Diffusion Models

CNS-Bench: Benchmarking Image Classifier Robustness Under Continuous Nuisance Shifts ICCV 2025 Co^3Gesture: Towards Coherent Concurrent Co-speech 3D Gesture Generation with Interactive Diffusion ICLR 2025 CObL: Toward Zero-Shot Ordinal Layering without User Prompting ICCV 2025 CoCoCo: Improving Text-Guided Video Inpainting for Better Consistency, Controllability and Compatibility AAAI 2025 CODE: Confident Ordinary Differential Editing AAAI 2025 CoDiCast: Conditional Diffusion Model for Global Weather Forecasting with Uncertainty Quantification IJCAI 2025 CognitionCapturer: Decoding Visual Stimuli from Human EEG Signal with Multimodal Information AAAI 2025 CoInD: Enabling Logical Compositions in Diffusion Models ICLR 2025 Color Alignment in Diffusion CVPR 2025 ColorizeDiffusion: Improving Reference-Based Sketch Colorization with Latent Diffusion Model WACV 2025 Comparing noisy neural population dynamics using optimal transport distances ICLR 2025 Compass Control: Multi Object Orientation Control for Text-to-Image Generation CVPR 2025 CoMPaSS: Enhancing Spatial Understanding in Text-to-Image Diffusion Models ICCV 2025 ComPC: Completing a 3D Point Cloud with 2D Diffusion Priors ICLR 2025 Complex-Cycle-Consistent Diffusion Model for Monaural Speech Enhancement AAAI 2025 ComposableNav: Instruction-Following Navigation in Dynamic Environments via Composable Diffusion CoRL 2025 Composing Parts for Expressive Object Generation CVPR 2025 Composition and Control with Distilled Energy Diffusion Models and Sequential Monte Carlo AISTATS 2025 Comprehensive Relighting: Generalizable and Consistent Monocular Human Relighting and Harmonization CVPR 2025 Compressed Image Generation with Denoising Diffusion Codebook Models ICML 2025 Compression-Aware One-Step Diffusion Model for JPEG Artifact Removal ICCV 2025 ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features ICML 2025 Concept Conductor: Orchestrating Multiple Personalized Concepts in Text-to-Image Synthesis AAAI 2025 ConceptGuard: Continual Personalized Text-to-Image Generation with Forgetting and Confusion Mitigation CVPR 2025 Concept Lancet: Image Editing with Compositional Representation Transplant CVPR 2025