# Dynamic Chunking for End-to-End Hierarchical Sequence Modeling

arXiv: https://arxiv.org/abs/2507.07955 · HTML: https://mlsanity.com/paper/2507.07955/

## Key facts

- Cited by 72 papers in the map (data through 14 Oct 2026).
- Builds on 97 of its 113 references that are in the map.
- First posted on arXiv 10 Jul 2025.

## Builds on (most cited first, 30 of 97)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [Root Mean Square Layer Normalization](https://mlsanity.com/paper/1910.07467/) (2019)

## Built on by (most cited first, 30 of 72)

- [Hierarchical Planning with Latent World Models](https://mlsanity.com/paper/2604.03208/) (2026)
- [Dynamic Large Concept Models: Latent Reasoning in an Adaptive Semantic Space](https://mlsanity.com/paper/2512.24617/) (2025)
- [SpiralFormer: Looped Transformers Can Learn Hierarchical Dependencies via Multi-Resolution Recursion](https://mlsanity.com/paper/2602.11698/) (2026)
- [False Friends Are Not Foes: Investigating Vocabulary Overlap in Multilingual Language Models](https://mlsanity.com/paper/2509.18750/) (2025)
- [Next Concept Prediction in Discrete Latent Space Leads to Stronger Language Models](https://mlsanity.com/paper/2602.08984/) (2026)
- [BabyBabelLM: A Multilingual Benchmark of Developmentally Plausible Training Data](https://mlsanity.com/paper/2510.10159/) (2025)
- [Bolmo: Byteifying the Next Generation of Language Models](https://mlsanity.com/paper/2512.15586/) (2025)
- [FLEXITOKENS: Flexible Tokenization for Evolving Language Models](https://mlsanity.com/paper/2507.12720/) (2025)
- [Xihe: Scalable Zero-Shot Time Series Learner Via Hierarchical Interleaved Block Attention](https://mlsanity.com/paper/2510.21795/) (2025)
- [Cross-Tokenizer LLM Distillation through a Byte-Level Interface](https://mlsanity.com/paper/2604.07466/) (2026)
- [Training Transformers for KV Cache Compressibility](https://mlsanity.com/paper/2605.05971/) (2026)
- [Context-level Language Modeling by Learning Predictive Context Embeddings](https://mlsanity.com/paper/2510.20280/) (2025)
- [Model-Aware Tokenizer Transfer](https://mlsanity.com/paper/2510.21954/) (2025)
- [Stop Taking Tokenizers for Granted: They Are Core Design Decisions in Large Language Models](https://mlsanity.com/paper/2601.13260/) (2026)
- [Hierarchical Latent Action Model](https://mlsanity.com/paper/2603.05815/) (2026)
- [DASH: Dynamic Audio-Driven Semantic Chunking for Efficient Omnimodal Token Compression](https://mlsanity.com/paper/2603.15685/) (2026)
- [Beyond Fixed Frames: Dynamic Character-Aligned Speech Tokenization](https://mlsanity.com/paper/2601.23174/) (2026)
- [PonderLM-3: Adaptive Token-Wise Pondering with Differentiable Masking](https://mlsanity.com/paper/2603.02023/) (2026)
- [Compute Optimal Tokenization](https://mlsanity.com/paper/2605.01188/) (2026)
- [ConceptMoE: Adaptive Token-to-Concept Compression for Implicit Compute Allocation](https://mlsanity.com/paper/2601.21420/) (2026)
- [Proxy Compression for Language Modeling](https://mlsanity.com/paper/2602.04289/) (2026)
- [dnaHNet: A Scalable and Hierarchical Foundation Model for Genomic Sequence Learning](https://mlsanity.com/paper/2602.10603/) (2026)
- [DC-DiT: Adaptive Compute and Elastic Inference for Visual Generation via Dynamic Chunking](https://mlsanity.com/paper/2603.06351/) (2026)
- [TimeSqueeze: Dynamic Patching for Efficient Time Series Forecasting](https://mlsanity.com/paper/2603.11352/) (2026)
- [Fast Byte Latent Transformer](https://mlsanity.com/paper/2605.08044/) (2026)
- [ByteGen: A Tokenizer-Free Generative Model for Orderbook Events in Byte Space](https://mlsanity.com/paper/2508.02247/) (2025)
- [MacPrompt: Maraconic-guided Jailbreak against Text-to-Image Models](https://mlsanity.com/paper/2601.07141/) (2026)
- [Echoes Over Time: Unlocking Length Generalization in Video-to-Audio Generation Models](https://mlsanity.com/paper/2602.20981/) (2026)
- [Decoupling the Benefits of Subword Tokenization for Language Model Training via Byte-level Simulation](https://mlsanity.com/paper/2604.27263/) (2026)
- [Efficient Pre-Training with Token Superposition](https://mlsanity.com/paper/2605.06546/) (2026)

## Abstract (arXiv)

Major progress on language models (LMs) in recent years has largely resulted from moving away from specialized models designed for specific tasks, to general models based on powerful architectures (e.g. the Transformer) that learn everything from raw data. Despite this trend, pre-processing steps such as tokenization remain a barrier to true end-to-end foundation models. We introduce a collection of new techniques that enable a dynamic chunking mechanism which automatically learns content- and context- dependent segmentation strategies learned jointly with the rest of the model. Incorporating this into an explicit hierarchical network (H-Net) allows replacing the (implicitly hierarchical) tokenization-LM-detokenization pipeline with a single model learned fully end-to-end. When compute- and data- matched, an H-Net with one stage of hierarchy operating at the byte level outperforms a strong Transformer language model operating over BPE tokens. Iterating the hierarchy to multiple stages further increases its performance by modeling multiple levels of abstraction, demonstrating significantly better scaling with data and matching the token-based Transformer of twice its size. H-Nets pretrained on English show significantly increased character-level robustness, and qualitatively learn meaningful data-dependent chunking strategies without any heuristics or explicit supervision. Finally, the H-Net's improvement over tokenized pipelines is further increased in languages and modalities with weaker tokenization heuristics, such as Chinese and code, or DNA sequences (nearly 4x improvement in data efficiency over baselines), showing the potential of true end-to-end models that learn and scale better from unprocessed data.