May 23, 2022, 1:12 a.m. | Tao Ge, Heming Xia, Xin Sun, Si-Qing Chen, Furu Wei

cs.CL updates on arXiv.org arxiv.org

We study lossless acceleration for seq2seq generation with a novel decoding
algorithm -- Aggressive Decoding. Unlike the previous efforts (e.g.,
non-autoregressive decoding) speeding up seq2seq generation at the cost of
quality loss, our approach aims to yield the identical (or better) generation
compared with autoregressive decoding but in a significant speedup, achieved by
innovative cooperation of aggressive decoding and verification that are both
efficient due to parallel computing.


We propose two Aggressive Decoding paradigms for 2 kinds of seq2seq tasks: …

arxiv generation seq2seq

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US

AI Research Scientist

@ Vara | Berlin, Germany and Remote

Data Architect

@ University of Texas at Austin | Austin, TX

Data ETL Engineer

@ University of Texas at Austin | Austin, TX

Data Scientist (Database Development)

@ Nasdaq | Bengaluru-Affluence