Although deep learning has achieved satisfactory performance in computer vision, a large
volume of images is required. However, collecting images is often expensive and …

In the past decade, the application of machine learning (ML) to healthcare has helped drive
the automation of physician tasks as well as enhancements in clinical capabilities and …

In tasks involving the interpretation of medical images, suitably trained machine-learning
models often exceed the performance of medical experts. Yet such a high-level of …

Large language models (LMs) have been shown to memorize parts of their training data,
and when prompted appropriately, they will emit the memorized training data verbatim. This …

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 …

Motivated by concerns that large-scale diffusion models can produce undesirable output
such as sexually explicit content or copyrighted artistic styles, we study erasure of specific …

Optimizing large language models (LLMs) for downstream use cases often involves the
customization of pre-trained LLMs through further fine-tuning. Meta's open release of Llama …

A membership inference attack allows an adversary to query a trained machine learning
model to predict whether or not a particular example was contained in the model's training …

We present modality gap, an intriguing geometric phenomenon of the representation space
of multi-modal models. Specifically, we show that different data modalities (eg images and …

Despite their wide adoption, the underlying training and memorization dynamics of very
large language models is not well understood. We empirically study exact memorization in …