Gus Xia

music generation (4) self-supervised learning (2) music representation (2) music understanding (2) music information retrieval (2) parameter-efficient fine-tuning (2) large language model (2) cross-modal retrieval (1) multimodal learning (1) zero-shot learning (1) autoregressive model (1) pre-trained model (1) diffusion model (1) latent space (1) encoder-decoder architecture (1) audio processing (1) retrieval-augmented generation (1) continual pre-training (1) vector quantization (1) vision-language model (1)