Top Papers
Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models
huggingface/pytorch-transformers
•
•
In this work, we take the first step to exploit the pre-trained (unfine-tuned) weights to mitigate backdoors in fine-tuned language models.
Parsing as Pretraining
huggingface/pytorch-pretrained-BERT
•
•
We first cast constituent and dependency parsing as sequence tagging.
pytorch
pytorch/pytorch
•
•
NeurIPS 2019
Tensors and Dynamic neural networks in Python with strong GPU acceleration
A ConvNet for the 2020s
keras-team/keras
•
•
CVPR 2022
The "Roaring 20s" of visual recognition began with the introduction of Vision Transformers (ViTs), which quickly superseded ConvNets as the state-of-the-art image classification model.
Ranked #2 on
Domain Generalization
on VizWiz-Classification
(using extra training data)
RegNet: Self-Regulated Network for Image Classification
keras-team/keras
•
•
The ResNet and its variants have achieved remarkable successes in various computer vision tasks.
Ranked #3 on
Medical Image Classification
on NCT-CRC-HE-100K
MaskNet: Introducing Feature-Wise Multiplication to CTR Ranking Models by Instance-Guided Mask
We also turn the feed-forward layer in DNN model into a mixture of addictive and multiplicative feature interactions by proposing MaskBlock in this paper.
Ranked #2 on
Click-Through Rate Prediction
on Criteo
Gender Classification and Bias Mitigation in Facial Images
We worked to increase classification accuracy and mitigate algorithmic biases on our baseline model trained on the augmented benchmark database.
