Technical Reports - 2025
Vulnerabilities of Language Models (EECS-2025-8)
Eric Wallace
The Free Termination Property of Queries Over Time (EECS-2025-7)
Conor Power, Paraschos Koutris and Joseph M. Hellerstein
Towards Principled Training and Serving of Large Language Models (EECS-2025-6)
Banghua Zhu
System Architecture for Agentic Large Language Models (EECS-2025-5)
Tianjun Zhang
Structured Representations for Goal-Directed Decision Making (EECS-2025-2)
Vivek Myers
The Alignment Problem Under Partial Observability (EECS-2025-1)
Scott Emmons