Xin Yi

16 papers A* 1Journal 13Unranked 2

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	AGMark: Attention-Guided Dynamic Watermarking for Large Vision-Language Models. CoRR Yue Li, Xin Yi, Dongsheng Shi, Yongyi Cui, Gerard de Melo, Linlin Wang
2026	J	`jnl`	Latent-space adversarial training with post-aware calibration for defending large language models against jailbreak attacks. Expert Syst. Appl. Xin Yi, Yue Li, Dongsheng Shi, Linlin Wang, Xiaoling Wang, Liang He
2025	J	`jnl`	Fine-grained detoxification framework via instance-level prefixes for large language models. Neurocomputing Xin Yi, Linlin Wang, Xiaoling Wang, Liang He
2025	J	`jnl`	From Evaluation to Defense: Constructing Persistent Edit-Based Fingerprints for Large Language Models. CoRR Yue Li, Xin Yi, Dongsheng Shi, Yongyi Cui, Gerard de Melo, Xiaoling Wang, Linlin Wang
2025	—	`conf`	Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language Models. ACL (Findings) Yue Li, Xin Yi, Dongsheng Shi, Gerard de Melo, Xiaoling Wang, Linlin Wang
2025	J	`jnl`	Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language Models. CoRR Yue Li, Xin Yi, Dongsheng Shi, Gerard de Melo, Xiaoling Wang, Linlin Wang
2025	J	`jnl`	Latent-space adversarial training with post-aware calibration for defending large language models against jailbreak attacks. CoRR Xin Yi, Yue Li, Linlin Wang, Xiaoling Wang, Liang He
2025	A*	`conf`	NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning. AAAI Xin Yi, Shunfan Zheng, Linlin Wang, Gerard de Melo, Xiaoling Wang, Liang He
2025	J	`jnl`	Unified Attacks to Large Language Model Watermarks: Spoofing and Scrubbing in Unauthorized Knowledge Distillation. CoRR Xin Yi, Shunfan Zheng, Linlin Wang, Xiaoling Wang, Liang He
2025	J	`jnl`	Unified attacks to large language model watermarks: Spoofing and scrubbing in unauthorized knowledge distillation. Knowl. Based Syst. Xin Yi, Yue Li, Shunfan Zheng, Linlin Wang, Xiaoling Wang, Liang He
2025	J	`jnl`	Verbalization diversification for relation extraction with long-tailed entity augmentation. Neurocomputing Yiping Liang, Tianbao Jiang, Xin Yi, Yan Cai, Linlin Wang, Xiaoling Wang, Liang He
2024	J	`jnl`	A safety realignment framework via subspace-oriented model fusion for large language models. CoRR Xin Yi, Shunfan Zheng, Linlin Wang, Xiaoling Wang, Liang He
2024	J	`jnl`	A safety realignment framework via subspace-oriented model fusion for large language models. Knowl. Based Syst. Xin Yi, Shunfan Zheng, Linlin Wang, Xiaoling Wang, Liang He
2024	J	`jnl`	Fine-Grained Detoxification via Instance-Level Prefixes for Large Language Models. CoRR Xin Yi, Linlin Wang, Xiaoling Wang, Liang He
2024	J	`jnl`	NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning. CoRR Xin Yi, Shunfan Zheng, Linlin Wang, Gerard de Melo, Xiaoling Wang, Liang He
2024	—	`conf`	Scenarios-aware Commonsense Correcton via Instance-level Knowledge Injection. DASFAA (5) Xin Yi, Linlin Wang, Xiaoling Wang, Liang He