SAKE: Towards Editing Auditory Attribute Knowledge of Large Audio-Language Models Paper • 2510.16917 • Published Oct 19 • 19
Investigating Safety Vulnerabilities of Large Audio-Language Models Under Speaker Emotional Variations Paper • 2510.16893 • Published Oct 19 • 17
Pseudo2Real: Task Arithmetic for Pseudo-Label Correction in Automatic Speech Recognition Paper • 2510.08047 • Published Oct 9 • 7