We present Mu^2SLAM, a multilingual sequence-to-sequence model
pre-train...
Robotic peg-in-hole assembly is an essential task in robotic automation
...
Due to the rising concerns on privacy protection, how to build machine
l...
As an emerging secure learning paradigm in leveraging cross-agency priva...
Multilingual neural machine translation models are trained to maximize t...
We present mSLAM, a multilingual Speech and LAnguage Model that learns
c...
Natural language understanding and generation models follow one of the t...
Self-supervised pre-training of text representations has been successful...
In this paper, we propose a new adversarial augmentation method for Neur...
Federated learning systems are vulnerable to attacks from malicious clie...
One critical challenge for applying today's Artificial Intelligence (AI)...
In federated learning systems, clients are autonomous in that their beha...
Neural machine translation (NMT) often suffers from the vulnerability to...
Although attention-based Neural Machine Translation (NMT) has achieved
r...
Small perturbations in the input can severely distort intermediate
repre...
This paper introduces THUMT, an open-source toolkit for neural machine
t...
While end-to-end neural machine translation (NMT) has made remarkable
pr...
While recent neural machine translation approaches have delivered
state-...
While end-to-end neural machine translation (NMT) has made remarkable
pr...
The attentional mechanism has proven to be effective in improving end-to...
We propose minimum risk training for end-to-end neural machine translati...