2026
Precision Health Initiative
The Illusion of Transparency: Explainability and Safety in Healthcare
Precision Health Initiative seminar at UVA, 2026
2026
AIxHealth Seminar
The Illusion of Transparency: Explainability and Safety in Healthcare
AIxHealth Seminar, GeorgiaTech, 2026
2026
ECE Distinguished Colloquium
Talk at the Charles L. and Ann Brown Distinguished Colloquium series
ECE Department, University of Virginia, 2026
2025
2025
FAR.AI Alignment Workshop
Polarity-Aware Probing for Quantifying Latent Alignment in Language Models
FAR.AI Alignment Workshop, 2025
2025
UMass Lowell CS Colloquia
Reasoning and Safety in Multilingual and Multimodal LLMs
Computer Science Colloquia, University of Massachusetts Lowell, 2025
2025
2024
FAR.AI Alignment Workshop
The (Un)Reliability of Chain-of-Thought Reasoning
FAR.AI Alignment Workshop, 2024
2024
IDEAL Chicago
Invited talk at Privacy and Interpretability in Generative AI workshop
IDEAL Chicago, 2024
2023
Computer Vision Talks
On the Impact of Estimating Example Difficulty
Computer Vision Talks, 2023
2022
TrustML Young Scientist Seminar
On the Impact of Estimating Example Difficulty
TrustML Young Scientist Seminar, 2022
2020
Weights & Biases
Detecting Out-of-Distribution Data with Variance-of-Gradient
Weights and Biases Deep Learning Salon, 2020