MIDAS: Multimodal Interactive Digital-human Synthesis via Real-time Autoregressive Video Generation Paper • 2508.19320 • Published 11 days ago • 27
Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation Paper • 2508.07981 • Published 26 days ago • 58
S^2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models Paper • 2508.12880 • Published 19 days ago • 45
UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning Paper • 2505.14231 • Published May 20 • 53