Diffusion Models

Reinforcement Learning-based Adaptive Control of Classifier-Free Guidance and Timestep Embeddings in Diffusion Models WACV 2026 Reinforcement Learning for Diffusion LLMs via Energy-Based Gibbs Alignment ACL 2026 Rejection Mixing: Fast Semantic Propagation of Mask Tokens for Efficient DLLM Inference CVPR 2026 RelaCtrl: Relevance-Guided Efficient Control for Diffusion Transformers AAAI 2026 Relightful Video Portrait Harmonization CVPR 2026 RemEdit: Efficient Diffusion Editing with Riemannian Geometry WACV 2026 Remote Sensing Image Super-Resolution for Imbalanced Textures: A Texture-Aware Diffusion Framework CVPR 2026 RenderFlow: Single-Step Neural Rendering via Flow Matching CVPR 2026 Repurposing 3D Generative Model for Autoregressive Layout Generation CVPR 2026 ResCa: Residual Caching for Diffusion Transformers Acceleration CVPR 2026 ResDiT: Evoking the Intrinsic Resolution Scalability in Diffusion Transformers CVPR 2026 Residual Diffusion Bridge Model for Image Restoration CVPR 2026 ResoDiff-44k: High-Fidelity Cross-Lingual Speech and Singing Synthesis via Discrete Diffusion ACL 2026 Resolving Endpoint Underfitting in Diffusion Bridges via Noise Alignment CVPR 2026 Restora-Flow: Mask-Guided Image Restoration with Flow Matching WACV 2026 Rethinking Diffusion Model-Based Video Super-Resolution: Leveraging Dense Guidance from Aligned Features CVPR 2026 Rethinking Flow and Diffusion Bridge Models for Speech Enhancement AAAI 2026 Rethinking Real Image Editing: Unleashing Diverse Editing Operators via Multi-Objective Optimization WACV 2026 Rethinking Target Label Conditioning in Adversarial Attacks: A 2D Tensor-Guided Generative Approach AAAI 2026 Rethinking Visual Rearrangement from A Diffusion Perspective CVPR 2026 Retrievals Can Be Detrimental: Unveiling the Backdoor Vulnerability of Retrieval-Augmented Diffusion Models ACL 2026 Revealing the Invisible: Latent Structure Modeling for Semantically Consistent Cloud Removal AAAI 2026 Reverse Personalization WACV 2026 REVIVE 3D: Refinement via Encoded Voluminous Inflated prior for Volume Enhancement CVPR 2026 Reviving ConvNeXt for Efficient Convolutional Diffusion Models CVPR 2026