Chih-Kai Yang

Encoder-Side Neuron Identification and Amplification for Acoustic Perception in Large Audio-Language Models

IAAN, Identifying and Amplifying Acoustic Neurons, a training-free and label-free method that scores each feed-forward neuron in the audio encoder by contrasting its activation on the real waveform with that on a noise reference lacking the real audio's acoustic information, improves average accuracy and improves a model already explicitly fine-tuned to prioritize acoustic evidence.