<ul><li>Authors: (1) Albert Gu, Machine Learning Department, Carnegie Mellon University and with equal contribution; (2) Tri Dao, Department of Computer Science, Princeton University and with equal contribution.</li><li>This paper discusses the math behind selective state space models (SSMs) and their application in various tasks.</li><li>The authors propose a selection mechanism as a means of compression in SSMs, improving their efficiency and performance.</li><li>The paper also provides empirical evaluations and benchmarks for synthetic tasks, language modeling, DNA modeling, and audio generation.</li></ul>

The Math Behind Selective State Space Models

Discover more