Diffusion Models

MagicPaint: Operate Anything for Image Inpainting with Diffusion Model AAAI 2026 MAISI-v2: Accelerated 3D High-Resolution Medical Image Synthesis with Rectified Flow and Region-specific Contrastive Loss AAAI 2026 MakeAnything: Harnessing Diffusion Transformers for Multi-Domain Procedural Sequence Generation CVPR 2026 Making Training-Free Diffusion Segmentors Scale with the Generative Power CVPR 2026 ManifoldGD: Training-Free Hierarchical Manifold Guidance for Diffusion-Based Dataset Distillation CVPR 2026 ManipDreamer3D: Synthesizing Plausible Robotic Manipulation Video with Occupancy-aware 3D Trajectory AAAI 2026 MapRoute:Precise-Concept Erasing Mappers via Semantic Routing CVPR 2026 Margin-Aware Preference Optimization for Aligning Diffusion Models Without Reference AAAI 2026 MaskDiME: Adaptive Masked Diffusion for Precise and Efficient Visual Counterfactual Explanations CVPR 2026 Masked Auto-Regressive Variational Acceleration: Fast Inference Makes Practical Reinforcement Learning CVPR 2026 Masked-Diffusion Autoencoders for 3D Medical Vision Representation Learning CVPR 2026 Masked Region Transformer for Layered Image Generation and Editing at Scale CVPR 2026 Mass Concept Erasure in Diffusion Models with Concept Hierarchy AAAI 2026 Match-and-Fuse: Consistent Generation from Unstructured Image Sets CVPR 2026 MatchMask: Mask-Centric Generative Data Augmentation for Label-Scarce Semantic Segmentation CVPR 2026 MatE: Material Extraction from Single-Image via Geometric Prior CVPR 2026 MatLat: Material Latent Space for PBR Texture Generation CVPR 2026 MatMart: Material Reconstruction of 3D Objects via Diffusion CVPR 2026 MatPedia: A Universal Generative Foundation for High-Fidelity Material Synthesis CVPR 2026 MatSpray: Fusing 2D Material World Knowledge on 3D Geometry CVPR 2026 MATT-Diff: Multimodal Active Target Tracking by Diffusion Policy L4DC 2026 MAUGen: A Unified Diffusion Approach for Multi-Identity Facial Expression and AU Label Generation AAAI 2026 MAViS: A Multi-Agent Framework for Long-Sequence Video Storytelling EACL 2026 MaxMark: High-Capacity Diffusion-Native Watermarking via Robust and Invertible Latent Embedding CVPR 2026 MBTI: Metric-Based Textual Inversion for Fine-Grained Image Generation WACV 2026