Conference Program
The Open SkAI Conference will take place from Tuesday, September 2–Friday, September 5, 2025. It will be located in downtown Chicago, IL at the SkAI Hub.
*More details will be added to the schedule as they become available.*
For a complete list of conference talk titles and abstracts, click here.
For a complete list of conference poster titles and abstracts, click here.
Tuesday, September 2
| Time (CT) | Session | Location |
|---|---|---|
| 8:00–9:30 a.m. | Breakfast and registration (for tutorial participants and volunteers) | Reception/lobby |
| 9:30–10:30 a.m. | Tutorials—“Scientific AI at Scale: Architectures and Distributed Training”—AI for science is accelerating as a data-and-model revolution takes hold, with advances in deep learning and foundation models showing that scale unlocks discovery, while translating those gains into scientific value still requires domain-specific design and customization. This tutorial will survey the major modeling architectures and learning approaches used for scientific datasets and tasks, and cover scalable training strategies, including data, model, and pipeline parallelism and distributed I/O, enabling efficient training on leadership-class systems at Argonne’s ALCF. | |
| 10:30–11:00 a.m. | Coffee break & poster set up | |
| 11:00 a.m.–12:00 p.m. | Tutorials—“Scientific AI at Scale: Architectures and Distributed Training” (cont.) | |
| 12:00–1:00 p.m. | Lunch (for tutorial participants) | |
| 1:00–1:30 p.m. | Opening | Auditorium and Zoom |
| 1:30–2:30 p.m. | Plenary 1 • Federica Bianco, University of Delaware—TBD | Auditorium and Zoom |
| 2:30–3:00 p.m. | Poster lightning talks | Auditorium and Zoom |
| 3:00–4:00 p.m. | Coffee break @ posters | SkAI Hub area |
| 4:00–5:20 p.m. | Inference and uncertainty quantification for large and complex data 1 • Ved Shah, Northwestern University—“ORACLE: A Real-Time, Hierarchical, Deep-Learning Photometric Classifier for the LSST” • Hyosun Park, Yonsei University—“Transformer-based Reduction of PSF Effect and Correlated Noise for Precision Dark Matter Mapping” • Georgios Valogiannis, The University of Chicago—“Saturating Cosmological Information with AI: Field-Level Inference and Beyond” • Shubhendu Trivedi, Fermilab—“Conformal Hierarchical Simulation-based Inference with Local Validity” • Patricia Iglesias-Navarro, Institute of Astrophysics of the Canary Islands—“Simulation-based inference of galaxy properties from JWST pixels” | Auditorium and Zoom |
| 5:20–5:30 p.m. | Day 1 wrap-up: Introduction to Discovery Engine crowdsourcing ideas, glossary, community norms | Auditorium and Zoom |
Wednesday, September 3
| Time (CT) | Session | Location |
|---|---|---|
| 8:00–9:00 a.m. | Breakfast and registration | Kitchen-dining area |
| 9:00–10:00 a.m. | Plenary 2 • George Karniadakis, Brown University—TBD | Auditorium and Zoom |
| 10:00–10:30 a.m. | Coffee break @ posters | SkAI Hub area |
| 10:30 a.m.–12:00 p.m. | Physics-informed architectures, interpretability, and ethics 1 • Invited speaker: Chenhao Tan, The University of Chicago—TBD • Manuel Ballester Matito, Northwestern University—“Accelerating Stellar Structure Modeling with Neural PDE Solvers” • Matt Ho, Columbia University—“Learning the Universe: Building a Scalable, Verifiable Emulation Pipeline for Astronomical Survey Science” • Laura Trouille, Adler Planetarium, Zooniverse—“Zooniverse and SkAI: Human-AI Collaboration for Scalable Scientific Discovery” | Auditorium and Zoom |
| 12:00–1:30 p.m. | Lunch/mentoring time | Kitchen-dining area |
| 1:30–2:50 p.m. | Generative AI for scientific data analysis and simulations 1 • Jiezhong Wu, Northwestern University—“A foundation AI model to infer the physics of transients” • Shunyuan Mao, Rice University—“Multi-resolution neural representation for self-supervised image reconstruction in radio interferometry” • Bin Xia, Georgia Tech and Argonne National Laboratory—“Towards a Generalizable Multi-Modal Foundation Model for Astrophysical Data” • Supranta Boruah, University of Pennsylvania—“Generative machine learning solutions for weak lensing mass mapping” • Tianao Li, Northwestern University—“Probabilistic Imaging of Galaxies for Weak Gravitational Lensing” | Auditorium and Zoom |
| 2:50–3:15 p.m. | Coffee break @ posters | SkAI Hub area |
| 3:15–4:15 p.m. | Poster session 1 | SkAI Hub area |
| 4:15–5:15 p.m. | Inference and uncertainty quantification for large and complex data 2 • Invited speaker: Rachel Mandelbaum, Carnegie Mellon University—TBD • Matiwos Mebratu, Stanford University—“Hybrid Prior Wavelet based Conditional Flow Matching Model (HyWave-CFM)” | Auditorium and Zoom |
| 5:15–5:30 p.m. | Day 2 wrap-up: Discovery Engine idea updates, glossary | Auditorium and Zoom |
Thursday, September 4
| Time (CT) | Session | Location |
|---|---|---|
| 8:00–9:00 a.m. | Breakfast and registration | Kitchen-dining area |
| 9:00–10:30 a.m. | Generative AI for scientific data analysis and simulations 2 • Invited speaker: Fei Sha, Google Research—“Advances in Probabilistic Generative Modeling for Scientific Machine Learning” • Hong-Yu Chen, Northwestern University—“StarEmbed-GPT: a foundation model for general-purpose inference on variable stars” • Keiya Hirashima, RIKEN Center for Interdisciplinary Theoretical and Mathematical Sciences—“Star-by-star Galaxy Simulations Accelerated by Surrogate Modeling for Supernova Feedback” • Tri Nguyen, Northwestern University—“Generating Halo Merger Trees with Graph Generative Models” | Auditorium and Zoom |
| 10:30–11:00 a.m. | Coffee break @ posters | SkAI Hub area |
| 11:00 a.m.–12:05 p.m. | Physics-informed architectures, interpretability, and ethics 2 • Peter Melchior, Princeton University—“Optimizing Instrument Utilization and Survey Designs with Structured Learning” • Amanda Wasserman, University of Illinois Urbana-Champaign—“Improving Supernova Cosmology with Active Learning Follow-up” • Aayush Saxena, University of Oxford—“Using Deep Learning to classify high-redshift galaxy spectra from JWST: uncovering exciting galaxy populations through AI” • Aritra Ghosh, University of Washington—“Harnessing ML & Large Surveys to Probe Galaxy Evolution: from HSC Size-Environment Correlations to Rubin Unsupervised Discovery” | Auditorium and Zoom |
| 12:05–12:30 p.m. | Poster lightning talks | Auditorium and Zoom |
| 12:30–2:00 p.m. | Mentoring lunch | Kitchen-dining area |
| 2:00–3:30 p.m. | Inference and uncertainty quantification for large and complex data 3 • Invited speaker: Matteo Sesia, University of Southern California—TBD • Alex Gagliano, Massachusetts Institute of Technology—“Mixture-of-Expert Variational Autoencoders for Multi-Modal Embedding of Supernova Data” • Liren Shan, Toyota Technological Institute at Chicago—“Volume Optimality in Conformal Prediction with Structured Prediction Sets” • Sreevani Jarugula, Fermilab—“Cosmology constraints from Strong Gravitational Lensing using Neural Ratio Estimation” | Auditorium and Zoom |
| 3:30–3:45 p.m. | Wrap-up: Conference photo | Auditorium and Zoom |
| 3:45–4:15 p.m. | Coffee break @ posters | SkAI Hub area |
| 4:15–5:15 p.m. | Poster session 2 | SkAI Hub area |
| 5:30–7:30 p.m. | Optional reception: Closing happy hour at CloudBar at 360 CHICAGO (top of the Hancock Center) | Top of Hancock Center |
Friday, September 5
| Time (CT) | Session | Location |
|---|---|---|
| 8:00–9:00 a.m. | Breakfast and registration | Kitchen-dining area |
| 9:00–10:35 a.m. | Physics-informed architectures, interpretability, and ethics 3 • Helen Qu, Flatiron Institute—“An Astrophysical Case Study in Robustness” • Akraprabha Ganguli, Argonne National Laboratory—“Enhancing interpretability in generative modeling: statistically disentangled latent spaces guided by generative factors in scientific datasets” • Adrian Bayer, Flatiron Institute/Princeton University—“Optimal, Interpretable, and Robust Cosmological Inference of the Multimodal Sky” • Daniel Anglés-Alcázar, University of Connecticut—“Cosmology and Astrophysics with MachinE Learning Simulations (CAMELS) to model the impact of baryonic physics on cosmological structure formation” • Nolan Smyth, University of Montreal—“Towards the automated discovery of differential equations in (astro)-physics” • Jack O'Brien, University of Illinois Urbana-Champaign—“Physics Informed Latent Space in Foundation Models of Transients” | Auditorium and Zoom |
| 10:35–11:00 a.m. | Coffee break @ posters | SkAI Hub area |
| 11:00 a.m.–12:35 p.m. | Inference and uncertainty quantification for large and complex data 4 • Jimena González, University of Wisconsin–Madison—“Does Machine Learning Work? A Comparative Analysis of Strong Gravitational Lens Searches in the Dark Energy Survey” • Anirban Bairagi, Institut d'Astrophysique de Paris—“PatchNet: GPU and Simulation is not the limitation anymore for Cosmological field-level inference” • Yuanyuan Zhang, NSF NOIRLab—“Lessons Learned from a Simulation-Based Inference Approach for Galaxy Cluster Abundance Cosmological Analysis” • Samuel Dyson, The University of Chicago—“Uncertainty Quantification in Time-Series Coincidence Detections” • Lindsay House, SkAI Institute—“Harnessing AI and Citizen Science to Improve Our Understanding of Dark Energy” • Ana Sofia Uzsoy, Harvard University—“Bayesian Component Separation for DESI LAE Automated Spectroscopic Redshifts and Photometric Targeting” | Auditorium and Zoom |
| 12:35–1:00 p.m. | Closing: Wrap-up, Discovery Engine, synthesis | Auditorium and Zoom |
| 1:00–2:00 p.m. | Lunch | Kitchen-dining area |
The SkAI Institute is one of the National Artificial Intelligence Research Institutes funded by the U.S. National Science Foundation and Simons Foundation. Information on National AI Institutes is available at aiinstitutes.org.
