3 papers
cs.AI2026
Demonstrating Generalization Failures via Mixtures of Conditional Policies
Jou Barzdukas, Jack Peck, Julian Schulz +3
Post-training of frontier language models is conducted on curated task suites, and inevitably leaves a distribution shift between training and deployment environments. This exposes…
cs.LG2025
A Concrete Roadmap towards Safety Cases based on Chain-of-Thought Monitoring
Julian Schulz
As AI systems approach dangerous capability levels where inability safety cases become insufficient, we need alternative approaches to ensure safety. This paper presents a roadmap…
cs.LG2025
Automated Feature Labeling with Token-Space Gradient Descent
Julian Schulz, Seamus Fallows
We present a novel approach to feature labeling using gradient descent in token-space. While existing methods typically use language models to generate hypotheses about feature mea…