Pith. sign in

REVIEW 7 cited by

From Bytes to Ideas: Language Modeling with Autoregressive U-Nets

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2506.14761 v1 pith:X77LESH6 submitted 2025-06-17 cs.CL cs.AI

classification cs.CLcs.AI
keywords modelwordsdeeperstagesautoregressivebytebytesfuture
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Tokenization imposes a fixed granularity on the input text, freezing how a language model operates on data and how far in the future it predicts. Byte Pair Encoding (BPE) and similar schemes split text once, build a static vocabulary, and leave the model stuck with that choice. We relax this rigidity by introducing an autoregressive U-Net that learns to embed its own tokens as it trains. The network reads raw bytes, pools them into words, then pairs of words, then up to 4 words, giving it a multi-scale view of the sequence. At deeper stages, the model must predict further into the future -- anticipating the next few words rather than the next byte -- so deeper stages focus on broader semantic patterns while earlier stages handle fine details. When carefully tuning and controlling pretraining compute, shallow hierarchies tie strong BPE baselines, and deeper hierarchies have a promising trend. Because tokenization now lives inside the model, the same system can handle character-level tasks and carry knowledge across low-resource languages.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. MultiHashFormer: Hash-based Generative Language Models

    cs.CL 2026-06 unverdicted novelty 7.0 of 10

    MultiHashFormer enables hash-based autoregression in LMs by encoding tokens as multi-hash signatures, outperforming standard Transformers at 100M-3B scales while keeping parameter count constant for multilingual expansion.

  2. Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models

    cs.CL 2026-05 conditional novelty 7.0 of 10

    Scratchpad Patching decouples compute from patch size in byte-level language models by inserting entropy-triggered scratchpads to update patch context dynamically.

  3. Cross-Tokenizer LLM Distillation through a Byte-Level Interface

    cs.CL 2026-04 unverdicted novelty 7.0 of 10

    Byte-Level Distillation achieves competitive or superior results in cross-tokenizer LLM distillation by using byte-level probabilities as a shared interface instead of aligning mismatched vocabularies.

  4. Dynamic Chunking for End-to-End Hierarchical Sequence Modeling

    cs.LG 2025-07 conditional novelty 7.0 of 10

    A learned dynamic chunking hierarchy lets byte-level language models match or beat BPE-tokenized Transformers at matched compute, with larger gains on Chinese, code, and DNA.

  5. Compute Optimal Tokenization

    cs.CL 2026-05 unverdicted novelty 6.0 of 10

    Compute-optimal language models require parameter count to scale with data bytes rather than tokens, with optimal token compression rate decreasing as compute budget grows.

  6. Compute Optimal Tokenization

    cs.CL 2026-05 unverdicted novelty 6.0 of 10

    In compute-optimal regimes, language model parameter count scales proportionally with data bytes rather than tokens, and the optimal compression rate decreases with increasing compute.

  7. Proxy Compression for Language Modeling

    cs.CL 2026-02 conditional novelty 6.0 of 10

    Proxy compression trains language models on both raw bytes and compressed sequences to enable efficient training with raw-byte inference at test time.

Pith tools