Giorgos Tolias

MLLMs, without any training, can beat specialized models at image retrieval, especially when the target domain differs from the training data of those specialized models.

Achieve state-of-the-art open-vocabulary segmentation by distilling a sliding-window ViT into a single-pass architecture, enabling efficient high-resolution reasoning.

Just a handful of annotated examples can dramatically close the performance gap between zero-shot and fully supervised open-vocabulary segmentation.