1 code implementation • 10 Oct 2023 • Pengyue Hou, Xingyu Li
The recent success of SimCSE has greatly advanced state-of-the-art sentence representations.
1 code implementation • 26 Oct 2022 • Pengyue Hou, Jie Han, Xingyu Li
Deep Neural Networks are vulnerable to adversarial attacks.
no code implementations • 28 Apr 2022 • Pengyue Hou, Ming Zhou, Jie Han, Petr Musilek, Xingyu Li
Adversarial training is an effective method to boost model robustness to malicious, adversarial attacks.