flow-based model

Behavior Regularization with Flow Latent Policy for Offline Reinforcement Learning AAAI 2026 CUPID: Generative 3D Reconstruction via Joint Object and Pose Modeling CVPR 2026 Decomposing Ensemble Spread in Lorenz ’96 with Learned Stochastic Parameterizations UAI 2026 Few-step Flow for 3D Generation via Marginal-Data Transport Distillation AAAI 2026 FlowPortal: Residual-Corrected Flow for Training-Free Video Relighting and Background Replacement CVPR 2026 FM-Steer: Enhance Generalist Policies with Value-Guided Cascaded Denoising CVPR 2026 One-Step Generative Policies with Q-Learning: A Reformulation of MeanFlow AAAI 2026 Color Transfer with Modulated Flows AAAI 2025 Deeply Supervised Flow-Based Generative Models ICCV 2025 DR-VAE: Debiased and Representation-enhanced Variational Autoencoder for Collaborative Recommendation AAAI 2025 Flow Stochastic Segmentation Networks ICCV 2025 Foley-Flow: Coordinated Video-to-Audio Generation with Masked Audio-Visual Alignment and Dynamic Conditional Flows CVPR 2025 Goku: Flow Based Video Generative Foundation Models CVPR 2025 Heterogeneous Datasets for Unsupervised Image Anomaly Detection WACV 2025 Integrating Multi-Source Data for Long Sequence Precipitation Forecasting AAAI 2025 Multi-Modal and Multi-Attribute Generation of Single Cells with CFGen ICLR 2025 Neural Conjugate Flows: A Physics-Informed Architecture with Flow Structure AAAI 2025 Reversing Flow for Image Restoration CVPR 2025 TARO: Timestep-Adaptive Representation Alignment with Onset-Aware Conditioning for Synchronized Video-to-Audio Synthesis ICCV 2025 TCSinger 2: Customizable Multilingual Zero-shot Singing Voice Synthesis ACL 2025 VinTAGe: Joint Video and Text Conditioning for Holistic Audio Generation CVPR 2025 AdaFlow: Imitation Learning with Variance-Adaptive Flow-Based Policies NeurIPS 2024 Boosting Flow-based Generative Super-Resolution Models via Learned Prior CVPR 2024 FlowIE: Efficient Image Enhancement via Rectified Flow CVPR 2024 FlowTurbo: Towards Real-time Flow-Based Image Generation with Velocity Refiner NeurIPS 2024