Wenxuan Song

representation learning (1) semantic segmentation (1) imitation learning (1) object detection (1) visual question answering (1) attention mechanism (1) multimodal learning (1) multi-modal learning (1) policy learning (1) efficient computing (1) visual attention (1) robot manipulation (1) multimodal large language model (1) hallucination mitigation (1) diffusion prior (1) text embedding (1) stable diffusion (1) one-step generation (1) diffusion transformer (1) vision-language-action model (1)