See author contributions for details.

Integrating multi-modal clinical data, such as electronic health records (EHR) and chest X-ray images (CXR), is particularly beneficial for clinical prediction tasks. However, in a temporal setting, multi-modal data are often inherently asynchronous.

Although using gated RNNs cells as feedforward networks is fairly non-standard, our primary motivation is to keep the AED and AO architectures as similar as possible in order to isolate the differences that arise from recurrence and positional encoding.

The problem of adversarial defenses for image classification, where the goal is to robustify a classifier against adversarial examples, is considered.

We first take a theoretical approach to analyzing debate and provide a framework through which debate can be mathematically examined. Building on this framework, we provide several theoretical results for multi-agent debate.

During the last decade, with the rise of deep convolutional neural networks (CNNs), great progress has been achieved in pedestrian detection.