Jingwen Li

combinatorial optimization (1) transformer architecture (1) semantic segmentation (1) vision transformer (1) domain adaptation (1) medical imaging (1) attention mechanism (1) multimodal learning (1) multi-modal learning (1) medical image segmentation (1) weakly-supervised learning (1) 3d object detection (1) low-resource language (1) traveling salesman problem (1) benchmark dataset (1) vision language model (1) vision-language model (1) proximal policy optimization (1) vision foundation model (1) image understanding (1)