Title: Towards Domain Adaptation, Interpretability, and Deployment in Large Language Models
Speaker: Vinamra Benara
Advisor: Ion Stoica
Date: Thursday, June 18th, 2026
Time: 12:30 PM to 1:30 PM (Pacific Time)
This is a virtual event held over google meet.
Abstract: This talk presents contributions toward domain adaptation, interpretability, and deployment in large language models. I will discuss how retrieval augmented generation and fine tuning can incorporate specialized knowledge, how question-answering can be used to generate more interpretable embeddings for scientific domains, and how LLM systems can be deployed for practical real world use.