This paper presents latent tokens, a lightweight method to enhance Transformer-based LLMs' performance and adaptability, particularly in out-of-distribution scenarios, with minimal complexity added.

https://arxiv.org/abs//2505.12629

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