AI2's byte-level LM method Bolmo accepted to Nature, extended to Qwen and Llama
allen_ai · x · 2026-10-08
Allen AI announces its approach for retrofitting language models to operate over bytes — the method behind Bolmo — has been accepted to Nature, with new checkpoints extending the method from OLMo to Qwen and Llama.
More from Research
- New HSS Benchmark Shows Top AI Models Fail Basic Intuitive Visual Reasoning Humans Find Easy — dustinvtran · 2026-10-08
- Rowan Sci finds frontier LLMs surprisingly good at inverse folding, with some help — AllThingsApx · 2026-10-08
- Researchers from frontier labs debate continual learning for 3 hours — ysu_nlp · 2026-10-08
- Periodic Labs' Liam Fedus on AI scientists, autonomous labs and synthesis superintelligence — Latent Space · 2026-10-08
- Cambridge lab uses Google's Co-Scientist to compress 2-3 years of research into 6 months — vivnat · 2026-10-08
- CVPR 2026 ReLearn workshop: Efros argues AI may already learn too much from humans — TheZachMueller · 2026-10-08