feng han

sequence generation (1) contrastive learning (1) action recognition (1) image generation (1) curriculum learning (1) object detection (1) preference learning (1) video captioning (1) self-supervised learning (1) knowledge distillation (1) named entity recognition (1) multimodal learning (1) video understanding (1) image editing (1) person detection (1) diffusion model (1) text-to-image model (1) concept erasure (1) skip connection (1) student model (1)