Steerable Visual Representations (SteerViT) Collection SteerViT is a framework that allows you to guide a pretrained vision model's focus and features using natural language • 5 items • Updated about 12 hours ago
I Have a Stream: Making Self-Supervised Learning Work on Continuous Video Paper • 2609.40333 • Published 6 days ago • 14
Self-Supervised Learning of Structured Dynamics from Videos Paper • 2607.21576 • Published Jul 23 • 21