Shuyu Li

transformer architecture (1) benchmark evaluation (1) cross-modal learning (1) generative model (1) diffusion model (1) multimodal large language model (1) song generation (1) music generation (1) hierarchical attention (1) chinese language (1) large language model (1) text-to-music generation (1) conditional diffusion model (1) music understanding (1) human-machine alignment (1) deformable image registration (1) video-to-music generation (1) large deformation (1) multi-level framework (1) masked self-attention (1)