Generative adversarial networks: A survey toward private and secure applications

Z Cai, Z **ong, H Xu, P Wang, W Li, Y Pan - ACM Computing Surveys …, 2021 - dl.acm.org
Generative Adversarial Networks (GANs) have promoted a variety of applications in
computer vision and natural language processing, among others, due to its generative …

Generative adversarial networks in computer vision: A survey and taxonomy

Z Wang, Q She, TE Ward - ACM Computing Surveys (CSUR), 2021 - dl.acm.org
Generative adversarial networks (GANs) have been extensively studied in the past few
years. Arguably their most significant impact has been in the area of computer vision where …

Discovering language model behaviors with model-written evaluations

E Perez, S Ringer, K Lukošiūtė, K Nguyen… - arxiv preprint arxiv …, 2022 - arxiv.org
As language models (LMs) scale, they develop many novel behaviors, good and bad,
exacerbating the need to evaluate how they behave. Prior work creates evaluations with …

Self-training with noisy student improves imagenet classification

Q **e, MT Luong, E Hovy… - Proceedings of the IEEE …, 2020 - openaccess.thecvf.com
We present a simple self-training method that achieves 88.4% top-1 accuracy on ImageNet,
which is 2.0% better than the state-of-the-art model that requires 3.5 B weakly labeled …

Unsupervised data augmentation for consistency training

Q **e, Z Dai, E Hovy, T Luong… - Advances in neural …, 2020 - proceedings.neurips.cc
Semi-supervised learning lately has shown much promise in improving deep learning
models when labeled data is scarce. Common among recent approaches is the use of …

A survey of unsupervised deep domain adaptation

G Wilson, DJ Cook - ACM Transactions on Intelligent Systems and …, 2020 - dl.acm.org
Deep learning has produced state-of-the-art results for a variety of tasks. While such
approaches for supervised learning have performed well, they assume that training and …

Race: Large-scale reading comprehension dataset from examinations

G Lai, Q **e, H Liu, Y Yang, E Hovy - arxiv preprint arxiv:1704.04683, 2017 - arxiv.org
We present RACE, a new dataset for benchmark evaluation of methods in the reading
comprehension task. Collected from the English exams for middle and high school Chinese …

Good semi-supervised learning that requires a bad gan

Z Dai, Z Yang, F Yang, WW Cohen… - Advances in neural …, 2017 - proceedings.neurips.cc
Semi-supervised learning methods based on generative adversarial networks (GANs)
obtained strong empirical results, but it is not clear 1) how the discriminator benefits from …

Deep reinforcement learning

SE Li - Reinforcement learning for sequential decision and …, 2023 - Springer
Similar to humans, RL agents use interactive learning to successfully obtain satisfactory
decision strategies. However, in many cases, it is desirable to learn directly from …

Synthetic QA corpora generation with roundtrip consistency

C Alberti, D Andor, E Pitler, J Devlin… - arxiv preprint arxiv …, 2019 - arxiv.org
We introduce a novel method of generating synthetic question answering corpora by
combining models of question generation and answer extraction, and by filtering the results …