Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols Paper • 2510.09462 • Published 8 days ago • 5
DISCO: Diversifying Sample Condensation for Efficient Model Evaluation Paper • 2510.07959 • Published 9 days ago • 14
DISCO: Diversifying Sample Condensation for Efficient Model Evaluation Paper • 2510.07959 • Published 9 days ago • 14 • 2
Diffusion Classifiers Understand Compositionality, but Conditions Apply Paper • 2505.17955 • Published May 23 • 22