Yilei Li

zero-shot learning (1) few-shot learning (1) action recognition (1) variational inference (1) multimodal learning (1) 3d vision (1) image synthesis (1) egocentric vision (1) entropy maximization (1) diffusion model (1) text-to-3d generation (1) classifier-free guidance (1) missing modality (1) contrastive alignment (1) view synthesis (1) mode collapse (1) egocentric action recognition (1) score distillation (1) texture generation (1) modality dropout (1)