MT Forcing: Towards Stable and Consistent Multi-Turn Image Editing with Autoregressive Diffusion Paper • 2610.25404 • Published Oct 18 • 40
TideGS: Scalable Training of Over One Billion 3D Gaussian Splatting Primitives via Out-of-Core Optimization Paper • 2605.20150 • Published May 19 • 7
Relit-LiVE: Relight Video by Jointly Learning Environment Video Paper • 2605.06658 • Published May 7 • 17
UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors Paper • 2605.00658 • Published May 1 • 86