To cope with real-world dynamics, an intelligent system needs to incrementally acquire,
update, accumulate, and exploit knowledge throughout its lifetime. This ability, known as …

This article surveys and organizes research works in a new paradigm in natural language
processing, which we dub “prompt-based learning.” Unlike traditional supervised learning …

Ensuring alignment, which refers to making models behave in accordance with human
intentions [1, 2], has become a critical task before deploying large language models (LLMs) …

Cutting-edge diffusion models produce images with high quality and customizability,
enabling them to be used for commercial art and graphic design purposes. But do diffusion …

Deep machine unlearning is the problem of'removing'from a trained neural network a subset
of its training set. This problem is very timely and has many applications, including the key …

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 …

In coming years or decades, artificial general intelligence (AGI) may surpass human
capabilities at many critical tasks. We argue that, without substantial effort to prevent it, AGIs …

Abstract Noisy label Facial Expression Recognition (FER) is more challenging than
traditional noisy label classification tasks due to the inter-class similarity and the annotation …

Existing studies indicate that deep neural networks (DNNs) can eventually memorize the
label noise. We observe that the memorization strength of DNNs towards each instance is …

This explainer document aims to provide an overview of the current state of the rapidly
expanding work on synthetic data technologies, with a particular focus on privacy. The …