Audio Jailbreaks in Large Audio-Language Models: Taxonomy, Attack-Defense Analysis, and Cost-Aware Evaluation
Sound · 2026-05 · arXiv:2605.30031
Bo-Han Feng, Yu-Hsuan Li Liang, Chien-Feng Liu, You-Hsuan Chang +1
HoliTok:A Coutinuous Holistic Tokenization with Robust Dual Capabilities of Speech Generation and Understanding
Sound · 2026-05 · arXiv:2605.29948
Bohan Li, Shi Lian, Hankun Wang, Yiwei Guo +5
COMET: Concept Space Dissection of the Modality Gap in Audio-Text Multimodal Contrastive Embeddings
Sound · 2026-05 · arXiv:2605.29628
Yonggang Zhu, Liting Gao, Aidong Men, Wenwu Wang