What is the Visual Cognition Gap between Humans and Multimodal LLMs?
What is the Visual Cognition Gap between Humans and Multimodal LLMs?
Recently, Multimodal Large Language Models (MLLMs) have shown great promise in language-guided perceptual tasks such as recognition, segmentation, and object detection. However, their effectiveness in addressing visual cognition problems that require high-level reasoning is not well-established. One such challenge is abstract visual reasoning (AVR) -- the cognitive ability to discern …