Short Course: An Overview of LLMs for Statisticians: Foundations, Reasoning, and Agentic AI

B17. Short Course: An Overview of LLMs for Statisticians: Foundations, Reasoning, and Agentic AI The Department of Statistics presents, 'An Overview of LLMs for Statisticians: Foundations, Reasoning, and Agentic AI', a short course taught by Linjun Zhang, Associate Professor in the Department of Statistics and an affiliated faculty member in Computer Science at Rutgers University Date/Time: November 6, 2026 9:00 a.m.–5:00 p.m. Lunch break: 12:00–1:30 p.m. Location: 1957 E Street NW, B17 Description: This short course provides an overview of the foundations and frontiers of modern large language models (LLMs), with an emphasis on topics relevant to statisticians and data scientists. We will begin with the basic principles underlying embeddings, transformers, and the LLM training pipeline, including pretraining, parameter-efficient fine-tuning, and reinforcement learning from human feedback. Building on these foundations, we will discuss recent developments in reasoning models and agentic AI, including context engineering, harness engineering, and the design of AI agents for complex tasks. We will also discuss key issues in AI safety, reliability, and evaluation. The short course will combine conceptual foundations with practical examples and hands-on activities, with the goal of helping participants understand, use, and critically evaluate modern AI systems. Short Bio: Linjun Zhang is an Associate Professor in the Department of Statistics and an affiliated faculty member in Computer Science at Rutgers University. He received his Ph.D. in Statistics from the Wharton School at the University of Pennsylvania in 2019, where he received the J. Parker Bursk Memorial Prize and the Donald S. Murray Prize for excellence in research and teaching, respectively. He is a recipient of the NSF CAREER Award, the Rutgers Presidential Teaching Award in 2024, and the Warren I. Susman Award for Excellence in Teaching in 2025. His current research interests include the statistical foundations of large language models, algorithmic fairness, privacy-preserving data analysis, and deep learning theory. Registration: Please go here to register. Participant Support: A limited number of NSF-funded participant support awards of up to $200 will be available to eligible participants. Awards will be provided following confirmed attendance at the full short course and are subject to NSF and GW eligibility requirements and availability of funds