Stephan Mandt
Biography
Stephan Mandt, Ph.D., is a Professor in the Department of Computer Science and Department of Statistics (by courtesy) at the University of California, Irvine. He also serves as Associate Director of the AI in Science Institute at UC Irvine and as Principal Investigator and AI Resident at the Chan Zuckerberg Initiative. Mandt's research focuses on deep generative models and neural data compression, with applications spanning climate science, thermodynamics, and scientific computing. He received his Ph.D. in Theoretical Physics from the University of Cologne in 2012, followed by postdoctoral positions at Princeton University and Columbia University, where he worked with David Blei. Before joining UC Irvine in 2018, he served as Head of the Machine Learning group at Disney Research.
Mandt has received the NSF CAREER Award and was named a Chan Zuckerberg Investigator in 2024. He received the NeurIPS Outstanding Paper Award in 2023 and was selected as a Kavli Fellow by the National Academy of Sciences in 2019. His work has been recognized with the Dean's Mid-Career Award for Excellence in Research at UC Irvine and the Qualcomm Faculty Award. He is a Mercator Fellow of the German Research Foundation and was previously a National Merit Scholar of Germany. Mandt holds nine U.S. patents and has published over 60 peer-reviewed conference papers at venues including NeurIPS, ICML, ICLR, and CVPR.
Mandt served as Program Chair of AISTATS 2024 and General Chair of AISTATS 2025, overseeing conferences with over 2,500 submissions and 1,000 attendees. He is a founding member of the Symposium on Advances in Approximate Bayesian Inference, which he organized from 2015 to 2017 and has advised since 2018. He serves as Action Editor for the Journal of Machine Learning Research and Transactions on Machine Learning Research, and has held Senior Area Chair positions at NeurIPS and ICLR. At UC Irvine, he co-directs the Hasso Plattner Institute and has mentored numerous postdoctoral researchers, Ph.D. students, and visiting scholars who have gone on to faculty positions and research roles at institutions including the University of Tübingen, TU Kaiserslautern, ETH Zürich, and Imperial College London.
Return to topEducation
- Ph.D. in Theoretical Physics, University of Cologne, Germany, 2012
- M.S. in Physics, University of Cologne, Germany, 2008
- B.S. in Physics, University of Cologne, Germany, 2008
Distinctions
- Chan Zuckerberg Investigator, 2024
- Mercator Fellow, German Research Foundation (DFG), 2022
- NeurIPS Outstanding Paper Award, Datasets and Benchmark Track, 2023
- Kavli Fellow, Frontiers of Science Program, National Academy of Sciences, 2019
- NSF CAREER Award, National Science Foundation, 2021
- Princeton Center for Complex Materials Postdoctoral Fellow, Princeton University, 2012
- National Merit Scholar of Germany (Studienstiftler, top 0.5% of university students), 2010
- Best Paper Award, ICLR Workshop on Uncertainty in Foundation Models, 2025
- Best Student Paper Award, Symposium on Advances in Approximate Bayesian Inference, 2019
- Qualcomm Faculty Award, 2022
Areas of Expertise
- Machine Learning
- Variational Inference Methods
- Neural Data Compression
- Stochastic Gradient Algorithms
- Diffusion Generative Models
- Climate Downscaling Applications
- Uncertainty Quantification
Recent Publications
- Hoffmann M., Specht T., Gottl Q., Burger J., Mandt S., Hasse H., Jirasek F., “Thermodynamically consistent machine learning model for excess Gibbs energy” (opens in new tab), Nature Communications, vol. 17, 2026.
- K. Pandey, F. Sofian, F. Draxler, T. Karaletsos, S. Mandt, “Variational Control for Guidance in Diffusion Models”, Proceedings of the International Conference on Machine Learning (ICML), vol. 267, pp. 47755–47780, 2025.
- M. Jazbec, E. Wong-Toi, G. Xia, D. Zhang, E. Nalisnick, S. Mandt, “Generative Uncertainty in Diffusion Models”, Proceedings of the International Conference on Uncertainty in Artificial Intelligence (UAI), vol. 286, pp. 1837–1858, 2025.
- D. Le, T. Pham, S. Lee, C. Clark, A. Kembhavi, S. Mandt, R. Krishna, J. Lu, “One Diffusion to Generate Them All” (opens in new tab), Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2671–2682, 2025.
- Y. Yang, J. Will, S. Mandt, “Progressive Compression with Universally Quantized Diffusion Models”, 13th International Conference on Learning Representations Iclr 2025, pp. 27254-27275, 2025.
- K. Pandey, J. Pathak, Y. Xu, S. Mandt, M. Pritchard, A. Vahdat, M. Mardani, “Heavy-Tailed Diffusion Models”, 13th International Conference on Learning Representations Iclr 2025, pp. 82578-82632, 2025.
- T. Truong, R. Sudharsan, Y. Yang, P. Ma, R. Yang, S. Mandt, J. Bloom, “AstroCompress: A benchmark dataset for multi-purpose compression of astronomical data”, 13th International Conference on Learning Representations Iclr 2025, pp. 52287-52311, 2025.
Most Cited Publications
- C. Zhang, J. Bütepage, H. Kjellström, S. Mandt, “Advances in Variational Inference” (opens in new tab), IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 41, pp. 41, 2018.
- S. Mandt, H. Hoffman, D. Blei, “Stochastic Gradient Descent as Approximate Bayesian Inference”, Journal of Machine Learning Research, vol. 18, pp. 1–35, 2017.
- R. Yang, P. Srivastava, S. Mandt, “Diffusion Probabilistic Modeling for Video Generation” (opens in new tab), Entropy, vol. 25, pp. 1469, 2023.
- V Fortuin, D Baranchuk, G Rätsch, S Mandt, “GP-VAE: Deep Probabilistic Time Series Imputation”, Artificial Intelligence and Statistics (AISTATS), 2020.
- R Bamler, S Mandt, “Dynamic Word Embeddings”, International Conference on Machine Learning 70, 380-389, 2017.
- Y. Li, S. Mandt, “Disentangled Sequential Autoencoder”, International Conference on Machine Learning 80, 5670-5679, 2018.
- R. Yang, S. Mandt, “Lossy image compression with conditional diffusion models”, Thirty-seventh Conference on Neural Information Processing Systems, 2013.
- Y Yang, S Mandt, L Theis, “An introduction to neural data compression”, Foundations and Trends in Computer Graphics and Vision 15 (2), 113-200, 2023.
Contact Information
Website: https://www.stephanmandt.com
Email: mandt@uci.edu
Address: 4228 Bren Hall
Return to topThis profile was created with the help of AI.
Last updated on 6/2/2026.