Overview
Speaker: Sagar Sharma
Date: Friday, November 6, 2026, 2:30 PM
Room: PM103
Large Language Models (LLMs) face significant challenges in continuously acquiring new information, preserving existing knowledge, and reasoning across multiple sources. Although traditional Retrieval-Augmented Generation (RAG) enables LLMs to access external knowledge, it remains limited in associative reasoning, knowledge integration, and long-term memory management.
Recent advances in non-parametric continual learning have introduced promising approaches that combine advanced retrieval mechanisms, knowledge graph-based reasoning, and dynamic memory architectures. These methods aim to enable LLMs to establish meaningful connections across information, adapt to evolving knowledge, and maintain persistent, context-aware memory without requiring frequent model retraining.
The talk discusses these emerging approaches, focusing on three representative papers.