Diffusion Models

PropFly: Learning to Propagate via On-the-Fly Supervision from Pre-trained Video Diffusion Models CVPR 2026 ProPhy: Progressive Physical Alignment for Dynamic World Simulation CVPR 2026 Prototype-Guided Concept Erasure in Diffusion Models CVPR 2026 Proxy Zero-Shot Hashing with Multimodal Fusion via Stable Diffusion AAAI 2026 PSDiffusion: Harmonized Multi-Layer Image Generation via Layout and Appearance Alignment WACV 2026 PS-SR: Pseudo-Single-Step Video Super-Resolution via Speculative Diffusion CVPR 2026 PureCC: Pure Learning for Text-to-Image Concept Customization CVPR 2026 PyramidalWan: On Making Pretrained Video Model Pyramidal for Efficient Inference CVPR 2026 QRShield: Exploiting Vulnerabilities of Latent Diffusion Models for Preventing AI Art Plagiarism AAAI 2026 Quality-Aware Language-Conditioned Local Auto-Regressive Anomaly Synthesis and Detection AAAI 2026 QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Models CVPR 2026 Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition CVPR 2026 RAIN: Redundancy-Aware Latent Injection for Quality-Preserving Image Watermarking AAAI 2026 RAISE: Requirement-Adaptive Evolutionary Refinement for Training-Free Text-to-Image Alignment CVPR 2026 RaLD: Generating High-Resolution 3D Radar Point Clouds with Latent Diffusion AAAI 2026 RAPID: Reusing Attention Sparsity with Inter-step Adaptation for Efficient Video Diffusion CVPR 2026 RatioMorph: Controllable Diffusion Framework for Automotive Viewpoint and Proportion Manipulation in Vehicle Design AAAI 2026 RAVEN: Erasing Invisible Watermarks via Novel View Synthesis CVPR 2026 RawMetaDiff: Unlocking Extreme Darkness from Dual-Exposure RAW with Meta-Guided Diffusion CVPR 2026 RCP-LO: A Relative Coordinate Prediction Framework for Generalizable Deep LiDAR Odometry AAAI 2026 RDF-MIG: A Robust Diffusion Framework for Masked Image Generation to Augment Semantic Segmentation and Change Detection CVPR 2026 REACH: Explicit Recovery Behavior for Diffusion Policies CVPR 2026 READ: Real-time and Efficient Asynchronous Diffusion for Audio-driven Talking Head Generation AAAI 2026 ReAlign: Text-to-Motion Generation via Step-Aware Reward-Guided Alignment AAAI 2026 Realism Control One-step Diffusion for Real-world Image Super Resolution AAAI 2026