SteerViT is a framework that equips any ViT with the ability to steer both its global and local visual representations with natural language.

SteerViT is a framework that equips any ViT with the ability to steer both its global and local visual representations with natural language.

This is a repository that implements the Dense NN Retrieval Evaluation used for evaluating the In-Context Learning Capabilities of Vision Encoders.

Awesome Vision-Language Compositionality, a comprehensive curation of research papers in literature.

An open-source AirPlay mirroring server for the Raspberry Pi. Supports iOS 9 and up.