method · first seen 5 Oct 2026
byte-level language modeling
Also: byte-level LLM, byte-level modeling, tokenizer-free modeling, byte-level language model, tokenizer-free language model, tokenizer-free language modeling
Language models that operate directly on raw bytes instead of subword tokens, avoiding tokenizer vocabularies.
Mentions per week
PapersCodeDiscussion
Rank 185 on 10 Nov 2026 · 7 mentions in 28 days · 7 independent groups · papers → discussion · first seen 5 weeks ago · acceleration +0.69
Earliest sources
- Byte Language Models: Scaling, Emergent Abstractions, and Information AllocationPapers · 5 Oct 2026 · Jie Wang, Shiwei Luo, Qi Zhang, Yuanbin Wu
- Retrofitting language models to operate over bytesDiscussion · 8 Oct 2026 · theanonymousone · 111 points
- The Right Byte First: How UTF-16 Helps Multilingual Boundary PredictionPapers · 15 Oct 2026 · Hyunsik Kim
- FederatedBytes: Tokenizer-Free, Byte-Level Small Language Models for Efficient Multimodal Federated LearningPapers · 16 Oct 2026 · Ali Sarabadani, Massimo Piccardi, Mehran Abolhasan, Farzad Tofigh, Ian Zhou, Jus…
- Scaling Hierarchical NetworksDiscussion · 28 Oct 2026 · guybedo · 92 points
- Going Deeper With MemoriesPapers · 3 Nov 2026 · Afshin Khadangi
Latest sources
- When does text encoding matter for language modeling?Papers · 10 Nov 2026 · Eugene Jang, Catherine Arnett, Terra Blevins
- One Byte, One Token: Byteifying a 27B Hybrid-Attention LLM with Self-Generated DataPapers · 10 Nov 2026 · Liwei Zhang, ZhiMing Tong, Mochen Guan, Linzhe Li
- Familiar letters, not related languages, let unseen languages into a shared space of meaningPapers · 4 Nov 2026 · Yuliang Liu, Xinyu Wang, Xiang Bai
- Going Deeper With MemoriesPapers · 3 Nov 2026 · Afshin Khadangi
- Scaling Hierarchical NetworksDiscussion · 28 Oct 2026 · guybedo · 92 points
- FederatedBytes: Tokenizer-Free, Byte-Level Small Language Models for Efficient Multimodal Federated LearningPapers · 16 Oct 2026 · Ali Sarabadani, Massimo Piccardi, Mehran Abolhasan, Farzad Tofigh, Ian Zhou, Jus…
- The Right Byte First: How UTF-16 Helps Multilingual Boundary PredictionPapers · 15 Oct 2026 · Hyunsik Kim
- Retrofitting language models to operate over bytesDiscussion · 8 Oct 2026 · theanonymousone · 111 points
- Byte Language Models: Scaling, Emergent Abstractions, and Information AllocationPapers · 5 Oct 2026 · Jie Wang, Shiwei Luo, Qi Zhang, Yuanbin Wu