Publications

Bayesian Experimental Design via Score Matching

Angus Phillips, Gavin Kerrigan, Tom Rainforth

• UAI
• arXiv
• Code

EventFlow: Forecasting Temporal Point Processes with Flow Matching

Gavin Kerrigan, Kai Nelson, Padhraic Smyth

• AISTATS
• Best Paper Award
• arXiv
• Code
• Press

A Geometric Approach to Optimal Experimental Design

Gavin Kerrigan, Christian A. Naesseth, Tom Rainforth

• AISTATS
• arXiv
• Code

Scaling Bayesian Experimental Design to High-Dimensions with Information-Guided Diffusion

Adhi Saravanan, Rik Knowles, Gavin Kerrigan, Tom Rainforth

• ICLR
• Publication

Guided Diffusion Sampling on Function Spaces with Applications to PDEs

Jiachen Yao, Abbas Mammadov, Julius Berner, Gavin Kerrigan, Jong Chul Ye, Kamyar Azizzadenesheli, Anima Anandkumar

• NeurIPS
• arXiv
• Code

A Generative Diffusion Model for Probabilistic Ensembles of Precipitation Maps Conditioned on Multisensor Satellite Observations

Clement Guilloteau, Gavin Kerrigan, Kai Nelson, Giosue Migliorini, Padhraic Smyth, Runze Li, Efi Foufoula-Georgiou

• IEEE TGRS
• Publication
• arXiv

Dynamic Conditional Optimal Transport through Simulation-Free Flows

Gavin Kerrigan, Giosue Migliorini, Padhraic Smyth

• NeurIPS
• arXiv
• Code

Precipitation Downscaling with Spatiotemporal Video Diffusion

Prakhar Srivastava, Ruihan Yang, Gavin Kerrigan, Gideon Dresdner, Jeremy McGibbon, Christopher Bretherton, Stephan Mandt

• NeurIPS
• arXiv

Functional Flow Matching

Gavin Kerrigan, Giosue Migliorini, Padhraic Smyth

• AISTATS
• Outstanding Student Paper Highlight Award
• Publication
• arXiv
• Code

Diffusion Generative Models in Infinite Dimensions

Gavin Kerrigan, Justin Ley, Padhraic Smyth

• AISTATS
• Publication
• arXiv
• Code

Bayesian Modeling of Human-AI Complementarity

Mark Steyvers, Heliodoro Tejeda, Gavin Kerrigan, Padhraic Smyth

• PNAS
• Publication
• Code
• Blog
• Press

Combining Human Predictions with Model Probabilities via Confusion Matrices and Calibration

Gavin Kerrigan, Padhraic Smyth, Mark Steyvers

• NeurIPS
• Publication
• arXiv
• Code

Differentially Private Language Models Benefit from Public Pre-Training

Gavin Kerrigan*, Dylan Slack*, Jens Tuyls*

• PrivateNLP Workshop at EMNLP
• Publication
• arXiv
• Code