The paper introduces Titans, a new architecture combining neural long-term memory and attention, outperforming Transformers in various tasks while efficiently handling larger context windows.

https://arxiv.org/abs//2501.00663

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