diffusion model

Co-Speech Gesture Video Generation with Implicit Motion-Audio Entanglement CVPR 2025 Counting Guidance for High Fidelity Text-to-Image Synthesis WACV 2025 CPSample: Classifier Protected Sampling for Guarding Training Data During Diffusion ICLR 2025 CraftsMan3D: High-fidelity Mesh Generation with 3D Native Diffusion and Interactive Geometry Refiner CVPR 2025 CreatiLayout: Siamese Multimodal Diffusion Transformer for Creative Layout-to-Image Generation ICCV 2025 Creative Agents: Empowering Agents with Imagination for Creative Tasks UAI 2025 Cross-Attention Head Position Patterns Can Align with Human Visual Concepts in Text-to-Image Generative Models ICLR 2025 Cross-Modal Learning for Music-to-Music-Video Description Generation NAACL 2025 Cross-Subject Mind Decoding from Inaccurate Representations ICCV 2025 Cross-View Meets Diffusion: Aerial Image Synthesis with Geometry and Text Guidance WACV 2025 Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Model ICLR 2025 CTRL-D: Controllable Dynamic 3D Scene Editing with Personalized 2D Diffusion CVPR 2025 CtrLoRA: An Extensible and Efficient Framework for Controllable Image Generation ICLR 2025 CtrlSynth: Controllable Image Text Synthesis for Data-Efficient Multimodal Learning ICML 2025 Ctrl-U: Robust Conditional Image Generation via Uncertainty-aware Reward Modeling ICLR 2025 CTSyn: A Foundation Model for Cross Tabular Data Generation ICLR 2025 CT to PET Translation: A Large-Scale Dataset and Domain-Knowledge-Guided Diffusion Approach WACV 2025 Curriculum Conditioned Diffusion for Multimodal Recommendation AAAI 2025 Curriculum Direct Preference Optimization for Diffusion and Consistency Models CVPR 2025 CusConcept: Customized Visual Concept Decomposition with Diffusion Models WACV 2025 CustAny: Customizing Anything from A Single Example CVPR 2025 CustomTTT: Motion and Appearance Customized Video Generation via Test-Time Training AAAI 2025 CyberHost: A One-stage Diffusion Framework for Audio-driven Talking Body Generation ICLR 2025 Cycle3D: High-quality and Consistent Image-to-3D Generation via Generation-Reconstruction Cycle AAAI 2025 Cycle Consistency as Reward: Learning Image-Text Alignment without Human Preferences ICCV 2025