5 papers
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…
Arcs on rational double points in arbitrary characteristic
Tommaso de Fernex, Shih-Hsin Wang
We prove that the Nash problem holds for two-dimensional rational double points in all characteristics. The proof is based on a direct computation of the families of arcs through t…