Generative Models

Not All Parameters Matter: Masking Diffusion Models for Enhancing Generation Ability CVPR 2025 Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models CVPR 2025 No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Models ICLR 2025 NRFlow: Towards Noise-Robust Generative Modeling via High-Order Mechanism UAI 2025 NRGBoost: Energy-Based Generative Boosted Trees ICLR 2025 Number Theoretic Accelerated Learning of Physics-Informed Neural Networks AAAI 2025 ObjectMover: Generative Object Movement with Video Prior CVPR 2025 Occlusion-Insensitive Talking Head Video Generation via Facelet Compensation AAAI 2025 ODA-GAN: Orthogonal Decoupling Alignment GAN Assisted by Weakly-supervised Learning for Virtual Immunohistochemistry Staining CVPR 2025 Offline Model-based Optimization for Real-World Molecular Discovery ICML 2025 Offline-to-Online Reinforcement Learning with Classifier-Free Diffusion Generation ICML 2025 OLiDM: Object-aware LiDAR Diffusion Models for Autonomous Driving AAAI 2025 OMG: Opacity Matters in Material Modeling with Gaussian Splatting ICLR 2025 OmniBind: Large-scale Omni Multimodal Representation via Binding Spaces ICLR 2025 OmniGen: Unified Image Generation CVPR 2025 Omni-ID: Holistic Identity Representation Designed for Generative Tasks CVPR 2025 OmniPhysGS: 3D Constitutive Gaussians for General Physics-Based Dynamics Generation ICLR 2025 OmniRe: Omni Urban Scene Reconstruction ICLR 2025 OmniSR: Shadow Removal Under Direct and Indirect Lighting AAAI 2025 Once-for-All: Controllable Generative Image Compression with Dynamic Granularity Adaptation ICLR 2025 One-Minute Video Generation with Test-Time Training CVPR 2025 One Stone, Two Birds: Enhancing Adversarial Defense Through the Lens of Distributional Discrepancy ICML 2025 One-Way Ticket: Time-Independent Unified Encoder for Distilling Text-to-Image Diffusion Models CVPR 2025 On Reducing Factual Hallucinations in Graph-to-Text Generation Using Large Language Models COLING 2025 On the Guidance of Flow Matching ICML 2025