As large language models (LLMs) proliferate, understanding their emergent behaviors remains a central challenge. This talk proposes a framework for interpreting LLM behavior through the lens of geometry. We argue that the structure of an LLM’s internal semantic space—the high-dimensional arrangement of concepts—serves as a…
As part of the 25th anniversary of the Liechtenstein Institute on Self-Determination (LISD), the university community and members of the public are invited to join an international colloquium on the Global Food and Water Security Project as well as advanced techniques in agriculture, forestry, and water stewardship.
In an era of constrained federal research funding and global economic competition, U.S. states are increasingly on the front lines of industrial strategy. New Jersey and New York, home to world-class universities, major industries, and diverse workforces, must adapt to ensure long-term innovation, job growth, and resilience…
Far and away the most prominent and practically influential approach to AI ethics to date is the paradigm of algorithmic fairness. Machine learning applied in high stakes contexts is an epistemic activity, aimed at inference over real world data and hence real world systems. The paradigm of ML fairness is a second-order…
