3 papers
cs.LG2026
VFUSE: Virulent Feature Understanding with Sparse autoEncoders
Michael Yu, Matthew L. Olson
Generative models have shown remarkable progress in a variety of domains such as protein design, but such power enables the opaque generation of hazardous proteins. In this work, w…
cs.LG2026
Data-Centric Interpretability for LLM-based Multi-Agent Reinforcement Learning
John Yan, Michael Yu, Yuqi Sun +3
Large language models (LLMs) are increasingly trained in complex Reinforcement Learning, multi-agent environments, making it difficult to understand how behavior changes over train…
cs.AI2025
Multi-Agent Data Visualization and Narrative Generation
Anton Wolter, Georgios Vidalakis, Michael Yu +2
Recent advancements in the field of AI agents have impacted the way we work, enabling greater automation and collaboration between humans and agents. In the data visualization fiel…