Image classification has always been a hot research direction in the world, and the
emergence of deep learning has promoted the development of this field. Convolutional …

Ensemble learning combines several individual models to obtain better generalization
performance. Currently, deep learning architectures are showing better performance …

Through considerable effort and intuition, several recent works have reverse-engineered
nontrivial behaviors oftransformer models. This paper systematizes the mechanistic …

Large language models (LLMs) with hundreds of billions of parameters have sparked a new
wave of exciting AI applications. However, they are computationally expensive at inference …

Large language models (LLMs) have demonstrated impressive capabilities in natural
language processing. However, their internal mechanisms are still unclear and this lack of …

We revisit large kernel design in modern convolutional neural networks (CNNs). Inspired by
recent advances in vision transformers (ViTs), in this paper, we demonstrate that using a few …

This work identifies 18 foundational challenges in assuring the alignment and safety of large
language models (LLMs). These challenges are organized into three different categories …

In this paper, we identify and characterize the emerging area of representation engineering
(RepE), an approach to enhancing the transparency of AI systems that draws on insights …

Deep-learning models have become pervasive tools in science and engineering. However,
their energy requirements now increasingly limit their scalability. Deep-learning …

We present a simple but powerful architecture of convolutional neural network, which has a
VGG-like inference-time body composed of nothing but a stack of 3x3 convolution and …