VisionZip: Longer is Better but Not Necessary in Vision Language Models Paper • 2412.04467 • Published 8 days ago • 96
SNOOPI: Supercharged One-step Diffusion Distillation with Proper Guidance Paper • 2412.02687 • Published 10 days ago • 106
TAPTRv3: Spatial and Temporal Context Foster Robust Tracking of Any Point in Long Video Paper • 2411.18671 • Published 16 days ago • 19