Explore a cutting-edge approach to knowledge-intensive tasks in this 14-minute conference talk from SIGIR 2024. Delve into the concept of CorpusLM, a unified language model on corpus presented by authors Xiaoxi Li, Zhicheng Dou, Yujia Zhou, and Fangchao Liu. Learn how this innovative model combines large language models with search capabilities to enhance performance in complex information retrieval and processing tasks. Gain insights into the potential applications and implications of CorpusLM for advancing the field of natural language processing and information retrieval.