-
Long Range Arena
The Long Range Arena dataset consists of 6 tasks with lengths 1K-16K steps encompassing modalities and objectives that require similarity, structural, and visuospatial reasoning. -
Sequence Counting and MNIST Classification
The proposed method is evaluated on a toy example problem of sequence counting followed by MNIST classification problem. -
Parallelizing Autoregressive Generation with Variational State Space Models
The MNIST and CIFAR datasets are used to evaluate the proposed Variational State Space Model (VSSM) for autoregressive generation. -
Long Range Arena (LRA) benchmark
The dataset used in this paper is the Long Range Arena (LRA) benchmark for efficient sequence models, which contains 6 tasks with lengths 1K-16K steps, encompassing modalities and...
