Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Lu, Songshuo"'
Current Retrieval-Augmented Generation (RAG) systems concatenate and process numerous retrieved document chunks for prefill which requires a large volume of computation, therefore leading to significant latency in time-to-first-token (TTFT). To reduc
Externí odkaz:
http://arxiv.org/abs/2410.07590
We present a generative dialogue system capable of operating in a full-duplex manner, allowing for seamless interaction. It is based on a large language model (LLM) carefully aligned to be aware of a perception module, a motor function module, and th
Externí odkaz:
http://arxiv.org/abs/2405.19487