In this paper, we propose DASpeech, a non-autoregressive direct S2ST model which realizes both fast and high-quality S2ST.

This work was done when Mingyu was at MIT.

In large-scale applications, datasets often contain billions of high-dimensional points. Grouping similar data points into clusters is crucial for understanding and organizing datasets.

In this work, we analyze stability as a property for reliable feature attribution methods.

The rapid scaling of language models is motivating research using low-bitwidth quantization. In this work, we propose a novel binarization technique for Transformers applied to machine translation (BMT), the first of its kind.