2 papers
cs.AI2026
Silencing the Guardrails: Inference-Time Jailbreaking via Dynamic Contextual Representation Ablation
Wenpeng Xing, Moran Fang, Guangtai Wang +2
While Large Language Models (LLMs) have achieved remarkable performance, they remain vulnerable to jailbreak attacks that circumvent safety constraints. Existing strategies, rangin…
cs.LG2025
Exploiting the Potential Supervision Information of Clean Samples in Partial Label Learning
Guangtai Wang, Chi-Man Vong, Jintao Huang
Diminishing the impact of false-positive labels is critical for conducting disambiguation in partial label learning. However, the existing disambiguation strategies mainly focus on…