Zhiyang Xu

large language model (4) multimodal learning (3) instruction tuning (3) vision-language model (2) benchmark evaluation (2) question answering (2) video understanding (2) image generation (1) semi-supervised learning (1) semantic segmentation (1) knowledge distillation (1) in-context learning (1) information extraction (1) natural language generation (1) self-supervised learning (1) information retrieval (1) structured prediction (1) text generation (1) named entity recognition (1) causal reasoning (1)