The team's automated reasoning research aims to build algorithms that allow computers to perform logical reasoning. The output of these algorithms is traditionally binary: satisfiable or unsatisfiable ...

While beating an AI at a board game may seem relatively trivial, it can help us identify failure modes of the AI, or ways in which we can improve their training to avoid having them develop these ...

More than a century before quantum mechanics was born, Irish mathematician William Rowan Hamilton stumbled onto an idea that would quietly foreshadow one of the deepest truths in physics. While ...

Abstract: Temporal knowledge graphs (TKGs) effectively capture the dynamic evolution of events over time, emerging as a critical driving force in the advancement of artificial intelligence. In recent ...

Large Language Models (LLMs) have advanced in mathematical reasoning but still struggle with precise computation and symbolic manipulation. THOR (Tool-Integrated Hierarchical Optimization via RL) ...

In this work, we investigate data–student suitability in reasoning distillation and introduce Rank-Surprisal Ratio (RSR), a simple yet effective metric for identifying suitable reasoning trajectories ...

Abstract: Analog/mixed-signal circuits are key for interfacing electronics with the physical world. Their design, however, remains a largely handcrafted process, resulting in long and error-prone ...