2 papers
cs.CL2024
Revisiting the Markov Property for Machine Translation
Cunxiao Du, Hao Zhou, Zhaopeng Tu +1
In this paper, we re-examine the Markov property in the context of neural machine translation. We design a Markov Autoregressive Transformer~(MAT) and undertake a comprehensive ass…
cs.CL2024
GliDe with a CaPE: A Low-Hassle Method to Accelerate Speculative Decoding
Cunxiao Du, Jing Jiang, Xu Yuanchen +8
Speculative decoding is a relatively new decoding framework that leverages small and efficient draft models to reduce the latency of LLMs. In this study, we introduce GliDe and CaP…