The popularity of machine learning (ML), deep learning (DL) and artificial intelligence (AI)
has risen sharply in recent years. Despite this spike in popularity, the inner workings of ML …

Recent advances in machine learning have led to increased interest in solving visual
computing problems using methods that employ coordinate‐based neural networks. These …

Closed-set 3D perception models trained on only a pre-defined set of object categories can
be inadequate for safety critical applications such as autonomous driving where new object …

This paper studies the behaviour of two-layer fully connected networks with linear
activations trained with gradient flow on the square loss. We show how the optimization …

Sharpness-aware minimization (SAM) is a recently proposed method that minimizes the
sharpness of the training loss of a neural network. While its generalization improvement is …

In this work, we reveal a strong implicit bias of stochastic gradient descent (SGD) that drives
overly expressive networks to much simpler subnetworks, thereby dramatically reducing the …

This paper theoretically explains the intuition that simple concepts are more likely to be
learned by deep neural networks (DNNs) than complex concepts. In fact, recent studies …

The generalization of representations learned via contrastive learning depends crucially on
what features of the data are extracted. However, we observe that the contrastive loss does …

Learning to act from observational data without active environmental interaction is a well-
known challenge in Reinforcement Learning (RL). Recent approaches involve constraints …

Our work focuses on tackling large-scale fine-grained image retrieval as ranking the images
depicting the concept of interests (ie, the same sub-category labels) highest based on the …