Yaqi Xie

multimodal learning (3) vision-language model (3) multi-agent system (2) zero-shot learning (1) few-shot learning (1) sequential decision-making (1) benchmark evaluation (1) prototype learning (1) logical reasoning (1) graph embedding (1) depth estimation (1) test-time adaptation (1) multi-modal learning (1) visual reasoning (1) scene graph generation (1) domain generalization (1) hierarchical reasoning (1) first-order logic (1) robust learning (1) semantic segmentation (1)