Diffusion Models

HandDiffuse: Generative Controllers for Two-Hand Interactions via Diffusion Models AAAI 2025 HarmoniCa: Harmonizing Training and Inference for Better Feature Caching in Diffusion Transformer Acceleration ICML 2025 Harmonious Music-driven Group Choreography with Trajectory-Controllable Diffusion AAAI 2025 Harmonizing Geometry and Uncertainty: Diffusion with Hyperspheres ICML 2025 Harmonizing Visual and Textual Embeddings for Zero-Shot Text-to-Image Customization AAAI 2025 Harmonizing Visual Representations for Unified Multimodal Understanding and Generation ICCV 2025 Harnessing Frequency Spectrum Insights for Image Copyright Protection Against Diffusion Models CVPR 2025 Harnessing Text-to-Image Diffusion Models for Point Cloud Self-Supervised Learning ICCV 2025 HART: Efficient Visual Generation with Hybrid Autoregressive Transformer ICLR 2025 Hash3D: Training-free Acceleration for 3D Generation CVPR 2025 Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions ICCV 2025 HDiff: Confidence-Guided Denoising Diffusion for Robust Hyper-relational Link Prediction EMNLP 2025 HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion Models ICLR 2025 HDR Image Generation via Gain Map Decomposed Diffusion ICCV 2025 HealthCards: Exploring Text-to-Image Generation as Visual Aids for Healthcare Knowledge Democratizing and Education EMNLP 2025 Hearing Hands: Generating Sounds from Physical Interactions in 3D Scenes CVPR 2025 Heavy-Tailed Diffusion Models ICLR 2025 Heavy-Tailed Diffusion with Denoising Levy Probabilistic Models ICLR 2025 h-Edit: Effective and Flexible Diffusion-Based Editing via Doob's h-Transform CVPR 2025 HERO: Human-Feedback Efficient Reinforcement Learning for Online Diffusion Model Finetuning ICLR 2025 Hessian Geometry of Latent Space in Generative Models ICML 2025 HexaGen3D: StableDiffusion is One Step Away from Fast and Diverse Text-to-3D Generation WACV 2025 Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging ICCV 2025 Hidden in the Noise: Two-Stage Robust Watermarking for Images ICLR 2025 Hiding Images in Diffusion Models by Editing Learned Score Functions CVPR 2025