☰

Padhraic Smyth

Distinguished Professor
Hasso Plattner Endowed Chair in Artificial Intelligence
Department of Computer Science (vice-chair)
Department of Statistics
School of Information and Computer Sciences
University of California, Irvine

Research Interests: machine learning, artificial intelligence, pattern recognition, statistics

Affiliations (at UCI)

• Faculty Member and Founding Director, Center for Machine Learning and Intelligent Systems
• Faculty Director, UCI Machine Learning Repository
• Co-Director, HPI Research Center in Machine Learning and Data Science at UCI
• Faculty Affiliate, UCI AI in Science Institute
• Faculty Affiliate, UCI Steckler Center for Responsible, Ethical, and Accessible Technology (CREATe)
• Faculty Affiliate, UCI Connected Learning Lab (CLL)

Selected Recent Papers

• From 'may' to 'is': certainty distortion in language model rewriting
  with Catarina Belem, Shang Wu, et al., Empirical Methods in Natural Language Processing Conference (EMNLP), 2026
• How AI assistance affects human skill development: a study of learning with logic puzzles
  with Shang Wu, Catarina Belem, et al., ACM Conference on Human-AI Complementarity and Alignment (HCOMP), 2026
• Beyond accuracy: are time series foundation models well-calibrated?
  with Coen Adler, Yuxin Chang, Felix Draxler, Samar Abdi, International Conference on Learning Representations (ICLR), 2026
• EventFlow: forecasting temporal point processes with flow matching
  with Gavin Kerrigan and Kai Nelson, 29th International Conference on AI and Statistics (Best Paper Award), 2026
• Deep continuous-time state-space models for marked event sequences
  with Yuxin Chang, Alex Boyd, Andy Warrington, 39th Neural Information Processing Systems Conference, 2025
  
• Bayesian inference for correlated human experts and classifiers
  with Markelle Kelly, Alex Boyd, Sam Showalter, and Mark Steyvers, International Conference on Machine Learning (ICML), 2025
  
• What large language models know and what people think they know
  with Mark Steyvers, Helio Tejeda, Aakriti Kumar, Catarina Belem, et al, Nature Machine Intelligence, 2025
• A generative diffusion model for probabilistic ensembles of precipitation maps conditioned on multisensor satellite observations
  with Clement Guilloteau, Gavin Kerrigan, et al IEEE Transactions on Geoscience and Remote Sensing, 2025
• Perceptions of linguistic uncertainty by language models and humans
  with Catarina Belem, Markelle Kelly, Mark Steyvers, and Sameer Singh, Proceedings of the 2024 Empirical Methods in Natural Language Processing Conference (EMNLP), 2024
• Bayesian modeling of human-AI complementarity
  with Mark Steyvers, Heliodoro Tejeda, and Gavin Kerrigan, Proceedings of the National Academy of Sciences, 2022

Teaching

• CS 274A, Probabilistic Learning
• CS 175, Project in Artificial Intelligence
• CS 178, Machine Learning and Data Mining (link available to UCI students via Canvas)
• Stats 5, Seminar in Data Science
• Stats 170A/B, Capstone Project in Data Science