Generative adversarial networks: A survey toward private and secure applications
Generative Adversarial Networks (GANs) have promoted a variety of applications in
computer vision and natural language processing, among others, due to its generative …
computer vision and natural language processing, among others, due to its generative …
Generative adversarial networks in computer vision: A survey and taxonomy
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 …
years. Arguably their most significant impact has been in the area of computer vision where …
Discovering language model behaviors with model-written evaluations
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 …
exacerbating the need to evaluate how they behave. Prior work creates evaluations with …
Self-training with noisy student improves imagenet classification
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 …
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
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 …
models when labeled data is scarce. Common among recent approaches is the use of …
A survey of unsupervised deep domain adaptation
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 …
approaches for supervised learning have performed well, they assume that training and …
Race: Large-scale reading comprehension dataset from examinations
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 …
comprehension task. Collected from the English exams for middle and high school Chinese …
Good semi-supervised learning that requires a bad gan
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 …
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 …
decision strategies. However, in many cases, it is desirable to learn directly from …
Synthetic QA corpora generation with roundtrip consistency
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 …
combining models of question generation and answer extraction, and by filtering the results …