Training Diffusion Language Models for Black-Box Optimization Paper • 2603.17919 • Published May 29 • 15
QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents Paper • 2605.27068 • Published May 26 • 24
LLM Safety From Within: Detecting Harmful Content with Internal Representations Paper • 2604.18519 • Published Apr 20 • 26