Jaehyun Kim, Heesu Kim, et al.
Neurocomputing
Today's common practice in developing conversational agents is pipelining off-the-shelf modularized services as ready-made building blocks. However, the discrete and sequential nature of the modules yields long response latency. We introduce Sci-Fii, a speculative inference framework accelerating conversational agent systems built with off-the-shelf modules, while keeping the modules unchanged.
Jaehyun Kim, Heesu Kim, et al.
Neurocomputing
Jian Fang, Yvo T. B. Mulder, et al.
VLDB Journal
Jinho Lee, Jongwook Chung, et al.
IEEE Transactions on VLSI Systems
Hans-Jörg Vögel, Christian Sü, et al.
SEFAIAS 2018