The paper proposes combining State Space Models (SSMs) with Mixture of Experts (MoE) to unlock the scaling potential of SSMs. The resulting model, MoE-Mamba, outperforms both Mamba and Transformer-MoE in terms of performance and training steps.

https://arxiv.org/abs//2401.04081

YouTube: https://www.youtube.com/@ArxivPapers

TikTok: https://www.tiktok.com/@arxiv_papers

Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016

Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers