Sotabase

Career

· Research Scientist, Google DeepMind2025–
· PhD in Computer Science, Stanford University2022–2026
· M.S. Student, MILA (Quebec AI Institute)2020–2022
· B.S. in Computer Science, Shanghai Jiao Tong University (SJTU)2016–2020

Publications (80)

GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation
International Conference on Learning Representations · 2022
652
cited
GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation
International Conference on Learning Representations · 2020
503
cited
Learning Gradient Fields for Molecular Conformation Generation
International Conference on Machine Learning · 2021
242
cited
Geometric Latent Diffusion Models for 3D Molecule Generation
International Conference on Machine Learning · 2023
225
cited
Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs
International Conference on Machine Learning · 2024
197
cited
A Graph to Graphs Framework for Retrosynthesis Prediction
International Conference on Machine Learning · 2020
173
cited
Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
Found. Trends Mach. Learn. · 2023
149
cited
Learning Neural Generative Dynamics for Molecular Conformation Generation
International Conference on Learning Representations · 2021
133
cited
Predicting Molecular Conformation via Dynamic Graph Score Matching
Neural Information Processing Systems · 2021
112
cited
When Do Graph Neural Networks Help with Node Classification: Investigating the Homophily Principle on Node Distinguishability
Neural Information Processing Systems · 2023
91
cited
An End-to-End Framework for Molecular Conformation Generation via Bilevel Programming
International Conference on Machine Learning · 2021
90
cited
Equivariant Flow Matching with Hybrid Probability Transport
Neural Information Processing Systems · 2023
87
cited
Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models
Neural Information Processing Systems · 2024
84
cited
Consistency Flow Matching: Defining Straight Flows with Velocity Consistency
arXiv.org · 2024
69
cited
MADiff: Offline Multi-agent Learning with Diffusion Models
Neural Information Processing Systems · 2023
68
cited
An all-atom protein generative model
bioRxiv · 2023
58
cited
MUDiff: Unified Diffusion for Complete Molecule Generation
LOG IN · 2023
53
cited
Energy-Based Imitation Learning
Adaptive Agents and Multi-Agent Systems · 2020
52
cited
Equivariant Graph Neural Operator for Modeling 3D Dynamics
International Conference on Machine Learning · 2024
45
cited
Generative Coarse-Graining of Molecular Conformations
International Conference on Machine Learning · 2022
43
cited
Sotabase
Minkai Xu | Researcher Profile | Sotabase | Sotabase