In many sequential tasks, a model needs to remember relevant events from the distant past to make correct predictions.

While mathematically elegant, a fundamental issue with AIXI is that it is only asymptotically computable.

Randomly masking and predicting word tokens has been a successful approach in pre-training language models for a variety of downstream tasks.

OOD detection relying on pure visual information can inherit the limitations, e.g., when an OOD

We introduce chefs' random tables (CRTs), a new class of non-trigonometric random features (RFs) to approximate Gaussian and softmax-kernels.

Since the data are high-dimensional or the network is large-scale, communication load can be a bottleneck for the efficiency of distributed algorithms.