Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Paper • 2607.07675 • Published 3 days ago • 42
Running on Zero Agents Featured 115 SAM3 Video Segmentation 🐠 115 Track and label objects in videos using text prompts or clicks
SpecBundle Collection A collection of production-grade draft models for speculative decoding • 18 items • Updated Apr 15 • 19
facebook/dinov3-vitl16-pretrain-lvd1689m Image Feature Extraction • 0.3B • Updated Aug 19, 2025 • 590k • 393