Fast Autoregressive Video Diffusion and World Models with Temporal Cache Compression and Sparse Attention Paper • 2602.01801 • Published 6 days ago • 27
OmnimatteZero: Training-free Real-time Omnimatte with Pre-trained Video Diffusion Models Paper • 2503.18033 • Published Mar 23, 2025 • 28
Single Image Iterative Subject-driven Generation and Editing Paper • 2503.16025 • Published Mar 20, 2025 • 14
Bringing Objects to Life: 4D generation from 3D objects Paper • 2412.20422 • Published Dec 29, 2024 • 41