Hexiang Hu

multimodal learning (7) visual question answering (6) transfer learning (4) object detection (3) imitation learning (3) few-shot learning (3) multi-modal learning (3) vision language model (2) instruction following (2) retrieval-augmented generation (2) instance segmentation (2) embedding learning (2) domain adaptation (2) diffusion model (2) image generation (2) reinforcement learning (2) in-context learning (2) image captioning (2) visual grounding (2) long-tailed distribution (2)