3 citations · 3 across the 3 of their papers we have counts for
3 papers
cs.LG2026
EAGLE-Pangu: Accelerator-Safe Tree Speculative Decoding on Ascend NPUs
Chang Han, Yijie Hu, Jingling Liu
Autoregressive decoding remains a primary bottleneck in large language model (LLM) serving, motivating speculative decoding methods that reduce expensive teacher-model invocations…
cs.CV2021
SimulSLT: End-to-End Simultaneous Sign Language Translation
Aoxiong Yin, Zhou Zhao, Jinglin Liu +4
Sign language translation as a kind of technology with profound social significance has attracted growing researchers' interest in recent years. However, the existing sign language…
cs.CL2020★ 3 cited
Task-Level Curriculum Learning for Non-Autoregressive Neural Machine Translation
Jinglin Liu, Yi Ren, Xu Tan +4
Non-autoregressive translation (NAT) achieves faster inference speed but at the cost of worse accuracy compared with autoregressive translation (AT). Since AT and NAT can share mod…