2 papers
cs.CV2026
Mind the Way You Select Negative Texts: Pursuing the Distance Consistency in OOD Detection with VLMs
Zhikang Xu, Qianqian Xu, Zitai Wang +4
Out-of-distribution (OOD) detection seeks to identify samples from unknown classes, a critical capability for deploying machine learning models in open-world scenarios. Recent rese…
cs.CL2026
TAO-Attack: Toward Advanced Optimization-Based Jailbreak Attacks for Large Language Models
Zhi Xu, Jiaqi Li, Xiaotong Zhang +2
Large language models (LLMs) have achieved remarkable success across diverse applications but remain vulnerable to jailbreak attacks, where attackers craft prompts that bypass safe…