2 papers
cs.AI2026
Persona Vectors in Games: Measuring and Steering Strategies via Activation Vectors
Johnathan Sun, Andrew Zhang
Large language models (LLMs) are increasingly deployed as autonomous decision-makers in strategic settings, yet we have limited tools for understanding their high-level behavioral…
cs.AI2025
Does visualization help AI understand data?
Victoria R. Li, Johnathan Sun, Martin Wattenberg
Charts and graphs help people analyze data, but can they also be useful to AI systems? To investigate this question, we perform a series of experiments with two commercial vision-l…