Although suchmodern methods allowedlearning successful semantic segmentation systems, their training requires large-scale labeled datasets with usually a need for pixel-level annotations.

Dynamical systems (DS) theory is fundamental for many areas of science and engineering. It can provide deep insights into the behavior of systems evolving in time, as typically described by differential or recursive equations.

The first three authors contributed equally.

We consider the black-box adversarial setting, where the adversary has to generate adversarial perturbations without access to the target models to compute gradients.

Federated learning (FL) is a challenging setting for optimization due to the heterogeneity of the data across different clients which can cause a client drift phenomenon.

Multimodal interleaved datasets featuring free-form interleaved sequences of images and text are crucial for training frontier large multimodal models (LMMs).