# Timesteps of Mamba Align with Human Reading Times

arXiv: https://arxiv.org/abs/2606.29904 · HTML: https://mlsanity.com/paper/2606.29904/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Core SSM architectures for language, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 12 of its 27 references that are in the map.
- First posted on arXiv 29 Jun 2026.

## Placed in

- State-space sequence models (S4, Mamba) / [Core SSM architectures for language](https://mlsanity.com/ssm/core-ssm-architectures-for-language/)

## Builds on (most cited first, 12 of 12)

- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Why Does Surprisal From Larger Transformer-Based Language Models Provide a Poorer Fit to Human Reading Times?](https://mlsanity.com/paper/2212.12131/) (2022)
- [Testing the Predictions of Surprisal Theory in 11 Languages](https://mlsanity.com/paper/2307.03667/) (2023)
- [Lower Perplexity is Not Always Human-Like](https://mlsanity.com/paper/2106.01229/) (2021)
- [Falcon Mamba: The First Competitive Attention-free 7B Language Model](https://mlsanity.com/paper/2410.05355/) (2024)
- [The Natural Stories Corpus](https://mlsanity.com/paper/1708.05763/) (2017)
- [Locating and Editing Factual Associations in Mamba](https://mlsanity.com/paper/2404.03646/) (2024)
- [Context Limitations Make Neural Language Models More Human-Like](https://mlsanity.com/paper/2205.11463/) (2022)
- [Large Language Models Are Human-Like Internally](https://mlsanity.com/paper/2502.01615/) (2025)
- [Accounting for Agreement Phenomena in Sentence Comprehension with Transformer Language Models: Effects of Similarity-based Interference on Surprisal and Attention](https://mlsanity.com/paper/2104.12874/) (2021)
- [If Attention Serves as a Cognitive Model of Human Memory Retrieval, What is the Plausible Memory Representation?](https://mlsanity.com/paper/2502.11469/) (2025)
- [Mamba Knockout for Unraveling Factual Information Flow](https://mlsanity.com/paper/2505.24244/) (2025)

## Abstract (arXiv)

This study demonstrates an alignment of per-word processing time in a popular state-space language model Mamba and human readers. In Mamba, the recurrent state transition at each layer conceptually takes some duration of time, the discretization timestep Deltat, determined dynamically in response to the input. Using a naturalistic reading dataset, we show that the per-word timestep from Mamba is a significant predictor of human reading times, and remains significant even when known predictors such as GPT-2 surprisal are controlled for. We further suggest, through formal analysis of Mamba's architecture and internal dynamics, that Mamba can serve as a new, valuable lens to look at human real-time language processing with ever-updated memory, because it allows us to look at how each module (layer) weighs short- and long-term information retention, and how noise may interact with dynamic, continuous memory representation. Code is available online.