Universal Reasoner: A Single, Composable Plug-and-Play Reasoner for Frozen LLMs Paper • 2505.19075 • Published May 25 • 21
Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment Paper • 2505.18600 • Published May 24 • 48
PLADIS: Pushing the Limits of Attention in Diffusion Models at Inference Time by Leveraging Sparsity Paper • 2503.07677 • Published Mar 10 • 86
Reangle-A-Video: 4D Video Generation as Video-to-Video Translation Paper • 2503.09151 • Published Mar 12 • 32
Track4Gen: Teaching Video Diffusion Models to Track Points Improves Video Generation Paper • 2412.06016 • Published Dec 8, 2024 • 20
VideoGuide: Improving Video Diffusion Models without Training Through a Teacher's Guide Paper • 2410.04364 • Published Oct 6, 2024 • 29
