Wenwen Zhuang

multimodal large language model (3) knowledge distillation (2) emotion recognition (2) multimodal learning (1) vision-language alignment (1) low-resource learning (1) cross-modal alignment (1) text-attributed graph (1) pretrained language model (1) progressive alignment (1) multimodal emotion recognition (1) graph neural network (1) diagram understanding (1) representation learning (1) topological pretraining (1) few-shot learning (1) mathematical reasoning (1)