Publications

2024

[1] Hamiltonian Diversity: Effectively Measuring Molecular Diversity by Shortest Hamiltonian Circuits
Xiuyuan Hu, Guoqing Liu, Quanming Yao, Yang Zhao, Hao Zhang.
In Journal of Cheminformatics, volume 16 (2024).
Paper Code

[2] When Will Gradient Regularization Be Harmful?
Yang Zhao, Hao Zhang, Xiuyuan Hu.
In 41th International Conference on Machine Learning (ICML), 2024.
Paper Code

[3] Empirical Evidence for the Fragment level understanding on Drug Molecular Structure of LLMs
Xiuyuan Hu, Guoqing Liu, Yang Zhao, Hao Zhang.
In AAAI 2024 workshop - LLMs4Bio: Large Language Models for Biological Discoveries, 2024.
Paper Code

2023

[1] De novo Drug Design using Reinforcement Learning with Multiple GPT Agents
Xiuyuan Hu, Guoqing Liu, Yang Zhao, Hao Zhang.
In 37th Conference on Neural Information Processing Systems (NeurIPS), 2023.
Paper Code

[2] De novo Drug Design against SARS-CoV-2 Protein Targets using SMILES-based Deep Reinforcement Learning
Xiuyuan Hu, Yanghepu Li, Guoqing Liu, Yang Zhao, Hao Zhang, Liang Zhao.
In 11th International Conference on Information Technology: IoT and Smart City (ICIT), 2023.
Paper

[3] Role Taxonomy of Units in Deep Neural Networks
Yang Zhao, Hao Zhang, Xiuyuan Hu.
In NeurIPS 2023 workshop - UniReps: Unifying Representations in Neural Models, 2023.
Paper

[4] Estimating the Generalization in Deep Neural Networks via Sparsity
Yang Zhao, Hao Zhang, Xiuyuan Hu.
In NeurIPS 2023 workshop - ATTRIB: Attributing Model Behavior at Scale, 2023.
Paper

2022

[1] Penalizing Gradient Norm for Efficiently Improving Generalization in Deep Learning
Yang Zhao, Hao Zhang, Xiuyuan Hu.
In 39th International Conference on Machine Learning (ICML), 2022.
Paper Code