This paper introduces Tree Cross Attention (TCA), a module that retrieves information from a logarithmic number of tokens for efficient inference. The proposed architecture, ReTreever, outperforms Perceiver IO while using the same number of tokens.

https://arxiv.org/abs//2309.17388

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