Jingying Gao

LoRA: A Logical Reasoning Augmented Dataset for Visual Question Answering

The capacity to reason logically is a hallmark of human cognition. Humans excel at integrating multimodal information for locigal reasoning, as exemplified by the Visual Question Answering (VQA) task, which is a challenging multimodal task. VQA tasks and large vision-and-language models aim to tackl…