Search Results for author:
Found 5 papers, 2 papers with code
The NiuTrans Machine Translation Systems for WMT20
This paper describes NiuTrans neural machine translation systems of the WMT20 news translation tasks.
Enhancing Speech Large Language Models with Prompt-Aware Mixture of Audio Encoders
Connecting audio encoders with large language models (LLMs) allows the LLM to perform various audio understanding tasks, such as automatic speech recognition (ASR) and audio captioning (AC).
Optimizing Speech Multi-View Feature Fusion through Conditional Computation
Recent advancements have highlighted the efficacy of self-supervised learning (SSL) features in various speech-related tasks, providing lightweight and versatile multi-view speech representations.
Early Exit Is a Natural Capability in Transformer-based Models: An Empirical Study on Early Exit without Joint Optimization
Large language models (LLMs) exhibit exceptional performance across various downstream tasks.
PartialFormer: Modeling Part Instead of Whole for Machine Translation
In this work, we emphasize the importance of hidden dimensions in designing lightweight FFNs, a factor often overlooked in previous architectures.
Ranked #23 on
Machine Translation
on WMT2014 English-German
