Abstract Convolutional Neural Networks (ConvNets) are commonly developed at a fixed
resource budget, and then scaled up for better accuracy if more resources are given. In this�…

Recent work on automated augmentation strategies has led to state-of-the-art results in
image classification and object detection. An obstacle to a large-scale adoption of these�…

Designing convolutional neural networks (CNN) for mobile devices is challenging because
mobile models need to be small and fast, yet still accurate. Although significant efforts have�…

We study the design decision of publicly available instruction tuning methods, by
reproducing and breaking down the development of Flan 2022 (Chung et al., 2022)�…

Pre-trained representations are becoming crucial for many NLP and perception tasks. While
representation learning in NLP has transitioned to training on raw text without human�…

This paper introduces EfficientNetV2, a new family of convolutional networks that have faster
training speed and better parameter efficiency than previous models. To develop these�…

The effort devoted to hand-crafting neural network image classifiers has motivated the use of
architecture search to discover them automatically. Although evolutionary algorithms have�…

We consider the problem of building high-level, class-specific feature detectors from only
unlabeled data. For example, is it possible to learn a face detector using only unlabeled�…

Recent work in unsupervised feature learning and deep learning has shown that being able
to train large models can dramatically improve performance. In this paper, we consider the�…

We present LaMDA: Language Models for Dialog Applications. LaMDA is a family of
Transformer-based neural language models specialized for dialog, which have up to 137B�…