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
Zero4D: Training-Free 4D Video Generation From Single Video Using Off-the-Shelf Video Diffusion Model Paper • 2503.22622 • Published Mar 28 • 18
PLADIS: Pushing the Limits of Attention in Diffusion Models at Inference Time by Leveraging Sparsity Paper • 2503.07677 • Published Mar 10 • 86
