Diffusion Models

Scaling Diffusion Mamba with Bidirectional SSMs for Efficient 3D Shape Generation AAAI 2025 Scaling Down Text Encoders of Text-to-Image Diffusion Models CVPR 2025 Scaling Inference Time Compute for Diffusion Models CVPR 2025 Scaling In-the-Wild Training for Diffusion-based Illumination Harmonization and Editing by Imposing Consistent Light Transport ICLR 2025 Scaling Laws for Synthetic Speech for Model Training Interspeech 2025 Scaling Properties of Diffusion Models For Perceptual Tasks CVPR 2025 Scaling up Masked Diffusion Models on Text ICLR 2025 Scenario Dreamer: Vectorized Latent Diffusion for Generating Driving Simulation Environments CVPR 2025 Scene4U: Hierarchical Layered 3D Scene Reconstruction from Single Panoramic Image for Your Immerse Exploration CVPR 2025 Scene Coordinate Reconstruction Priors ICCV 2025 SceneCrafter: Controllable Multi-View Driving Scene Editing CVPR 2025 Scene Graph Guided Generation: Enable Accurate Relations Generation in Text-to-Image Models via Textural Rectification ICCV 2025 SceneMI: Motion In-betweening for Modeling Human-Scene Interaction ICCV 2025 Schedule On the Fly: Diffusion Time Prediction for Faster and Better Image Generation CVPR 2025 Science-T2I: Addressing Scientific Illusions in Image Synthesis CVPR 2025 Score as Action: Fine Tuning Diffusion Generative Models by Continuous-time Reinforcement Learning ICML 2025 Score-Based Diffusion Models in Function Space JMLR 2025 Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion Models ICLR 2025 ScoreFusion: Fusing Score-based Generative Models via Kullback–Leibler Barycenters AISTATS 2025 ScoreHOI: Physically Plausible Reconstruction of Human-Object Interaction via Score-Guided Diffusion ICCV 2025 Score matching for bridges without learning time-reversals AISTATS 2025 Score-of-Mixture Training: One-Step Generative Model Training Made Simple via Score Estimation of Mixture Distributions ICML 2025 SCott: Accelerating Diffusion Models with Stochastic Consistency Distillation AAAI 2025 ScreenMark: Watermarking Arbitrary Visual Content on Screen AAAI 2025 ScribbleLight: Single Image Indoor Relighting with Scribbles CVPR 2025