Leveraging Large Language Models for Scalable Vector Graphics-Driven Image Understanding
This work explores a novel approach for extending LLMs to visual tasks, potentially opening new research avenues, but it appears incremental as it adapts existing LLM capabilities to a new data format without major methodological breakthroughs.
The paper tackled the problem of enabling large language models (LLMs) to understand images by converting them into Scalable Vector Graphics (SVG) representations, and found that LLMs performed decently on tasks like visual reasoning, image classification under distribution shift, and image generation.
Large language models (LLMs) have made significant advancements in natural language understanding. However, through that enormous semantic representation that the LLM has learnt, is it somehow possible for it to understand images as well? This work investigates this question. To enable the LLM to process images, we convert them into a representation given by Scalable Vector Graphics (SVG). To study what the LLM can do with this XML-based textual description of images, we test the LLM on three broad computer vision tasks: (i) visual reasoning and question answering, (ii) image classification under distribution shift, few-shot learning, and (iii) generating new images using visual prompting. Even though we do not naturally associate LLMs with any visual understanding capabilities, our results indicate that the LLM can often do a decent job in many of these tasks, potentially opening new avenues for research into LLMs' ability to understand image data. Our code, data, and models can be found here https://github.com/mu-cai/svg-llm.