Codes and Models for VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset

Recognize Any Regions

Self-Supervised Visual-Tactile Representation Learning via Multimodal Contrastive Training

Freeze the Backbone: A Parameter-Efficient Contrastive Approach to Robust Medical Vision-Language Pre-training. Thesis of MSc AI degree at Imperial College London.

Mini-batch selective sampling for knowledge adaption of VLMs for mammography.