2025.acl-long.453.pdf

N/A

Byte Latent Transformer: Patches Scale Better Than Tokens Artidoro Pagnoni1 , Ram Pasunuru‡ , Pedro Rodriguez‡ , John Nguyen‡ , Benjamin Muller, Margaret Li1 , Chunting Zhou⋄ , Lili Yu, Jason Weston, Luke Zettlemoyer3 , Gargi Ghosh, Mike Lewis, Ari Holtzman2,⋄,† , Srinivasan Iyer† FAIR at Meta, 1 Paul G. Allen School of Computer Science & Engineering, University of Washington, 2 University of Chicago…

saved by

• Laerdon Kim

related reading

• Byte Latent Transformer: Patches Scale Better Than Tokensarxiv.org
• The Bitter Lesson is coming for Tokenization – ⛰️ lucalplucalp.dev
• Byte Latent Transformer: Patches Scale Better Than Tokens | Research - AI at Metaai.meta.com
• [2512.23675] End-to-End Test-Time Training for Long Contextarxiv.org
• [2510.13786] The Art of Scaling Reinforcement Learning Compute for LLMsarxiv.org
• [2005.14165] Language Models are Few-Shot Learnersarxiv.org
• [2106.09685] LoRA: Low-Rank Adaptation of Large Language Modelsarxiv.org
• Large Language Diffusion Modelsarxiv.org
• The End of Tokenizationronaldyu.substack.com
• 1706.03762arxiv.org
• 2502.11089arxiv.org
• [2509.14786] Pre-training under infinite computearxiv.org