ForcingBooster: Adaptive Patch-wise Denoising for Fast Autoregressive Video Diffusion Paper • 2610.12625 • Published Oct 8 • 32
Repurposing 3D Generative Model for Autoregressive Layout Generation Paper • 2604.16299 • Published Apr 17 • 11
TriAttention: Efficient Long Reasoning with Trigonometric KV Compression Paper • 2604.04921 • Published Apr 6 • 112
Learning to Reason in 4D: Dynamic Spatial Understanding for Vision Language Models Paper • 2512.20557 • Published Dec 23, 2025 • 52
AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models Paper • 2506.19851 • Published Jun 24, 2025 • 60
AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models Paper • 2506.19851 • Published Jun 24, 2025 • 60