The Generative Pre-trained Transformer (GPT) represents a notable breakthrough in the
domain of natural language processing, which is propelling us toward the development of …

Data augmentation, the artificial creation of training data for machine learning by
transformations, is a widely studied research field across machine learning disciplines …

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 …

Large pre-trained models such as CLIP or ALIGN offer consistent accuracy across a range of
data distributions when performing zero-shot inference (ie, without fine-tuning on a specific …

We explore machine unlearning (MU) in the domain of large language models (LLMs),
referred to as LLM unlearning. This initiative aims to eliminate undesirable data influence …

Transformer emerges as a powerful tool for visual recognition. In addition to demonstrating
competitive performance on a broad range of visual benchmarks, recent works also argue …

As a research community, we are still lacking a systematic understanding of the progress on
adversarial robustness which often makes it hard to identify the most promising ideas in …

Adversarial training is one of the most effective approaches defending against adversarial
examples for deep learning models. Unlike other defense strategies, adversarial training …

We study how robust current ImageNet models are to distribution shifts arising from natural
variations in datasets. Most research on robustness focuses on synthetic image …