Diffusion Models

Image Regeneration: Evaluating Text-to-Image Model via Generating Identical Image with Multimodal Large Language Models AAAI 2025 Images as Noisy Labels: Unleashing the Potential of the Diffusion Model for Open-Vocabulary Semantic Segmentation ICCV 2025 Image Watermarks are Removable using Controllable Regeneration from Clean Noise ICLR 2025 IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance ICCV 2025 IMPACT: Iterative Mask-based Parallel Decoding for Text-to-Audio Generation with Diffusion Modeling ICML 2025 Implicit Bias Injection Attacks against Text-to-Image Diffusion Models CVPR 2025 Importance-Based Token Merging for Efficient Image and Video Generation ICCV 2025 IM-Portrait: Learning 3D-aware Video Diffusion for Photorealistic Talking Heads from Monocular VideosC CVPR 2025 Imposter: Text and Frequency Guidance for Subject Driven Action Personalization using Diffusion Models COLING 2025 Improved Convergence Rate for Diffusion Probabilistic Models ICLR 2025 Improved Diffusion-based Generative Model with Better Adversarial Robustness ICLR 2025 Improved Discretization Complexity Analysis of Consistency Models: Variance Exploding Forward Process and Decay Discretization Scheme ICML 2025 Improved Intelligibility of Dysarthric Speech using Conditional Flow Matching Interspeech 2025 Improved Noise Schedule for Diffusion Training ICCV 2025 Improved Sampling Algorithms for Lévy-Itô Diffusion Models ICLR 2025 Improved Sampling Of Diffusion Models In Fluid Dynamics With Tweedie's Formula ICLR 2025 Improved Training Technique for Latent Consistency Models ICLR 2025 Improving Compositional Generation with Diffusion Models Using Lift Scores ICML 2025 Improving Conditional Diffusion Models through Re-Noising from Unconditional Diffusion Priors WACV 2025 Improving Consistency Models with Generator-Augmented Flows ICML 2025 Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing CVPR 2025 Improving Editability in Image Generation with Layer-wise Memory CVPR 2025 Improving Faithfulness of Text-to-Image Diffusion Models through Inference Intervention WACV 2025 Improving Long-Text Alignment for Text-to-Image Diffusion Models ICLR 2025 Improving Probabilistic Diffusion Models With Optimal Diagonal Covariance Matching ICLR 2025