Recent success of deep learning is largely attributed to the sheer amount of data used for
training deep neural networks. Despite the unprecedented success, the massive data …

Generalization to out-of-distribution (OOD) data is a capability natural to humans yet
challenging for machines to reproduce. This is because most learning algorithms strongly …

The scaling of Transformers has driven breakthrough capabilities for language models. At
present, the largest large language models (LLMs) contain upwards of 100B parameters …

Scaling up neural networks has led to remarkable performance across a wide range of
tasks. Moreover, performance often follows reliable scaling laws as a function of training set …

It has been recognized that the data generated by the denoising diffusion probabilistic
model (DDPM) improves adversarial training. After two years of rapid development in …

Cross-entropy is a widely used loss function in applications. It coincides with the logistic loss
applied to the outputs of a neural network, when the softmax is used. But, what guarantees …

Multimodal datasets are a critical component in recent breakthroughs such as CLIP, Stable
Diffusion and GPT-4, yet their design does not receive the same research attention as model …

The current modus operandi in adapting pre-trained models involves updating all the
backbone parameters, ie., full fine-tuning. This paper introduces Visual Prompt Tuning (VPT) …

Today, computer systems hold large amounts of personal data. Yet while such an
abundance of data allows breakthroughs in artificial intelligence, and especially machine …

Detecting out-of-distribution inputs is critical for the safe deployment of machine learning
models in the real world. However, neural networks are known to suffer from the …