Blog
Research and engineering notes on uncertainty quantification, risk-aware machine learning, and trustworthy AI from the Themis AI team.
-
Before AI Acts
Why trustworthy decision layers belong alongside model-level safety.
-
Quantifying Epistemic Uncertainty with the Laplace Approximation
Your trained model already knows what it doesn't know — it's hidden in the curvature of the loss landscape. The Laplace approximation extracts it, post hoc, with no retraining.
-
Spotting the Unfamiliar: Out-of-Distribution Detection with Uncertainty
Models fail most dangerously on inputs they've never seen. Epistemic uncertainty flags those out-of-distribution cases in real time — so the system can escalate, abstain, or adapt.
-
Managing Risk in Production AI Systems
Why production AI needs risk measurement, not just predictions — and how to turn a model's uncertainty into enforceable risk policies.
-
NIST's Risk Management Framework and Themis AI
Examining the Risk Management Framework by NIST.
-
Catching LLM Hallucinations with Uncertainty
LLMs fail without warning. A separate uncertainty estimate lets a model abstain, escalate, or defer instead of confidently making things up.
-
Drug Discovery Cost Reduction with Uncertainty-Guided Predictions
Drug Discovery Cost Reduction with Uncertainty-Guided Predictions
-
Uncertainty-Aware Human Intervention for Autonomous Vehicles
Uncertainty-Aware Human Intervention for Autonomous Vehicles.
-
Risk-Aware Selective Answering and Generative Models
Risk-Aware Selective Answering and Generative Models.
-
Uncertainty-Aware Language Modeling for Selective Question Answering
Presenting uncertainty-aware LLMs capable of estimating uncertainty with every prediction.
-
Probability vs Confidence
Why a model’s output probability is not always a reliable guide to whether its answer is correct.
-
Robust and Trustworthy Deep Learning (part 3): Themis AI
Themis AI's cutting-edge technological advancements in robust and trustworthy deep learning
-
Robust and Trustworthy Deep Learning (Part 2): Uncertainty
Themis AI's cutting-edge technological advancements in robust and trustworthy deep learning
-
Robust and Trustworthy Deep Learning (Part 1): Bias
Themis AI's cutting-edge technological advancements in robust and trustworthy deep learning
-
Preliminary Steps Towards Risk-Aware Image Generation
Using Capsa to automatically evaluate the quality of images generated by Stable Diffusion