tensorflow

tensorflow/tensorflow 27 Feb 2019

An Open Source Machine Learning Framework for Everyone

BIG-bench Machine Learning

Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models

huggingface/pytorch-transformers 18 Oct 2022

In this work, we take the first step to exploit the pre-trained (unfine-tuned) weights to mitigate backdoors in fine-tuned language models.

Language Modelling Sentiment Analysis +2

Parsing as Pretraining

huggingface/pytorch-pretrained-BERT 5 Feb 2020

We first cast constituent and dependency parsing as sequence tagging.

Dependency Parsing Language Modelling

transformers

huggingface/transformers 15 May 2023

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Controllable Language Modelling Dialogue Generation +2

pytorch

pytorch/pytorch NeurIPS 2019

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Vocal Bursts Intensity Prediction

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The "Roaring 20s" of visual recognition began with the introduction of Vision Transformers (ViTs), which quickly superseded ConvNets as the state-of-the-art image classification model.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)

Domain Generalization Image Classification +2

RegNet: Self-Regulated Network for Image Classification

keras-team/keras 3 Jan 2021

The ResNet and its variants have achieved remarkable successes in various computer vision tasks.

General Classification Image Classification +1

MaskNet: Introducing Feature-Wise Multiplication to CTR Ranking Models by Instance-Guided Mask

twitter/the-algorithm 9 Feb 2021

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.

Click-Through Rate Prediction Recommendation Systems

Gender Classification and Bias Mitigation in Facial Images

Developer-Y/cs-video-courses 13 Jul 2020

We worked to increase classification accuracy and mitigate algorithmic biases on our baseline model trained on the augmented benchmark database.

Classification General Classification