12 citations · 17 across the 3 of their papers we have counts for
3 papers
cs.CL2021★ 4 cited
Plug-Tagger: A Pluggable Sequence Labeling Framework Using Language Models
Xin Zhou, Ruotian Ma, Tao Gui +3
Plug-and-play functionality allows deep learning models to adapt well to different tasks without requiring any parameters modified. Recently, prefix-tuning was shown to be a plug-a…
cs.CL2021★ 12 cited
KNN-BERT: Fine-Tuning Pre-Trained Models with KNN Classifier
Linyang Li, Demin Song, Ruotian Ma +2
Pre-trained models are widely used in fine-tuning downstream tasks with linear classifiers optimized by the cross-entropy loss, which might face robustness and stability problems.…
cs.CR2021★ 1 cited
Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning
Linyang Li, Demin Song, Xiaonan Li +3
\textbf{P}re-\textbf{T}rained \textbf{M}odel\textbf{s} have been widely applied and recently proved vulnerable under backdoor attacks: the released pre-trained weights can be malic…