Diffusion Models

DriveFlow: Rectified Flow Adaptation for Robust 3D Object Detection in Autonomous Driving AAAI 2026 DRM: Diffusion-based Reward Model With Step-wise Guidance CVPR 2026 DTG-Restore: Training-Free Diffusion Refinement for Generative Video Super-Resolution CVPR 2026 Dual Ascent Diffusion for Inverse Problems CVPR 2026 Dual-Seed Evolutionary Algorithm for Noise Optimization in Diffusion Models AAAI 2026 DuoCast: Duo-Probabilistic Diffusion for Precipitation Nowcasting AAAI 2026 DuoGen: Towards Autonomous Interleaved Multimodal Generation CVPR 2026 DuoMo: Dual Motion Diffusion for World-Space Human Reconstruction CVPR 2026 DUO-VSR: Dual-Stream Distillation for One-Step Video Super-Resolution CVPR 2026 DyaDiT: A Multi-Modal Diffusion Transformer for Socially Favorable Dyadic Gesture Generation CVPR 2026 Dynamic-eDiTor: Training-Free Text-Driven 4D Scene Editing with Multimodal Diffusion Transformer CVPR 2026 Dynamic Generation of Multi LLM Agents Communication Topologies with Graph Diffusion Models ACL 2026 Dynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models ACL 2026 DynFusion: Rethinking Condition Fusion for Adaptive Multi-Conditional Text-to-Image Generation CVPR 2026 DySy-Det: A Synergistic Framework with Dynamic Reconstruction-Path Consistency for AI-Generated Image Detection AAAI 2026 EarthCrafter: Scalable 3D Earth Generation via Dual-Sparse Latent Diffusion AAAI 2026 EasyOmnimatte: Taming Pretrained Inpainting Diffusion Models for End-to-End Video Layered Decompositio CVPR 2026 EasyText: Controllable Diffusion Transformer for Multilingual Text Rendering AAAI 2026 EchoMimicV3: 1.3B Parameters Are All You Need for Unified Multi-Modal and Multi-Task Human Animation AAAI 2026 EchoVDiff: Cardiac-Cycle Echocardiography Video Generation from Arbitrary Single Frame CVPR 2026 EcoDiffusion: Uncertainty-Aware Emulation of Ecosystem Processes with Conditional Diffusion for Long Sequences with Single-Step Initialization AAAI 2026 Edge-Aware Image Manipulation via Diffusion Models with a Novel Structure-Preservation Loss WACV 2026 Edit2Perceive: Image Editing Diffusion Models Are Strong Dense Perceivers CVPR 2026 EffectMaker: Unifying Reasoning and Generation for Customized Visual Effect Creation CVPR 2026 Efficient and Training-Free Single-Image Diffusion Models CVPR 2026