Research on prompting has shown excellent performance with little or even no supervised
training across many tasks. However, prompting for machine translation is still under …

We demonstrate the potential of few-shot translation systems, trained with unpaired
language data, for both high and low-resource language pairs. We show that with only 5 …

This paper presents the results of the news translation task, the multilingual low-resource
translation for Indo-European languages, the triangular translation task, and the automatic …

While diffusion models have achieved great success in generating continuous signals such
as images and audio, it remains elusive for diffusion models in learning discrete sequence …

Non-autoregressive Transformer (NAT) is a family of text generation models, which aims to
reduce the decoding latency by predicting the whole sentences in parallel. However, such …

Benefiting from the sequence-level knowledge distillation, the Non-Autoregressive
Transformer (NAT) achieves great success in neural machine translation tasks. However …

The recent surge of generative AI has been fueled by the generative power of diffusion
probabilistic models and the scalable capabilities of large language models. Despite their …

Multilingual machine translation aims to develop a single model for multiple language
directions. However, existing multilingual models based on Transformer are limited in terms …

Non-autoregressive translation (NAT) reduces the decoding latency but suffers from
performance degradation due to the multi-modality problem. Recently, the structure of …

This paper introduces diffusion protein language model (DPLM), a versatile protein
language model that demonstrates strong generative and predictive capabilities for protein …