Robuta

https://arxiv.org/html/2407.13311v1 General Vision Encoder Features as Guidance in Medical Image Registration vision encoder medical image general features guidance https://openreview.net/forum?id=YIxKeHQZpi UNIT: Unifying Image and Text Recognition in One Vision Encoder | OpenReview Currently, vision encoder models like Vision Transformers (ViTs) typically excel at image recognition tasks but cannot simultaneously support text recognition... text recognition one vision unit image https://research.google/pubs/mammut-a-simple-vision-encoder-text-decoder-architecture-for-multimodal-tasks/ MaMMUT: A Simple Vision-Encoder Text-Decoder Architecture for MultiModal Tasks simple vision mammut encoder