2026-05-11

3 saved articles
BackLibrary
ArticleRead
Fast Byte Latent Transformer
[Submitted on 8 May 2026] / arXiv.org
Recent byte-level language models (LMs) match the performance of token-level models without relying on subword vocabularies, yet their utility is limited by slow, byte-by-byte autoregressive generation. We address this bottleneck in the Byte Latent Transformer (BLT) through new training and generation techniques. First, we introduce BLT Diffusion (BLT-D), a new model and our fastest BLT variant, trained with an auxiliary block-wise diffusion objective alongside the standard next-byte prediction
--
arxiv.org
arxiv.org / source link only
--
Hermes Agent — The Agent That Grows With You
Hermes Agent
Hermes Agent — a standalone terminal app and a native application for macOS, Windows, and Linux. Install it and start a conversation with the agent that grows with you.
--