Shih-Hsin Wang

RMFlow: Refined Mean Flow by a Noise-Injection Step for Multimodal Generation

A Theoretically-Principled Sparse, Connected, and Rigid Graph Representation of Molecules

Towards Multiscale Graph-based Protein Learning with Geometric Secondary Structural Motifs

Improving Flow Matching by Aligning Flow Divergence

Learning Molecular Symmetry Breaking via Symmetry-adapted Neural Networks