Hongyang Gao

RESTRAIN: From Spurious Votes to Signals — Self-Training RL with Self-Penalization

Flow-Matching based Refiner for Molecular Conformer Generation

Motif-Aware Embeddings for Enhanced Few-Shot Graph Learning

Global Convergence in Neural ODEs: Impact of Activation Functions

MAGE: Model-Level Graph Neural Networks Explanations via Motif-based Graph Generation

MotifExplainer: a Motif-based Graph Neural Network Explainer

G2T-LLM: Graph-to-Tree Text Encoding for Molecule Generation with Fine-Tuned Large Language Models