Diffusion Models

Towards Enhanced Image Inpainting: Mitigating Unwanted Object Insertion and Preserving Color Consistency CVPR 2025 Towards Hierarchical Rectified Flow ICLR 2025 Towards High-fidelity 3D Talking Avatar with Personalized Dynamic Texture CVPR 2025 Towards Open-World Generation of Stereo Images and Unsupervised Matching ICCV 2025 Towards Precise Embodied Dialogue Localization via Causality Guided Diffusion CVPR 2025 Towards Precise Scaling Laws for Video Diffusion Transformers CVPR 2025 Towards Privacy-Preserving Split Learning for ControlNet WACV 2025 Towards Realistic Data Generation for Real-World Super-Resolution ICLR 2025 Towards Robust and Scalable Knowledge Editing in Text-to-Image Diffusion Models ACML 2025 Towards Robust Defense against Customization via Protective Perturbation Resistant to Diffusion-based Purification ICCV 2025 Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints ICCV 2025 Towards Transformer-Based Aligned Generation with Self-Coherence Guidance CVPR 2025 Towards Understanding and Quantifying Uncertainty for Text-to-Image Generation CVPR 2025 Towards Understanding Text Hallucination of Diffusion Models via Local Generation Bias ICLR 2025 Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective ICLR 2025 Towards Universal Dataset Distillation via Task-Driven Diffusion CVPR 2025 Towards Unsupervised Blind Face Restoration using Diffusion Prior WACV 2025 TrackDiffusion: Tracklet-Conditioned Video Generation via Diffusion Models WACV 2025 TrackGo: A Flexible and Efficient Method for Controllable Video Generation AAAI 2025 TrackVLA: Embodied Visual Tracking in the Wild CoRL 2025 Training Diffusion-based Generative Models with Limited Data ICML 2025 Training-free and Adaptive Sparse Attention for Efficient Long Video Generation ICCV 2025 Training-Free and Hardware-Friendly Acceleration for Diffusion Models via Similarity-based Token Pruning AAAI 2025 Training-free Camera Control for Video Generation ICLR 2025 Training-free Dense-Aligned Diffusion Guidance for Modular Conditional Image Synthesis CVPR 2025