Talks
Invited Talks
Building and Evaluating AI Systems for New Post-Deployment Tasks and Distributions
Benchmarks to Bedside: Opportunities and Challenges in Evaluating AI's Clinical Utility
School of Data Science Colloquium, University of Virginia, 2025
What Benchmarks Really Measure: From Methods to Models in AI Evaluation
Princeton University, 2026
Microsoft Research (NYC), 2025
AI 101
Schmidt Sciences, 2025
Measurement to Meaning
MIT LIDS Postdoc Nexus Meeting, MIT, 2025
Hitting the Wrong Target: Are Domain Generalization Benchmarks with Accuracy on the Line Misspecified?
Hitting the Right Target: From AI in the Lab to AI in the Real World
Computer Science and Engineering Seminar, Georgia Institute of Technology, 2025
Tandon College of Engineering Faculty First Look Program, New York University, 2025
Clued-in to Clueless: Navigating Distribution Shifts with Varying Levels of Target Distribution Information
Computer Science Seminar, Texas State University, 2024
Towards Externally Valid Evaluation of AI Systems
MobiliT.AI Forum, 2024
Denoising fMRI via Probabilistic Graphical Model Augmentation of ICA-AROMA
Contributed Talks
On (using benchmarks for) Evaluating Methods vs. Evaluating Models
Workshop on Evaluating the Evolving LLM Lifecycle: Benchmarks, Emergent Abilities, and Scaling @ Conference on Neural Information Processing Systems (NeurIPS), 2025 — Oral Presentation
Hitting the Wrong Target: Are Domain Generalization Benchmarks with Accuracy on the Line Misspecified?
On Domain Generalization Datasets as Proxy Benchmarks for Causal Representation Learning
Workshop on Causal Representation Learning (CRL) @ Conference on Neural Information Processing Systems (NeurIPS), 2024 — Oral Presentation
Learning Domain General Predictors
Separating Neural Encoding and Decoding Pathways in fMRI by Disentangling Causal and Anticausal Mechanisms
University of Illinois at Urbana-Champaign Miniature Brain Machinery Retreat, 2022
Denoising fMRI via Probabilistic Graphical Model Augmentation of ICA-AROMA
University of Illinois at Urbana-Champaign Miniature Brain Machinery Retreat, 2022
University of Illinois at Urbana-Champaign Miniature Brain Machinery Retreat, 2021
Automated Incorporation of Machine Learning (AIM)
Sandia National Laboratories MARTIANS End of Summer Symposia, 2020
Interpretable Recurrent Convolutional Neural Networks for Cyber Alert Triaging
Sandia National Laboratories MARTIANS End of Summer Symposia, 2019
No matching items