I'm reviewing my #acl #nlp paper ARR batch (early! 🤯) and noticing a common issue! Make figures, shapes in figures, and text in figures bigger 🔍! Tip: physically match paper size on monitor and print 🖨️ final copy out. If you can't read in print at arms length, its too small.

🚀 Introducing the Byte Latent Transformer (BLT) – A LLM architecture that scales better than Llama 3 using patches instead of tokens 🤯
Paper 📄 dl.fbaipublicfiles.com/blt/BLT__Pat...
Code 🛠️ github.com/facebookrese...