Ministral 3 Collection A collection of edge models, with Base, Instruct and Reasoning variants, in 3 different sizes: 3B, 8B and 14B. All with vision capabilities. • 9 items • Updated 23 days ago • 133
CutS3D: Cutting Semantics in 3D for 2D Unsupervised Instance Segmentation Paper • 2411.16319 • Published Nov 25, 2024 • 1
Your other Left! Vision-Language Models Fail to Identify Relative Positions in Medical Images Paper • 2508.00549 • Published Aug 1 • 1
Your other Left! Vision-Language Models Fail to Identify Relative Positions in Medical Images Paper • 2508.00549 • Published Aug 1
Less is More: Selective Reduction of CT Data for Self-Supervised Pre-Training of Deep Learning Models with Contrastive Learning Improves Downstream Classification Performance Paper • 2410.14524 • Published Oct 18, 2024
Self-Supervised Pre-Training with Contrastive and Masked Autoencoder Methods for Dealing with Small Datasets in Deep Learning for Medical Imaging Paper • 2308.06534 • Published Aug 12, 2023