Songtao Liu
[Google Scholar] [Github]
Email: skl5761@psu.edu
Hi, this is Songtao. I’m currently a third-year Ph.D. student advised by Prof. Peng Liu at Penn State. I obtained my B.S. from School of Data Science at Fudan University. My research focuses on machine learning, generative modeling, and large language models.
We’re looking for graduate and undergraduate students to work with me and Prof. Liu on AI for Science (Drug Design and Molecule Synthesis) and Large Language Models (Efficient LLMs and Alignment). Feel free to send me an email (songtaoliu.ml@gmail.com) if you’d like to schedule a chat!
I am actively looking for both full-time and part-time internships for the spring and summer of 2025, as well as full-time positions for the summer and fall of 2025 in the industry. If my research interests align with your needs, please feel free to contact me.
Preference Optimization for Molecule Synthesis with Conditional Residual Energy-based Models
Songtao Liu, Hanjun Dai, Yue Zhao, Peng Liu
International Conference on Machine Learning (ICML), 2024 Oral
[arXiv] [Code]
Graph Adversarial Diffusion Convolution
Songtao Liu, Jinghui Chen, Tianfan Fu, Lu Lin, Marinka Zitnik, Dinghao Wu
International Conference on Machine Learning (ICML), 2024
[arXiv] [Code]
FusionRetro: Molecule Representation Fusion via In-Context Learning for Retrosynthetic Planning
Songtao Liu, Zhengkai Tu, Minkai Xu, Zuobai Zhang, Lu Lin, Rex Ying, Jian Tang, Peilin Zhao, Dinghao Wu
*International Conference on Machine Learning (ICML), 2023
[arXiv] [Code]
Local Augmentation for Graph Neural Networks
Songtao Liu, Rex Ying, Hanze Dong, Lanqing Li, Tingyang Xu, Yu Rong, Peilin Zhao, Junzhou Huang, Dinghao Wu
International Conference on Machine Learning (ICML), 2022
[arXiv] [Code]
Conference/Journal Reviewer: ICML 2022/2024, NeurIPS 2022/2023/2024, ICLR 2024, AISTATS 2024, TMLR