Yuanpu Cao - RankMe

29 papers A* 8B 1Journal 16Unranked 4

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	ParaBlock: Communication-Computation Parallel Block Coordinate Federated Learning for Large Language Models. Trans. Mach. Learn. Res. Yujia Wang, Yuanpu Cao, Jinghui Chen
2026	J	`jnl`	PreFlect: From Retrospective to Prospective Reflection in Large Language Model Agents. CoRR Hanyu Wang, Yuanpu Cao, Lu Lin, Jinghui Chen
2025	A*	`conf`	AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion Models. ICML Yaopei Zeng, Yuanpu Cao, Bochuan Cao, Yurui Chang, Jinghui Chen, Lu Lin
2025	J	`jnl`	GuardDoor: Safeguarding Against Malicious Diffusion Editing via Protective Backdoors. CoRR Yaopei Zeng, Yuanpu Cao, Lu Lin
2025	J	`jnl`	ParaBlock: Communication-Computation Parallel Block Coordinate Federated Learning for Large Language Models. CoRR Yujia Wang, Yuanpu Cao, Jinghui Chen
2025	A*	`conf`	Phi: Preference Hijacking in Multi-modal Large Language Models at Inference Time. EMNLP Yifan Lan, Yuanpu Cao, Weitong Zhang, Lu Lin, Jinghui Chen
2025	J	`jnl`	Phi: Preference Hijacking in Multi-modal Large Language Models at Inference Time. CoRR Yifan Lan, Yuanpu Cao, Weitong Zhang, Lu Lin, Jinghui Chen
2025	—	`conf`	Shadow-Activated Backdoor Attacks on Multimodal Large Language Models. ACL (Findings) Ziyi Yin, Muchao Ye, Yuanpu Cao, Jiaqi Wang, Aofei Chang, Han Liu, Jinghui Chen, Ting Wang, Fenglong Ma
2025	J	`jnl`	Towards Robust Multimodal Large Language Models Against Jailbreak Attacks. CoRR Ziyi Yin, Yuanpu Cao, Han Liu, Ting Wang, Jinghui Chen, Fenhlong Ma
2025	A*	`conf`	TruthFlow: Truthful LLM Generation via Representation Flow Correction. ICML Hanyu Wang, Bochuan Cao, Yuanpu Cao, Jinghui Chen
2025	J	`jnl`	TruthFlow: Truthful LLM Generation via Representation Flow Correction. CoRR Hanyu Wang, Bochuan Cao, Yuanpu Cao, Jinghui Chen
2025	—	`conf`	WordGame: Efficient & Effective LLM Jailbreak via Simultaneous Obfuscation in Query and Response. NAACL (Findings) Tianrong Zhang, Bochuan Cao, Yuanpu Cao, Lu Lin, Prasenjit Mitra, Jinghui Chen
2025	A*	`conf`	You Can't Steal Nothing: Mitigating Prompt Leakages in LLMs via System Vectors. CCS Bochuan Cao, Changjiang Li, Yuanpu Cao, Yameng Ge, Ting Wang, Jinghui Chen
2025	J	`jnl`	You Can't Steal Nothing: Mitigating Prompt Leakages in LLMs via System Vectors. CoRR Bochuan Cao, Changjiang Li, Yuanpu Cao, Yameng Ge, Ting Wang, Jinghui Chen
2024	J	`jnl`	AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion models. CoRR Yaopei Zeng, Yuanpu Cao, Bochuan Cao, Yurui Chang, Jinghui Chen, Lu Lin
2024	J	`jnl`	Adversarially Robust Industrial Anomaly Detection Through Diffusion Model. CoRR Yuanpu Cao, Lu Lin, Jinghui Chen
2024	—	`conf`	Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM. ACL (1) Bochuan Cao, Yuanpu Cao, Lu Lin, Jinghui Chen
2024	A*	`conf`	Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization. NeurIPS Yuanpu Cao, Tianrong Zhang, Bochuan Cao, Ziyi Yin, Lu Lin, Fenglong Ma, Jinghui Chen
2024	J	`jnl`	Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization. CoRR Yuanpu Cao, Tianrong Zhang, Bochuan Cao, Ziyi Yin, Lu Lin, Fenglong Ma, Jinghui Chen
2024	—	`conf`	Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections. NAACL-HLT Yuanpu Cao, Bochuan Cao, Jinghui Chen
2024	A*	`conf`	Tackling the Data Heterogeneity in Asynchronous Federated Learning with Cached Update Calibration. ICLR Yujia Wang, Yuanpu Cao, Jingcheng Wu, Ruoyu Chen, Jinghui Chen
2024	J	`jnl`	WordGame: Efficient & Effective LLM Jailbreak via Simultaneous Obfuscation in Query and Response. CoRR Tianrong Zhang, Bochuan Cao, Yuanpu Cao, Lu Lin, Prasenjit Mitra, Jinghui Chen
2023	J	`jnl`	Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM. CoRR Bochuan Cao, Yuanpu Cao, Lu Lin, Jinghui Chen
2023	J	`jnl`	Federated Learning with Projected Trajectory Regularization. CoRR Tiejin Chen, Yuanpu Cao, Yujia Wang, Cho-Jui Hsieh, Jinghui Chen
2023	J	`jnl`	Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections. CoRR Yuanpu Cao, Bochuan Cao, Jinghui Chen
2021	A*	`conf`	CTF: Anomaly Detection in High-Dimensional Time Series with Coarse-to-Fine Model Transfer. INFOCOM Ming Sun, Ya Su, Shenglin Zhang, Yuanpu Cao, Yuqing Liu, Dan Pei, Wenfei Wu, Yongsu Zhang, Xiaozhou Liu, Junliang Tang
2020	A*	`conf`	RLCard: A Platform for Reinforcement Learning in Card Games. IJCAI Daochen Zha, Kwei-Herng Lai, Songyi Huang, Yuanpu Cao, Keerthana Reddy, Juan Vargas, Alex Nguyen, Ruzhe Wei, Junyu Guo, Xia Hu
2019	B	`conf`	CoFlux: robustly correlating KPIs by fluctuations for service troubleshooting. IWQoS Ya Su, Youjian Zhao, Wentao Xia, Rong Liu, Jiahao Bu, Jing Zhu, Yuanpu Cao, Haibin Li, Chenhao Niu, Yiyin Zhang, Zhaogang Wang, Dan Pei
2019	J	`jnl`	RLCard: A Toolkit for Reinforcement Learning in Card Games. CoRR Daochen Zha, Kwei-Herng Lai, Yuanpu Cao, Songyi Huang, Ruzhe Wei, Junyu Guo, Xia Hu