Shalvi Mahajan's presentation on Retrieval-Augmented Generation (RAG) highlights a novel approach that merges information retrieval and natural language generation, enhancing performance across language applications.
Kevin Noel discusses the practical application of LLM in production settings, covering critical concepts such as Representation Learning, multi-task learning, and the distinctions between LM and LLM architectures.
Thejas Muralidhar Bhat and Naveen Rathani explore deploying numerous models for high-velocity data forecasting, focusing on conducting micro-level forecasts for operational data at Wells Fargo.
Collection
[
|
...
]