Xinting Hu

in-context learning (2) diffusion model (2) few-shot learning (2) semantic segmentation (2) class-incremental learning (2) large multimodal model (2) semi-supervised learning (1) self-supervised learning (1) 3d reconstruction (1) visual question answering (1) image generation (1) attention mechanism (1) personalized generation (1) knowledge distillation (1) catastrophic forgetting (1) multi-modal learning (1) incremental learning (1) multimodal learning (1) video understanding (1) vision transformer (1)