A Vision Check-up for Language Models
This work addresses the problem of bridging language and vision understanding for AI researchers, though it is incremental as it builds on existing text modeling techniques.
The study investigated whether large language models (LLMs) can learn about the visual world by modeling relationships between strings, using code to represent images, and found that LLMs can generate and recognize visual concepts, with experiments showing potential for training vision models using LLMs.
What does learning to model relationships between strings teach large language models (LLMs) about the visual world? We systematically evaluate LLMs' abilities to generate and recognize an assortment of visual concepts of increasing complexity and then demonstrate how a preliminary visual representation learning system can be trained using models of text. As language models lack the ability to consume or output visual information as pixels, we use code to represent images in our study. Although LLM-generated images do not look like natural images, results on image generation and the ability of models to correct these generated images indicate that precise modeling of strings can teach language models about numerous aspects of the visual world. Furthermore, experiments on self-supervised visual representation learning, utilizing images generated with text models, highlight the potential to train vision models capable of making semantic assessments of natural images using just LLMs.