Search Results for author:
Found 2 papers, 0 papers with code
Generalizability of Mixture of Domain-Specific Adapters from the Lens of Signed Weight Directions and its Application to Effective Model Pruning
Several parameter-efficient fine-tuning methods based on adapters have been proposed as a streamlined approach to incorporate not only a single specialized knowledge into existing Pre-Trained Language Models (PLMs) but also multiple of them at once.
Marrying Adapters and Mixup to Efficiently Enhance the Adversarial Robustness of Pre-Trained Language Models for Text Classification
Existing works show that augmenting training data of neural networks using both clean and adversarial examples can enhance their generalizability under adversarial attacks.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
