Overview

Byte-level language models predict raw bytes rather than subword tokens, aiming to reduce tokenizer blind spots across languages, spelling variants, and code. Approaches include hierarchical or adaptive byte patching, continuous chunk representations with byte decoders, standard Transformers, and distillation from token-trained models. They are evaluated using bits per byte and downstream language, code, and multilingual tasks; patching, multi-byte prediction, and speculative decoding aim to manage compute and speed generation. Byte models can match or surpass token models at larger training scales and improve character-level robustness, but longer sequences, boundary selection, UTF-8 validity, and fine-grained character understanding remain important tradeoffs.

Latest papers

34 papers4 papers in the last four weeks, down 50% on the four weeks before. 0.0% of all new papers.

Mar 10, 2026

HoloByte: Continuous Hyperspherical Distillation for Tokenizer-Free Modeling

Sequence modeling universally relies on discrete subword tokenization to circumvent the O(N2)\mathcal{O}(N^2) computational intractability of native byte-level attention. However, this heuristic quantization imposes artificial morphological boundaries, enforces vocabulary dependence, and fractures the continuity of the optimization landscape. To resolve this dichotomy, we introduce HoloByte: a strictly tokenizer-free framework utilizing Continuous Hyperspherical Distillation. HoloByte partitions discrete byte sequences into fixed-capacity chunks and projects them into a continuous, strictly bounded hyperspherical manifold via an invertible, dimension-preserving orthogonal rotation operator. This spatial superposition allows a macroscopic transformer to operate exclusively on compressed continuous representations, formally reducing the exact attention time complexity from O(N2D)\mathcal{O}(N^2D) to O(N2W2D+ND2)\mathcal{O}\left( \frac{N^2}{W^2}D + ND^2 \right). A localized causal micro-decoder subsequently unbinds these representations to compute exact byte-level distributions. To govern this continuous trajectory, we propose a dual-objective formulation incorporating a mathematically precise Holographic Latent Mean Squared Error, which strictly bounds the gradient and guarantees asymptotic stability. Theoretically, we derive the minimal embedding dimension D=Ω(Wln⁡∣V∣)D = Ω(W \ln |\mathcal{V}|) required to ensure error-free discrete recovery from the continuous manifold. Empirically, under strictly matched parameter constraints, HoloByte is systematically outperforming a comparable discrete Byte-Pair Encoding (BPE) baseline. These results establish Continuous Hyperspherical Distillation as a mathematically rigorous and computationally tractable foundation for vocabulary-invariant sequence modeling. The code is available at https://github.com/VladimerKhasia/HoloByte
Mar 9, 2026

Benchmarking Language Modeling for Lossless Compression of Full-Fidelity Audio

Autoregressive "language" models (LMs) trained on raw waveforms can be repurposed for lossless audio compression, but prior work is limited to 8-bit audio, leaving open whether such approaches work for practical settings (16/24-bit) and can compete with existing codecs. We benchmark LM-based compression on full-fidelity audio across diverse domains (music, speech, bioacoustics), sampling rates (16kHz-48kHz), and bit depths (8, 16, 24-bit). Standard sample-level tokenization becomes intractable at higher bit depths due to vocabulary size (65K for 16-bit; 16.7M for 24-bit). We propose Trilobyte, a byte-level tokenization schema for full resolution audio, improving vocabulary scaling from O(2b)O(2^{b}) to O(1)O(1) and enabling the first tractable 24-bit LM-based lossless compression. While LMs consistently outperform FLAC and yield state-of-the-art compression at 8-bit and 16-bit, we observe that compression gains become more modest as bit depth increases beyond 8-bit.
Mar 3, 2026

ByteFlow: Language Modeling through Adaptive Byte Compression without a Tokenizer

Modern language models still rely on fixed, pre-defined subword tokenizations. Once a tokenizer is trained, the LM can only operate at this fixed level of granularity, which often leads to brittle and counterintuitive behaviors even in otherwise strong reasoning models. We introduce ByteFlow Net, a new hierarchical architecture that removes tokenizers entirely and instead enables models to learn their own segmentation of raw byte streams into semantically meaningful units. ByteFlow Net performs compression-driven segmentation based on the coding rate of latent representations, yielding adaptive boundaries \emph{while preserving a static computation graph via Top-KK selection}. Unlike prior self-tokenizing methods that depend on brittle heuristics with human-designed inductive biases, ByteFlow Net adapts its internal representation granularity to the input itself. Experiments demonstrate that this compression-based chunking strategy yields substantial performance gains, with ByteFlow Net outperforming both BPE-based Transformers and previous byte-level architectures. These results suggest that end-to-end, tokenizer-free modeling is not only feasible but also more effective, opening a path toward more adaptive and information-grounded language models.
Feb 1, 2026

Distilling Token-Trained Models into Byte-Level Models

Byte Language Models (BLMs) have emerged as a promising direction for scaling language models beyond tokenization. However, existing BLMs typically require training from scratch on trillions of bytes, making them prohibitively expensive. In this paper, we propose an efficient distillation recipe that converts existing token-trained LLMs into BLMs while retaining comparable capabilities. Our recipe follows a two-stage curriculum: (1) Progressive Knowledge Distillation, which aligns byte-level representations with the embeddings of the token-trained teacher model; and (2) Byte-Level Supervised Fine-Tuning, which enables end-to-end generation entirely in the byte space. We validate our approach across multiple model families, including Llama, Qwen, and OLMo, and demonstrate that the distilled BLMs retain most of the teacher models' performance using only approximately 125B bytes.