no code implementations • 13 Mar 2024 • Jia-Nan Li, Quan Tu, Cunli Mao, Zhengtao Yu, Ji-Rong Wen, Rui Yan
Accordingly, we introduce StreamingDialogue, which compresses long dialogue history into conv-attn sinks with minimal losses, and thus reduces computational complexity quadratically with the number of sinks (i. e., the number of utterances).
