Jingqun Tang

Reinforcement Learning (1)

multimodal learning (3) multimodal large language model (3) visual question answering (2) document understanding (2) scene text recognition (2) image captioning (2) benchmark evaluation (2) domain adaptation (1) image generation (1) image segmentation (1) in-context learning (1) few-shot learning (1) vision-language alignment (1) object removal (1) modality alignment (1) scene text detection (1) image editing (1) visual recognition (1) parallel processing (1) object detection (1)