Course Websites

Subject offerings of new and developing areas of knowledge in computer science intended to augment the existing curriculum. See Class Schedule or departmental course information for topics and prerequisites. Course Information: May be repeated in the same or separate terms if topics vary.

Generative and agentic AI has transformed NLP and established a new paradigm upon large language models (LLMs) for building autonomous agents that can interact, acquire, and process knowledge for humans. While LLMs like ChatGPT have created real buzz, our understanding of these large and complex models is limited: How does it work? What can it do? As LLMs can read, reason, and generate, can we use LLMs to automate daily tasks of knowledge acquisition, such as reading technical papers, browsing websites, checking emails, and teaching a subject? This class will take a laboratory and collaborative approach to understand and use agentic LLM by surveying the literature and doing research. Objective: Publishable survey/research papers. Format: Hands-on survey and research in small groups of 1-2 leads and 1-2 apprentices. Prerequisites: 1) Lead- Research experience in NLP/ML/DM (having published in ACL/EMNLP or similar venues) and 2) Collaborator/Apprentice: CS447 and strong CS background.