Zihan Guan

30 papers A* 7A 3Journal 17Unranked 3
YearRankTypeTitle / Venue / Authors
2026 J jnl
Agentic Framework for Epidemiological Modeling.
CoRR
Rituparna Datta, Zihan Guan, Baltazar Espinoza, Yiqi Su, Priya Pitre, Srinivasan Venkatramanan, Naren Ramakrishnan, Anil Vullikanti
2026 J jnl
Alignment-Weighted DPO: A principled reasoning approach to improve safety alignment.
CoRR
Mengxuan Hu, Vivek V. Datla, Anoop Kumar, Zihan Guan, Sheng Li, Alfy Samuel, Daben Liu
2026 J jnl
Enhanced Diagnostic Performance via Large-Resolution Inference Optimization for Pathology Foundation Models.
CoRR
Mengxuan Hu, Zihan Guan, John Kang, Sheng Li, Zhongliang Zhou
2026 J jnl
NIMMGen: Learning Neural-Integrated Mechanistic Digital Twins with LLMs.
CoRR
Zihan Guan, Rituparna Datta, Mengxuan Hu, Shunshun Liu, Aiying Zhang, Prasanna Balachandran, Sheng Li, Anil Vullikanti
2025 J jnl
A Framework for Multi-source Privacy Preserving Epidemic Analysis.
CoRR
Zihan Guan, Zhiyuan Zhao, Fengwei Tian, Dung Nguyen, Payel Bhattacharjee, Ravi Tandon, B. Aditya Prakash, Anil Vullikanti
2025 A conf
Backdoor in Seconds: Unlocking Vulnerabilities in Large Pre-trained Models via Model Editing.
CIKM
Dongliang Guo, Mengxuan Hu, Zihan Guan, Junfeng Guo, Thomas Hartvigsen, Sheng Li
2025 A* conf
BalancEdit: Dynamically Balancing the Generality-Locality Trade-off in Multi-modal Model Editing.
ICML
Dongliang Guo, Mengxuan Hu, Zihan Guan, Thomas Hartvigsen, Sheng Li
2025 J jnl
BalancEdit: Dynamically Balancing the Generality-Locality Trade-off in Multi-modal Model Editing.
CoRR
Dongliang Guo, Mengxuan Hu, Zihan Guan, Thomas Hartvigsen, Sheng Li
2025 A* conf
Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety.
ICML
Zihan Guan, Mengxuan Hu, Ronghang Zhu, Sheng Li, Anil Vullikanti
2025 J jnl
Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety.
CoRR
Zihan Guan, Mengxuan Hu, Ronghang Zhu, Sheng Li, Anil Vullikanti
2025 J jnl
Improving Hospital Risk Prediction with Knowledge-Augmented Multimodal EHR Modeling.
CoRR
Rituparna Datta, Jiaming Cui, Zihan Guan, Vishal G. Reddy, Joshua C. Eby, Gregory Madden, Rupesh Silwal, Anil Vullikanti
2025 A* conf
Mind Control through Causal Inference: Predicting Clean Images from Poisoned Data.
ICLR
Mengxuan Hu, Zihan Guan, Yi Zeng, Junfeng Guo, Zhongliang Zhou, Jielu Zhang, Ruoxi Jia, Anil Kumar S. Vullikanti, Sheng Li
2025 — conf
No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users.
EMNLP (Findings)
Mengxuan Hu, Hongyi Wu, Ronghang Zhu, Zihan Guan, Dongliang Guo, Daiqing Qi, Sheng Li
2025 — conf
PharmaData-Agent: A Specialized Agent for Pharmaceutical Data Analysis.
ICDM (Workshops)
Zihan Guan, Hanyin Wang, Zhongliang Zhou, Qiaohui Zhou, Peining Tao, Junshui Ma
2025 A* conf
UFID: A Unified Framework for Black-box Input-level Backdoor Detection on Diffusion Models.
AAAI
Zihan Guan, Mengxuan Hu, Sheng Li, Anil Kumar S. Vullikanti
2024 J jnl
BBCaL: Black-box Backdoor Detection under the Causality Lens.
Trans. Mach. Learn. Res.
Mengxuan Hu, Zihan Guan, Junfeng Guo, Zhongliang Zhou, Jielu Zhang, Sheng Li
2024 J jnl
Backdoor in Seconds: Unlocking Vulnerabilities in Large Pre-trained Models via Model Editing.
CoRR
Dongliang Guo, Mengxuan Hu, Zihan Guan, Junfeng Guo, Thomas Hartvigsen, Sheng Li
2024 A* conf
BadSAM: Exploring Security Vulnerabilities of SAM via Backdoor Attacks (Student Abstract).
AAAI
Zihan Guan, Mengxuan Hu, Zhongliang Zhou, Jielu Zhang, Sheng Li, Ninghao Liu
2024 A* conf
Img2Loc: Revisiting Image Geolocalization using Multi-modality Foundation Models and Image-based Retrieval-Augmented Generation.
SIGIR
Zhongliang Zhou, Jielu Zhang, Zihan Guan, Mengxuan Hu, Ni Lao, Lan Mu, Sheng Li, Gengchen Mai
2024 J jnl
Img2Loc: Revisiting Image Geolocalization using Multi-modality Foundation Models and Image-based Retrieval-Augmented Generation.
CoRR
Zhongliang Zhou, Jielu Zhang, Zihan Guan, Mengxuan Hu, Ni Lao, Lan Mu, Sheng Li, Gengchen Mai
2024 J jnl
No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users.
CoRR
Mengxuan Hu, Hongyi Wu, Zihan Guan, Ronghang Zhu, Dongliang Guo, Daiqing Qi, Sheng Li
2024 — conf
Text2Seg: Zero-shot Remote Sensing Image Semantic Segmentation via Text-Guided Visual Foundation Models.
GeoAI@SIGSPATIAL
Jielu Zhang, Zhongliang Zhou, Gengchen Mai, Mengxuan Hu, Zihan Guan, Sheng Li, Lan Mu
2024 J jnl
UFID: A Unified Framework for Input-level Backdoor Detection on Diffusion Models.
CoRR
Zihan Guan, Mengxuan Hu, Sheng Li, Anil Vullikanti
2023 A conf
Attacking Neural Networks with Neural Networks: Towards Deep Synchronization for Backdoor Attacks.
CIKM
Zihan Guan, Lichao Sun, Mengnan Du, Ninghao Liu
2023 J jnl
BadSAM: Exploring Security Vulnerabilities of SAM via Backdoor Attacks.
CoRR
Zihan Guan, Mengxuan Hu, Zhongliang Zhou, Jielu Zhang, Sheng Li, Ninghao Liu
2023 A* conf
Black-box Backdoor Defense via Zero-shot Image Purification.
NeurIPS
Yucheng Shi, Mengnan Du, Xuansheng Wu, Zihan Guan, Jin Sun, Ninghao Liu
2023 J jnl
Black-box Backdoor Defense via Zero-shot Image Purification.
CoRR
Yucheng Shi, Mengnan Du, Xuansheng Wu, Zihan Guan, Ninghao Liu
2023 J jnl
CohortGPT: An Enhanced GPT for Participant Recruitment in Clinical Study.
CoRR
Zihan Guan, Zihao Wu, Zhengliang Liu, Dufan Wu, Hui Ren, Quanzheng Li, Xiang Li, Ninghao Liu
2023 A conf
XGBD: Explanation-Guided Graph Backdoor Detection.
ECAI
Zihan Guan, Mengnan Du, Ninghao Liu
2023 J jnl
XGBD: Explanation-Guided Graph Backdoor Detection.
CoRR
Zihan Guan, Mengnan Du, Ninghao Liu