Catastrophic forgetting remains a critical challenge in the field of
con...
Augmented Reality (AR) has been used to facilitate surgical guidance dur...
The sparse Mixture-of-Experts (Sparse-MoE) framework efficiently scales ...
Current adversarial attacks against speaker recognition systems (SRSs)
r...
The sheer size of modern neural networks makes model serving a serious
c...
Deep learning has become a promising programming paradigm in software
de...
Existing zero-shot cross-lingual transfer methods rely on parallel corpo...
The latest industrial inference engines, such as FasterTransformer1 and
...
Previous studies have proved that cross-lingual knowledge distillation c...
Scientific literature serves as a high-quality corpus, supporting a lot ...
The use of Augmented Reality (AR) for navigation purposes has shown
bene...
We present a new probabilistic method for detecting, deblending, and
cat...
Speaker recognition systems (SRSs) have recently been shown to be vulner...
In this paper, we pay attention to the issue which is usually overlooked...
Due to the vulnerability of deep neural networks (DNNs) to adversarial
e...
Multi-task learning can leverage information learned by one task to bene...
The world of empirical machine learning (ML) strongly relies on benchmar...
As a new programming paradigm, deep learning has expanded its applicatio...
Verifying and explaining the behavior of neural networks is becoming
inc...
Multi-task learning can leverage information learned by one task to bene...
Achieving state-of-the-art performance on natural language understanding...
The dot product self-attention is known to be central and indispensable ...
Pre-trained language models like BERT have proven to be highly performan...
Speaker recognition (SR) is widely used in our daily life as a biometric...
Pre-trained language representation models, such as BERT, capture a gene...
Existing works, including ELMO and BERT, have revealed the importance of...
Numerous methods for crafting adversarial examples were proposed recentl...
Recommender systems are one of the most pervasive applications of machin...
Analogical reasoning is effective in capturing linguistic regularities. ...
Despite the loss of semantic information, bag-of-ngram based methods sti...