Recent advances in foundation models present new opportunities for
inter...
Recent advances in weakly supervised text classification mostly focus on...
Deep neural classifiers trained with cross-entropy loss (CE loss) often
...
Backpropagation, the cornerstone of deep learning, is limited to computi...
Deep neural networks have seen enormous success in various real-world
ap...
How to train an ideal teacher for knowledge distillation is still an ope...
Weakly supervised text classification methods typically train a deep neu...
A cyber-attack is a malicious attempt by experienced hackers to breach t...
Here, we show that the robust overfitting shall be viewed as the early p...
Backdoor attack introduces artificial vulnerabilities into the model by
...
Contextualized representations based on neural language models have furt...
Multiple intriguing problems hover in adversarial training, including
ro...
Our goal is to understand why the robustness drops after conducting
adve...