diffusion model

HierDiffuse: Progressive Diffusion for Robust Interest Fusion in CTR Prediction EMNLP 2025 HiFi-Portrait: Zero-shot Identity-preserved Portrait Generation with High-fidelity Multi-face Fusion CVPR 2025 HiGarment: Cross-modal Harmony Based Diffusion Model for Flat Sketch to Realistic Garment Image ICCV 2025 High-Fidelity Relightable Monocular Portrait Animation with Lighting-Controllable Video Diffusion Model CVPR 2025 High-Precision Dichotomous Image Segmentation via Probing Diffusion Capacity ICLR 2025 High-Resolution Frame Interpolation with Patch-based Cascaded Diffusion AAAI 2025 History-Guided Video Diffusion ICML 2025 Holistic Unlearning Benchmark: A Multi-Faceted Evaluation for Text-to-Image Diffusion Model Unlearning ICCV 2025 HomeDiffusion: Zero-Shot Object Customization with Multi-View Representation Learning for Indoor Scenes AAAI 2025 HomoGen: Enhanced Video Inpainting via Homography Propagation and Diffusion CVPR 2025 HouseCrafter: Lifting Floorplans to 3D Scenes with 2D Diffusion Models ICCV 2025 How Compositional Generalization and Creativity Improve as Diffusion Models are Trained ICML 2025 How Distributed Collaboration Influences the Diffusion Model Training? A Theoretical Perspective ICML 2025 How Far Is Video Generation from World Model: A Physical Law Perspective ICML 2025 How Much is a Noisy Image Worth? Data Scaling Laws for Ambient Diffusion. ICLR 2025 HSRDiff: A Hierarchical Self-Regulation Diffusion Model for Stochastic Semantic Segmentation AAAI 2025 HUANG: A Robust Diffusion Model-based Targeted Adversarial Attack Against Deep Hashing Retrieval AAAI 2025 Human Body Restoration with One-Step Diffusion Model and A New Benchmark ICML 2025 HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation CVPR 2025 Human Motion Capture from Loose and Sparse Inertial Sensors with Garment-aware Diffusion Models IJCAI 2025 Human vs. AI: A Novel Benchmark and a Comparative Study on the Detection of Generated Images and the Impact of Prompts COLING 2025 Hummingbird: High Fidelity Image Generation via Multimodal Context Alignment ICLR 2025 HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animation CVPR 2025 Hybrid Layout Control for Diffusion Transformer: Fewer Annotations, Superior Aesthetics ICCV 2025 Hybrid Regularization Improves Diffusion-based Inverse Problem Solving ICLR 2025