Zejiang Hou

model compression (2) adversarial robustness (1) unsupervised pretraining (1) model robustness (1) speech recognition (1) language identification (1) neural network optimization (1) noise robustness (1) adversarial attack (1) convolutional neural network (1) multimodal large language model (1) noisy label training (1) inference efficiency (1) dynamic computation (1) column subset selection (1) channel pruning (1) speech language model (1) multilingual speech recognition (1) convolution-free transformer (1) speech-language model (1)