The vulnerability of deep neural network models to adversarial example
a...
Deep learning is experiencing a rise in foundation models that are expec...
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 ...
Foundation models are becoming the dominant deep learning technologies.
...
In this paper, we pay attention to the issue which is usually overlooked...
Graph matching finds the correspondence of nodes across two correlated g...
Optimal transport (OT) naturally arises in a wide range of machine learn...
As an emerging technique for confidential computing, trusted execution
e...
Expensive bounding-box annotations have limited the development of objec...
Trusted execution environments (TEE) such as Intel's Software Guard Exte...
Pre-training models such as BERT have achieved great success in many nat...
Graph matching finds the correspondence of nodes across two graphs and i...
A trusted execution environment (TEE) such as Intel Software Guard Exten...
Pre-trained language models like BERT have proven to be highly performan...
In this paper, we focus on solving a class of constrained non-convex
non...
Pre-trained language representation models, such as BERT, capture a gene...