flow matching

AdvFM: Lookahead Flow-Matching Velocity-Field Attacks for Imperceptible and Transferable Adversarial Examples CVPR 2026 A-FloPS: Accelerating Diffusion Models via Adaptive Flow Path Sampler AAAI 2026 Ambiguity-aware Truncated Flow Matching for Ambiguous Medical Image Segmentation AAAI 2026 BAgger: Backwards Aggregation for Mitigating Drift in Autoregressive Video Diffusion Models CVPR 2026 Balancing Signal and Variance: Adaptive Offline RL Post-Training for VLA Flow Models AAAI 2026 BiFM: Bidirectional Flow Matching for Few-Step Image Editing and Generation CVPR 2026 BokehFlow: Depth-Free Controllable Bokeh Rendering via Flow Matching AAAI 2026 Can We Build Scene Graphs, Not Classify Them? FlowSG: Progressive Image-Conditioned Scene Graph Generation with Flow Matching CVPR 2026 Class-Partitioned VQ-VAE and Latent Flow Matching for Point Cloud Scene Generation AAAI 2026 C-LaV: Conditional Latent Velocity Field Denoising for Weather-Robust LiDAR Place Recognition CVPR 2026 Continuous Degradation Modeling via Latent Flow Matching for Real-World Super-Resolution AAAI 2026 COT-FM: Cluster-wise Optimal Transport Flow Matching CVPR 2026 DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation CVPR 2026 Deformable Polygonal Flow Matching with Informed Priors and Hierarchical Graph Constraints AAAI 2026 EfficientFlow: Efficient Equivariant Flow Policy Learning for Embodied AI AAAI 2026 Efficient probabilistic surrogate modeling techniques for partially-observed large-scale dynamical systems L4DC 2026 EgoFlow: Gradient-Guided Flow Matching for Egocentric 6DoF Object Motion Generation CVPR 2026 Emotion-Conditioned Motion Sub-spaces with Flow Matching for Real-Time Audio-Driven Talking Heads AAAI 2026 End-to-End Language-Action Model for Humanoid Whole Body Control CVPR 2026 FE2E: From Editor to Dense Geometry Estimator CVPR 2026 Few-shot Acoustic Synthesis with Multimodal Flow Matching CVPR 2026 Flash-DMD: Towards High-Fidelity Few-Step Image Generation with Efficient Distillation and Joint Reinforcement Learning CVPR 2026 FlashLips: 100-FPS Mask-Free Latent Lip-Sync using Reconstruction Instead of Diffusion or GANs CVPR 2026 FlashVideo: Flowing Fidelity to Detail for Efficient High-Resolution Video Generation AAAI 2026 Flowception: Temporally Expansive Flow Matching for Video Generation CVPR 2026