ColPali: A Novel AI Model Architecture and Training Strategy based on Vision Language Models (VLMs) to Efficiently Index Documents Purely from Their Visual Features

ColPali is a groundbreaking AI model architecture that improves document retrieval by integrating visual and textual features. Developed by researchers from Illuin Technology, Equall.ai, CentraleSupélec, Paris-Saclay, and ETH Zürich, it leverages Vision Language Models (VLMs) to create high-quality contextualized embeddings Show more