I am a joint postdoc at UC Berkeley & Caltech, working with Prof. Jennifer Chayes, Prof. Christian Borgs, and Prof. Anima Anandkumar.

I got my CS Ph.D. degree with at Quebec Artificial Intelligence Institute (AKA Mila) and Université de Montréal, advised by Prof. Jian Tang. Meanwhile, I have close collaboration with Prof. Hongyu Guo.

I got my CS master’s degree from University of Wisconsin-Madison, and was the graduate researcher at Morgridge Institute for Research. During my stay in UW-Madison, I started my first research project and was fortunately advised by Prof. Anthony Gitter, Prof. Yingyu Liang, and Prof. Dimitris Papailiopoulos. Proir to that, I got my bachelor’s degree from Shandong University.

E-Mail: shengchao1224 at gmail dot com

I also want to share some inspiring research values (special thanks to Weiyang)

• Focus on creating novel ideas, not publishing papers
• Follow curiosity and passion, not trends
• Ideas are not owned, but come with debts to those who came before
• Ideas become stronger when shared, discussed and criticized
• Life is surprisingly short, so solve problems that interest and excite you most
• It is good to be quick, but it is more important to be deep
• Think like an amateur, do as an expert
• Last lecture by Prof. Randy Pausch
• [My research motto] Know me through my work! :)

Research Topics

• Representation Learning and Distribution Modeling
  • structured/geometric/graph representation learning
  • self-supervised learning
  • multi-task learning
  • deep generative modeling
  • controllable/conditional deep generative modeling
• Large Language Model
• Molecule Discovery
  • small molecules
  • proteins
  • materials
  • genomes
• ML and Physical Dynamics
  • classical molecular dynamics
  • ab-initio molecular dynamcis
  • learning dynamics

Selected Publications

Molecular Dynamics and Learning Dynamics

• NeuralMD: A Multi-Grained Symmetric Differential Equation Model for Learning Protein-Ligand Binding Dynamics
  Shengchao Liu^*, Weitao Du^*, Yanjing Li, Zhuoxinran Li, Vignesh Bhethanabotla, Nakul Rampal, Omar Yaghi, Christian Borgs, Anima Anandkumar^*, Hongyu Guo^*, Jennifer Chayes^*
  [Arxiv] [Project Page] [Code]
  [ICLR AI4DifferentialEquations Workshop 2024 Oral]

• Bad Global Minima Exist and SGD Can Reach Them
  Shengchao Liu, Dimitris Papailiopoulos, Dimitris Achlioptas
  NeurIPS 2020
  [Paper] [Code] [Slides] [Poster] [Video/Audio, NeurIPS 2020]
  [ICML Deep Learning Phenomena Workshop 2019 Oral]

LLM for Molecule Design

• ChatDrug: ChatGPT-powered Conversational Drug Editing Using Retrieval and Domain Feedback
  Shengchao Liu^*, Jiongxiao Wang^*, Yijin Yang, Chengpeng Wang, Ling Liu, Hongyu Guo, Chaowei Xiao
  ICLR 2024
  [Paper] [Project Page] [ArXiv] [Code]
  [ICML SynS and ML Workshop 2023 Oral]

• ProteinDT: A Text-guided Protein Design Framework
  Shengchao Liu, Yanjing Li, Zhuoxinran Li, Anthony Gitter, Yutao Zhu, Jiarui Lu, Zhao Xu, Weili Nie, Arvind Ramanathan, Chaowei Xiao^*, Jian Tang^*, Hongyu Guo^*, Anima Anandkumar^*
  [Project Page] [ArXiv] [Code]

• MoleculeSTM: Multi-modal Molecule Structure-text Model for Text-based Editing and Retrieval
  Shengchao Liu, Weili Nie, Chengpeng Wang, Jiarui Lu, Zhuoran Qiao, Ling Liu, Jian Tang, Chaowei Xiao, Anima Anandkumar
  Nature Machine Intelligence 2023
  [Paper] [Project Page] [ArXiv] [Code]
  [NeurIPS AI4Science Workshop 2022]

• GraphCG: Unsupervised Discovery of Steerable Factors When Graph Deep Generative Models Are Entangled
  Shengchao Liu, Chengpeng Wang, Jiarui Lu, Weili Nie, Hanchen Wang, Zuoxinran Li, Bolei Zhou, Jian Tang
  TMLR 2024
  [Paper] [Project Page] [ArXiv] [Code]
  [NeurIPS GLFrontiers Workshop 2022 Oral]

Transfer Learning

• MoleculeSDE: A Group Symmetric Stochastic Differential Equation Model for Molecule Multi-modal Pretraining
  Shengchao Liu^*, Weitao Du^*, Zhiming Ma, Hongyu Guo, Jian Tang
  ICML 2023
  [Project Page] [Paper] [ArXiv] [Code]

• GeoSSL: Molecular Geometry Pretraining with SE(3)-Invariant Denoising Distance Matching
  Shengchao Liu, Hongyu Guo, Jian Tang
  ICLR 2023
  [Project Page] [Paper] [ArXiv] [Code]

• GraphMVP: Pre-training Molecular Graph Representation with 3D Geometry
  Shengchao Liu, Hanchen Wang, Weiyang Liu, Joan Lasenby, Hongyu Guo, Jian Tang
  ICLR 2022
  [Project Page] [Paper] [ArXiv] [Code] [Slides] [Poster]
  [NeurIPS SSL Workshop 2021]
  [ICLR GTRL Workshop 2022 Spotlight]

• SGNN-EBM: Structured Multi-task Learning for Molecular Property Prediction
  Shengchao Liu, Meng Qu, Zuobai Zhang, Huiyu Cai, Jian Tang
  AISTATS 2022
  [Project Page] [Paper] [ArXiv] [Code] [Slides] [Poster]
  [NeurIPS AI4Science Workshop 2021]

• LBTW: Loss-Balanced Task Weighting to Reduce Negative Transfer in Multi-Task Learning
  Shengchao Liu, Yingyu Liang, Anthony Gitter
  AAAI-Student Abstract 2019
  [Paper] [Appendix] [Code] [Poster]

Representation Learning

• Geom3D: Symmetry-Informed Geometric Representation for Molecules, Proteins, and Crystalline Materials
  Shengchao Liu, Weitao Du, Yanjing Li, Zhuoxinran Li, Zhiling Zheng, Chenru Duan, Zhiming Ma, Omar Yaghi, Anima Anandkumar, Christian Borgs, Jennifer Chayes, Hongyu Guo, Jian Tang
  NeurIPS Datasets and Benchmarks 2023
  [Paper] [ArXiv] [Code]

• AWARE: Attentive Walk-Aggregating Graph Neural Networks
  Mehmet F. Demirel, Shengchao Liu, Siddhant Garg, Zhenmei Shi, Yingyu Liang
  TMLR 2022
  [Paper] [ArXiv] [Code]

• N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules
  Shengchao Liu, Mehmet Furkan Demirel, Yingyu Liang
  NeurIPS 2019 Spotlight
  [Paper] [ArXiv] [Code] [Slides][Poster]
  [NeurIPS MLMM Workshop 2018]

Interests

• Coding. Like ACM-ICPC and Capture the Flag.
• Video Editing. Quite cool stuff.
• Reading. Novels are my favourite, but also history and computer books.
• Music. Classical music are perfect match for coding.