyu Wu, Feng Liu, Lei Feng
    In ICML 2025
  • Robustness Inspired Graph Backdoor Defense [Paper, Code]
    Zhiwei Zhang, Minhua Lin, Junjie Xu, Zongyu Wu, Enyan Dai, Suhang Wang
    In ICLR 2025 (Oral)
  • Catastrophic Failure of LLM Unlearning via Quantization [Paper, Code]
    Zhiwei Zhang, Fali Wang, Xiaomin Li, Zongyu Wu, Xianfeng Tang, Hui Liu, Qi He, Wenpeng Yin, Suhang Wang
    In ICLR 2025
  • A Comprehensive Survey of Small Language Models in the Era of Large Language Models [Paper, Project Page]
    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
    ACM TIST, 2025
  • Bridging Source and Target Domains via Link Prediction for Unsupervised Domain Adaptation on Graphs [Paper]
    Yilong Wang, Tianxiang Zhao, Zongyu Wu, Suhang Wang
    In WSDM 2025 (Oral)
  • Leveraging Catastrophic Forgetting to Develop Safe Diffusion Models against Malicious Finetuning [Paper]
    Jiadong Pan, Hongcheng Gao, Zongyu Wu, Taihang Hu, Li Su, Qingming Huang, Liang Li
    In WSDM 2025 (Spotlight)

Selected Preprints
  • Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents [Preprint, Code]
    Minhua Lin, Juncheng Wu, Zijun Wang, Zhan Shi, Yisi Sang, Bing He, Zewen Liu, Tianxin Wei, Zongyu Wu, Zhiwei Zhang, Dakuo Wang, Xiang Zhang, Benoit Dumoulin, Cihang Xie, Yuyin Zhou, Suhang Wang, Hanqing Lu
    arXiv, 2026
  • Position: Agentic Evolution is the Path to Evolving LLMs [Preprint, Code]
    Minhua Lin, Hanqing Lu, Zhan Shi, Bing He, Rui Mao, Zhiwei Zhang, Zongyu Wu, Xianfeng Tang, Hui Liu, Zhenwei Dai, Xiang Zhang, Suhang Wang, Benoit Dumoulin, Jian Pei
    arXiv, 2026
  • A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applications [Preprint, Project Page]
    Minhua Lin, Zongyu Wu, Zhichao Xu, Hui Liu, Xianfeng Tang, Qi He, Charu Aggarwal, Hui Liu, Xiang Zhang, Suhang Wang
    arXiv, 2025
  • LanP: Rethinking the Impact of Language Priors in Large Vision-Language Models. [Preprint]
    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, 2025

This page is modified based on Jon Barron's website.