Bio. I am a postdoctoral scholar in the Division of Biology and Biological Engineering at California Institute of Technology, advised by Prof. Matt Thomson. Before that, I received the Ph.D. degree from Texas A&M University, advised by Prof. Yang Shen and co-advised by Prof. Zhangyang (Atlas) Wang, and the B.Eng. degree from Xi’an Jiaotong University. Please refer to my CV for more information.

My research focuses on machine learning on non-Euclidean data (e.g. graphs or point clouds) and in dynamical systems, with fundamental understanding in theory and applications to real-world problems in life sciences (in particular modeling of molecular and cellular systems). Please refer to my Google Scholar for a complete list of the established works.

News.
2024/10. “Correlational Lagrangian Schrödinger Bridge: Learning Dynamics with Population-Level Regularization” (biology-inspired diffusion models under correlation conservation) is accepted @ AIDrugX Workshop, NeurIPS’24. 🎉
2024/07 - Present. Join the Division of Biology and Biological Engineering at California Institute of Technology, Pasadena, as a postdoctoral scholar advised by Prof. Matt Thomson.
2024/06. Pass the Ph.D. final defense titled “Generalizable Graph AI for Biomedicine: Data-Driven Self-Supervision and Principled Regularization”, and become a Ph.D. 🎓🎉
2024/04. Participate in the community effort of CAGI6 Rare Genomes Project with the outcome accepted @ Human Genomics’24.
2024/03. “Multi-Modal Contrastive Learning for Proteins by Combining Domain-Informed Views” (multi-modal protein representation learning) is accepted @ MLGenX Workshop, ICLR’24. [poster]
2024/01. “Latent 3D Graph Diffusion” (latent diffusion models for 3D graphs) is accepted @ ICLR’24. [poster]

2023/10. Talk on Prof. James Cai’s lab @ TAMU, online.
2023/08. Talk on the Spatial Omics Journal Club @ Genentech, online.
2023/05 – 2023/08. Join the Research and Early Development organization at Genentech, Inc. (gRED), South San Francisco, as an AIML intern advised by Dr. Changlin Wan & Dr. Kai Liu.
2023/04. Receive the Quality Graduate Student Award from ECEN @ Texas A&M University.
2023/01. “Graph Domain Adaptation via Theory-Grounded Spectral Regularization” (model-based risk bound analysis of GDA) is accepted @ ICLR’23. [poster] 🎉

2022/10. “Does Inter-Protein Contact Prediction Benefit from Multi-Modal Data and Auxiliary Tasks?” (multi-modal/task protein-protein interface prediction) is accepted @ MLSB Workshop, NeurIPS’22. [poster]
2022/09. “Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative” (contrastive learning on hypergraphs) is accepted @ NeurIPS’22. [poster]
2022/06. “Cross-Modality and Self-Supervised Protein Embedding for Compound-Protein Affinity and Contact Prediction” (multi-modal self-supervision in CPAC) is accepted @ Bioinformatics’22 (MoML’22, ECCB’22). [poster]
2022/05 – 2022/08. Join the Department of Data Science and Machine Learning at insitro, Inc., South San Francisco, as an ML small molecules intern advised by Dr. Bowen Liu & Ralph Ma. 🎉
2022/03. Talk on the AI&A Journal Club @ AstraZeneca, online.
2022/01. “Bayesian Modeling and Uncertainty Quantification for Learning to Optimize: What, Why, and How” (Bayesian learning to optimize) is accepted @ ICLR’22. [poster]

2021/12. Receive the NSF Student Travel Awards from WSDM’22.
2021/10. Talk on Prof. Mingyuan Zhou’s group @ UT Austin, online.
2021/10. “Bringing Your Own View: Graph Contrastive Learning without Prefabricated Data Augmentations” (generative augmentations in GraphCL) is accepted @ WSDM’22. [poster]
2021/09. Receive the Chevron Scholarship from ECEN @ Texas A&M University.
2021/08. Talk on LoGaG @ Technical University of Munich, online.
2021/07. Talk on 3DSIG COSI @ ISMB/ECCB’21, online. [video]
2021/07. Serve as the session chair of Semisupervised and Unsupervised Learning @ ICML’21 and talk.
2021/06 – 2021/08. Join the Product Semantics Team at Amazon.com Services, Inc. remotely, as an applied scientist intern advised by Dr. Tong Zhao.
2021/05. “Graph Contrastive Learning Automated” (long presentation, automatic augmentation selection in GraphCL) is accepted @ ICML’21. [video] 🎉
2021/03. “Probabilistic Constructive Interference Precoding for Imperfect CSIT” (undergraduate thesis work, robust CI precoding) is accepted @ TVT’21. 🎉
2021/02. Pass the Ph.D. qualifying exam.

2020/09. “Cross-Modality Protein Embedding for Compound-Protein Affinity and Contact Prediction” (cross-modality learning in CPAC) is accepted @ MLSB Workshop, NeurIPS’20. [poster]
2020/09. “Graph Contrastive Learning with Augmentations” (contrastive learning in GNN pre-training) is accepted @ NeurIPS’20. [poster]
2020/09 – 2024/05. Employed by the Department of Electrical and Computer Engineering at Texas A&M University, College Station, as a graduate research assistant advised by Prof. Yang Shen.
2020/06. “When Does Self-Supervision Help Graph Convolutional Networks?” (self-supervision in GCNs) is accepted @ ICML’20.
2020/02. “L²-GCN: Layer-Wise and Learned Efficient Training of Graph Convolutional Networks” (efficient GCN training) is accepted @ CVPR’20.

2019/08 – 2024/08. Attend Texas A&M University, College Station, for the Ph.D. Degree in Electrical Engineering, advised by Prof. Yang Shen.
2019/02. Receive the Electrical and Computer Engineering PhD Merit Fellowship from ECEN @ Texas A&M University.