8 papers
Second Order Drifting Models
Drake Brown, Yuhao Huang, Shih-Hsin Wang +1
Drifting models are a recent class of one-step generative models that evolve the model distribution during training using a predefined sample-based drift field. Although they avoid…
FdAudio: MeanFlow-Anchored Fréchet-Distance Post-Training for One-Step Text-to-Audio Generation
Kuan-Po Huang, Bo-Ru Lu, Ho-Lam Chung +2
While recent few-step sampling text-to-audio generation models like MeanAudio substantially accelerate generation by modeling average velocities, their strict one-step generation q…
Improving Flow Matching by Aligning Flow Divergence
Yuhao Huang, Taos Transue, Shih-Hsin Wang +3
Conditional flow matching (CFM) stands out as an efficient, simulation-free approach for training flow-based generative models, achieving remarkable performance for data generation…
Towards Multiscale Graph-based Protein Learning with Geometric Secondary Structural Motifs
Shih-Hsin Wang, Yuhao Huang, Taos Transue +4
Graph neural networks (GNNs) have emerged as powerful tools for learning protein structures by capturing spatial relationships at the residue level. However, existing GNN-based met…
RMFlow: Refined Mean Flow by a Noise-Injection Step for Multimodal Generation
Yuhao Huang, Shih-Hsin Wang, Andrea L. Bertozzi +1
Mean flow (MeanFlow) enables efficient, high-fidelity image generation, yet its single-function evaluation (1-NFE) generation often cannot yield compelling results. We address this…
Plug-and-Play Image Restoration with Flow Matching: A Continuous Viewpoint
Fan Jia, Yuhao Huang, Shih-Hsin Wang +3
Flow matching-based generative models have been integrated into the plug-and-play image restoration framework, and the resulting plug-and-play flow matching (PnP-Flow) model has ac…