To put a dent in the universe.
——Steve Jobs
Zhongliang Zhou(周中良）
I am a Senior Scientist at Merck & Co., Inc. Previously, I obtained my Ph.D. in Computer Science at the University of Georgia co-advised by Dr.Natarajan Kannan and Dr.Sheng Li.
My main research interests focus on interdisciplinary research, Machine Learning, and Deep learning with applications in bioinformatics, and computer vision. I am also interested in explainable machine learning(XAI).
In my spare time, I am keen on photography, tennis, and badminton.
I am fortunate to have two cutest puppies in the world named Juan Mao(卷毛) and Alpha(阿尔法).
News
One paper for backdoor defense is accepted by ICLR 2025!
One paper for backdoor detection is accepted by TMLR with feature certificate!
One paper for GeoXAI is accepted by the International Journal of Geographical Information Science!
One paper for RAG in Pharmaceutical Application is accepted by AAAI 2025, See you in Philly!
I was awarded the Best PhD Dissertation Award by the University of Georgia School of Computing!
One paper for using LLM and RAG for image geo-localization is accepted by SIGIR!
One review paper for Informatic challenges and advances in illuminating the druggable proteome is accepted by Drug Discovery Today(IF 7.4)!
One paper for building an explainable model for mapping kinase-substrate interaction is accepted by Oxford Bioinformatics(IF 6.931)!
I have successfully defended my Ph.D. degree!
I have received the UGA Sustainable Grant!
I was invited to give a talk at UIUC Conceptual Foundation Group.
One paper for detecting backdoor from LVM was accepted by AAAI 2024 as student abstract!
One paper on fish identification was accepted at AJCAI 2023. More information about our project can be found in this news article!
Two papers have been accepted by ICML 2023 workshop! One will be presented as a spotlight presentation!
I will join Microsoft Research as a research intern this summer, see you in Redmond!
One paper accepted by Oxford Bioinformatics(IF 6.931)!
Two papers accepted by Briefing in Bioinformatics(IF 13.9)!
I received the 2022 Outstanding Graduate Student award from the University of Georgia Department of Computer Science!
Publication
Hu, M., Guan, Z., Zeng, Y., Guo, J., Zhou, Z., Zhang, J., Jia, R., Vullikanti, A., Li, S. (2025) Mind Control through Causal Inference: Predicting Clean Images from Poisoned Data. ICLR 2025.
Hu, M., Guan, Z., Guo, J., Zhou, Z., Zhang, J., Li, S. (2025). BBCaL: Black-box Backdoor Detection under the Causality Lens. Transactions on Machine Learning Research
Zhang, J., Lan, M., Zhang, D., Chen, Z., Thapa, J., Pagán, J., Li, Y., Mai, G., Zhou, Z. (2025). SpaCE: a spatial counterfactual explainable deep learning model for predicting out-of-hospital cardiac arrest survival outcome. International Journal of Geographical Information Science.
Zhou, Q.*, Zhou, Z.*,Johnson, M., Ngo, M., Ferrari, F., Ma, J. (2025). ClinicalRAG: Automating Pharmaceutical Label Quality Control with Hierarchical RAG and Large Language Models. AAAi 2025
Zhou, Z.*, Zhang, J.*, Guan, Z., Hu, M., Lao, N., Mu, L., Li, S., Mai, G., (2024). Img2Loc: Revisiting Image Geolocalization using Multi-modality Foundation Models and Image-based Retrieval-Augmented Generation. SIGIR 2024.
Taujal, R., Gravel, N., Zhou, Z., Yeung, W., Kochut, K., & Kannan, N. (2024). Informatic challenges and advances in illuminating the druggable proteome. Drug Discovery Today, 103894.
Zhou, Z., Yeung, W., Soleymani, S., Gravel, N., Salcedo, M., Li, S., & Kannan, N. (2024). Using explainable machine learning to uncover the kinase-substrate interaction landscape. Bioinformatics, btae033.
Zhou, Z., Hu, M., Salcedo, M., Gravel, N., Yeung, W., Venkat, A., ... & Li, S. (2023). XAI meets Biology: A Comprehensive Review of Explainable AI in Bioinformatics Applications. arXiv preprint arXiv:2312.06082.
Shi, W.*, Zhou, Z.*, Letcher, B. H., Hitt, N., Kanno, Y., Futamura, R., ... & Li, S. (2023, November). Aging Contrast: A Contrastive Learning Framework for Fish Re-identification Across Seasons and Years. In Australasian Joint Conference on Artificial Intelligence (pp. 252-264). Singapore: Springer Nature Singapore.
Zhou, Z.*, Yeung, W.*, Soleymani, S.,Gravel, N., Salcedo, M., S., Li, S& Kannan, N. Explaining the blackbox - Unraveling Protein Language Model's Learning Mechanisms for Kinase-Specific Phosphorylation Prediction. ICML Workshop on Computational Biology (Spotlight)
Zhang, J., Zhang, D., Chen, Z., Zhou, Z., Mai, G., Mu, L. Identifying and Intervening in Key Predictors of Out-of-Hospital Cardiac Arrest Survival Outcome Using Explainable Artificial Intelligence. ICML 3rd Workshop on Interpretable Machine Learning in Healthcare
Zhang, J.*, Zhou, Z.*, Mai, G., Hu, M., Lan, M., and Li, S., Text2Seg: Remote Sensing Image Semantic Segmentation via Text-Guided Visual Foundation Models. (preprint)
Guan, Z.*, Hu M.*, Zhou, Z.*, Zhang, J., Li, S., Liu, N., BadSAM: Exploring Security Vulnerabilities of SAM via Backdoor Attacks. Proceedings of the AAAI Conference on Artificial Intelligence, 2023
Zhou, Z.*, Hitt, N., Letcher, B., Shi, W., and Li, S., Pigmentation-based Visual Learning for Salvelinus fontinalis Individual Re-identification. IEEE International Conference on Big Data (IEEE BigData), 2022.
Zhou, Z.*, Yeung, W.*, Gravel, N., Salcedo, M, S., Soleymani, S, Li, S& Kannan, N. Phosformer: An explainable Transformer model for protein kinase-specific phosphorylation prediction. Bioinformatics, 2023.
Yeung, W.*, Zhou, Z.*, Li, S. & Kannan, N. Alignment-free estimation of sequence conservation for identifying functional sites using protein sequence embeddings. Briefing in Bioinformatics, 2023(*co-first author)
Yeung, W.*, Zhou, Z.*, Li, S. & Kannan, N. (2022). Tree visualizations of protein sequence embedding space enable improved functional clustering of diverse protein superfamilies. Briefing in Bioinformatics, 2023(*co-first author)
Berger, B. M., Yeung, W., Goyal, A., Zhou, Z., Hildebrandt, E. R., Kannan, N., & Schmidt, W. K. (2022). Functional classification and validation of yeast prenylation motifs using machine learning and genetic reporters. PloS one, 17(6), e0270128.
Taujale, R.*, Zhou, Z.*, Yeung, W., Moremen, K. W., Li, S., & Kannan, N. (2021). Mapping the glycosyltransferase fold landscape using interpretable deep learning. Nature communications, 12(1), 1-12.(*co-first author)
Taujale, R., Venkat, A., Huang, L. C., Zhou, Z., Yeung, W., Rasheed, K. M., ... & Kannan, N. (2020). Deep evolutionary analysis reveals the design principles of fold A glycosyltransferases. Elife, 9, e54532.
Li, M., Zhang, J., Wu, B., Zhou, Z., & Xu, Y. (2018). Identifying Keystone Species in the Microbial Community Based on Cross-Sectional Data. Current gene therapy, 18(5), 296-306.
Work Experience
Senior Scientist, Merck & Co., Inc Feb 2024-present
Research Intern Microsoft Research May 2023-August 2023
Machine Learning Intern Norfolk Southern May 2022-August 2022
Data Scientist Intern BASF August 2021-March 2022
Front-end SDE Intern HIT August 2018-June 2019
Professional Service
ICCV 2023, CVPR 2021, IEEE TCSVT, IEEE CIM, Briefing in bioinformatics, Oxford bioinformatics, Frontiers of Computer Science, Plos One, Computational Biology and Chemistry Reviewer
AAAI 2023, AAAI 2024, SDM 2024, ECAI 2024 PC Member
Teaching Experience
Teaching assistant for CSCE 145 - Algorithmic Design I
Guest Lecturer for CSCI 3360 Data Science