Attention in sequence models

A short project on how attention replaced recurrence in sequence models. It includes:

• A literature review of the work it builds on, citing the project’s bibliography.
• Presentation slides for a short talk on the same question.
• The paper, written in LaTeX with co-authors in Overleaf.

An example workspace for the Asta workspace skill, built and published from main; see its README for the demo and how to start your own.