Mobile and wearable devices have enabled numerous applications, including activity
tracking, wellness monitoring, and human–computer interaction, that measure and improve …

Web-crawled datasets have enabled remarkable generalization capabilities in recent image-
text models such as CLIP (Contrastive Language-Image pre-training) or Flamingo, but little …

Objective. Federated learning (FL) is a computational paradigm that enables organizations
to collaborate on machine learning (ML) and deep learning (DL) projects without sharing …

State-of-the-art AI models largely lack an understanding of the cause-effect relationship that
governs human understanding of the real world. Consequently, these models do not …

Large neural models have demonstrated human-level performance on language and vision
benchmarks, while their performance degrades considerably on adversarial or out-of …

Adversarial learning has demonstrated good performance in the unsupervised domain
adaptation setting, by learning domain-invariant representations. However, recent work has …

Subpopulation shift widely exists in many real-world machine learning applications, referring
to the training and test distributions containing the same subpopulation groups but varying in …

Human Activity Recognition (HAR) has been studied extensively, yet current approaches are
not capable of generalizing across different domains (ie, subjects, devices, or datasets) with …

Federated Learning (FL) is a way for machines to learn from data that is kept locally, in order
to protect the privacy of clients. This is typically done using local SGD, which helps to …

A grand goal in deep learning research is to learn representations capable of generalizing
across distribution shifts. Disentanglement is one promising direction aimed at aligning a …