Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox
Picture for Xinhsuai Dong

Xinhsuai Dong

How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?



Xinhsuai Dong , Luu Anh Tuan , Min Lin , Shuicheng Yan , Hanwang Zhang

Figure 1 for How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?
Figure 2 for How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?
Figure 3 for How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?
Figure 4 for How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?
* Accepted by NeurIPS-2021 
   Access Paper or Ask Questions