Bohan Li

diffusion model (3) few-shot learning (2) speech synthesis (2) evidence lower bound (2) self-supervised learning (2) 3d vision (2) language model (2) variational autoencoder (2) scene generation (2) semantic scene completion (2) posterior collapse (2) representation learning (2) latent representation (2) prompt engineering (2) data augmentation (1) machine translation (1) transfer learning (1) attention mechanism (1) image generation (1) video generation (1)