Chengwei Wei

Digital Humanities (1)

large language model (4) multimodal learning (3) instruction following (2) evaluation benchmark (2) in-context learning (1) speech processing (1) text generation (1) code generation (1) automatic speech recognition (1) instruction tuning (1) model alignment (1) low-resource language (1) benchmark dataset (1) vision language model (1) vision-language model (1) robustness evaluation (1) data synthesis (1) optical character recognition (1) audio modality (1) cultural reasoning (1)