Zhi Zhong

text-to-video diffusion (2) diffusion model (2) multimodal learning (1) cross-modal learning (1) cross-modal alignment (1) vision-language model (1) text-to-video generation (1) latent optimization (1) inference-time alignment (1) multimodal model (1) language encoder (1) sentence embedding (1) audio-language model (1) vision language (1) music-to-video generation (1) description generation (1) cross-modal model (1) forward gradient descent (1) guided generation (1) music description (1)