Visual Cognition

Visual cognition research investigates how the brain processes and interprets visual information, aiming to understand and replicate this ability in artificial intelligence. Current research focuses on bridging the gap between human-level visual reasoning, particularly in areas like abstract reasoning and understanding complex interactions (e.g., human-object interactions), and the capabilities of large language models (LLMs) enhanced with visual processing. This involves developing new benchmarks and datasets to evaluate model performance and exploring methods to improve LLMs' ability to handle complex visual information, including strategies to mitigate cognitive biases. Advances in this field have implications for improving AI systems' ability to interpret visual data and could lead to advancements in areas such as medical image analysis and assistive technologies.