Xiaoqiang Lin

Xiaoqiang Lin, a Ph.D. student at the National University of Singapore and former Meta researcher, dives into the innovative REFRAG method for enhancing retrieval-augmented generation. He explains how REFRAG improves LLM inference speeds, making Time-To-First-Token 31x faster. The discussion also covers multi-granular chunk embeddings, performance trade-offs in compression, and the exciting future of agentic AI. Listeners will learn about the balance between data and architecture for long-context capabilities and the practical compute requirements for training.