Gang Liu

torch-molecule. torch-molecule is a deep learning package for molecular discovery, designed with an sklearn-style interface for property prediction, inverse design and representation learning.

deepevolve. DeepEvolve is a research and coding agent for new algorithm discovery in different science domains with Deep Research and AlphaEvolve.

Graph-DiT. The code for "Graph Diffusion Transformer for Multi-Conditional Molecular Generation"

GREA. [KDD'22] Source codes of "Graph Rationalization with Environment-based Augmentations"

Llamole. Llamole: Multimodal Large Language Models for Inverse Molecular Design with Retrosynthetic Planning

InfoAlign. The code for "Learning Molecular Representation in a Cell"

SGIR. [KDD'23] Source codes of "Semi-Supervised Graph Imbalanced Regression"

Data-Centric-Transfer. [NeurIPS'23] Source code of "Data-Centric Learning from Unlabeled Graphs with Diffusion Model": A data-centric transfer learning framework with diffusion model on graphs.

DemoDiff. DemoDiff is a diffusion-based molecular foundation model for in-context inverse molecular design.

infoalign-package. Python package for InfoAlign

MolBench_tool. MolBench: A Molecular Representation Benchmarking Toolkit

polymer_repeat. Python

graph-data-augmentation-papers. A curated list of graph data augmentation papers.

cf_visualize. Visualization of counterfactual explanation for NetFLow datasets