Draft executive order would create AI litigation task force and threaten federal funding to force states to abandon artificial intelligence regulations.

Although numerous studies have been emerged on adversarial attacks and defenses in fields such as face recognition, person re-identification, and pedestrian detection, there is currently a lack of research on the security of VIReID systems.

In this paper, we take initial steps towards correcting predictive errors of ViTs, particularly those arising from subpopulation shifts.

Mobile health leverages personalized and contextually tailored interventions optimized through bandit and reinforcement learning algorithms.

In our work, we focus on smooth convex or strongly convex problems in the interpolation regime.

Extrapolation necessitates the capability of generalizing beyond the training distribution support, which is essential for the robust deployment of machine learning models in real-world scenarios.

Obtaining effective representations of DNA sequences is crucial for genome analysis.

Sliced Wasserstein (SW) and Generalized Sliced Wasserstein (GSW) have been widely used in applications due to their computational and statistical scalability.