12 papers
Encoder-Side Neuron Identification and Amplification for Acoustic Perception in Large Audio-Language Models
Yu-Han Huang, Chih-Kai Yang, Ke-Han Lu +2
The paper proposes IAAN, a training‑free method that identifies and amplifies specific neurons inside the audio encoder of large audio‑language models to improve recognition of fin…
MUGEN: Evaluating and Improving Multi-audio Understanding of Large Audio-Language Models
Chih-Kai Yang, Yun-Shao Tsai, Yu-Kai Guo +7
While multi-audio understanding is critical for large audio-language models (LALMs), it remains underexplored. We introduce MUGEN, a comprehensive benchmark evaluating this capabil…
Escaping the Procrustean Bed: Groupwise Orthogonal Connectors for Audio-Language Models
Ho-Lam Chung, Ke-Han Lu, Yi-Cheng Lin +3
Audio-language models compress a speech encoder's output through a Querying Transformer (Q-Former) connector before feeding it to a large language model. We identify two failures i…
Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey
Chih-Kai Yang, Neo S. Ho, Hung-yi Lee
With advancements in large audio-language models (LALMs), which enhance large language models (LLMs) with auditory capabilities, these models are expected to demonstrate universal…
How Auditory Knowledge in LLM Backbones Shapes Audio Language Models: A Holistic Evaluation
Ke-Han Lu, Szu-Wei Fu, Chao-Han Huck Yang +13
Large language models (LLMs) have been widely used as knowledge backbones of Large Audio Language Models (LALMs), yet how much auditory knowledge they encode through text-only pre-…
SAKE: Towards Editing Auditory Attribute Knowledge of Large Audio-Language Models
Chih-Kai Yang, Yen-Ting Piao, Tzu-Wen Hsu +8
Knowledge editing enables targeted updates without retraining, but prior work focuses on textual or visual facts, leaving abstract auditory perceptual knowledge underexplored. We i…