Sotabase

Career

· Assistant Professor, The Chinese University of Hong Kong2025–
· Postdoctoral Researcher, University of California, Berkeley2023–2025
· Doctor of Philosophy - PhD, Computer Science, Université de Montréal2020–2023
· Master of Science - MS, Computer Science, University of Wisconsin-Madison2015–2018

Publications (41)

Scientific discovery in the age of artificial intelligence
Nature · 2023
1,351
cited
Pre-training Molecular Graph Representation with 3D Geometry
International Conference on Learning Representations · 2021
415
cited
ATOMO: Communication-efficient Learning via Atomic Sparsification
Neural Information Processing Systems · 2018
379
cited
Multi-modal molecule structure–text model for text-based retrieval and editing
Nature Machine Intelligence · 2022
238
cited
N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules
Neural Information Processing Systems · 2018
221
cited
Loss-Balanced Task Weighting to Reduce Negative Transfer in Multi-Task Learning
AAAI Conference on Artificial Intelligence · 2019
173
cited
Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning
International Conference on Machine Learning · 2020
125
cited
MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Design
arXiv.org · 2022
98
cited
Molecular Geometry Pretraining with SE(3)-Invariant Denoising Distance Matching
International Conference on Learning Representations · 2022
94
cited
A text-guided protein design framework
Nature Machine Intelligence · 2023
90
cited
Bad Global Minima Exist and SGD Can Reach Them
Neural Information Processing Systems · 2019
84
cited
TorchDrug: A Powerful and Flexible Machine Learning Platform for Drug Discovery
arXiv.org · 2022
84
cited
GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning
bioRxiv · 2023
83
cited
Shaping the Water-Harvesting Behavior of Metal-Organic Frameworks Aided by Fine-Tuned GPT Models.
Journal of the American Chemical Society · 2023
81
cited
Learning Drug Functions from Chemical Structures with Convolutional Neural Networks and Random Forests
Journal of Chemical Information and Modeling · 2019
75
cited
Practical Model Selection for Prospective Virtual Screening
bioRxiv · 2018
65
cited
ChatGPT-powered Conversational Drug Editing Using Retrieval and Domain Feedback
arXiv.org · 2023
43
cited
A Group Symmetric Stochastic Differential Equation Model for Molecule Multi-modal Pretraining
International Conference on Machine Learning · 2023
42
cited
Symmetry-Informed Geometric Representation for Molecules, Proteins, and Crystalline Materials
Neural Information Processing Systems · 2023
37
cited
Evaluating Self-Supervised Learning for Molecular Graph Embeddings
Neural Information Processing Systems · 2022
34
cited
Sotabase
Shengchao Liu | Researcher Profile | Sotabase | Sotabase