# The Hidden Attention of Mamba Models

arXiv: https://arxiv.org/abs/2403.01590 · HTML: https://mlsanity.com/paper/2403.01590/

## Key facts

- Cited by 91 papers in the map (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 76 of its 84 references that are in the map.
- First posted on arXiv 3 Mar 2024.

## 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, 30 of 76)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [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)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling](https://mlsanity.com/paper/2304.01373/) (2023)
- [Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model](https://mlsanity.com/paper/2401.09417/) (2024)
- [VMamba: Visual State Space Model](https://mlsanity.com/paper/2401.10166/) (2024)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [RWKV: Reinventing RNNs for the Transformer Era](https://mlsanity.com/paper/2305.13048/) (2023)
- [Simplified State Space Layers for Sequence Modeling](https://mlsanity.com/paper/2208.04933/) (2022)
- [Quantifying Attention Flow in Transformers](https://mlsanity.com/paper/2005.00928/) (2020)
- [Transformer Interpretability Beyond Attention Visualization](https://mlsanity.com/paper/2012.09838/) (2020)
- [Retentive Network: A Successor to Transformer for Large Language Models](https://mlsanity.com/paper/2307.08621/) (2023)
- [Interpretable Explanations of Black Boxes by Meaningful Perturbation](https://mlsanity.com/paper/1704.03296/) (2017)
- [Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers](https://mlsanity.com/paper/2110.13985/) (2021)
- [U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation](https://mlsanity.com/paper/2401.04722/) (2024)
- [Hyena Hierarchy: Towards Larger Convolutional Language Models](https://mlsanity.com/paper/2302.10866/) (2023)
- [Diagonal State Spaces are as Effective as Structured State Spaces](https://mlsanity.com/paper/2203.14343/) (2022)
- [Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers](https://mlsanity.com/paper/2103.15679/) (2021)
- [VM-UNet: Vision Mamba UNet for Medical Image Segmentation](https://mlsanity.com/paper/2402.02491/) (2024)
- [SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image Segmentation](https://mlsanity.com/paper/2401.13560/) (2024)
- [Long Range Language Modeling via Gated State Spaces](https://mlsanity.com/paper/2206.13947/) (2022)
- [Transformer Quality in Linear Time](https://mlsanity.com/paper/2202.10447/) (2022)

## Built on by (most cited first, 30 of 91)

- [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://mlsanity.com/paper/2405.21060/) (2024)
- [Jamba: A Hybrid Transformer-Mamba Language Model](https://mlsanity.com/paper/2403.19887/) (2024)
- [HGRN2: Gated Linear RNNs with State Expansion](https://mlsanity.com/paper/2404.07904/) (2024)
- [Demystify Mamba in Vision: A Linear Attention Perspective](https://mlsanity.com/paper/2405.16605/) (2024)
- [Hymba: A Hybrid-head Architecture for Small Language Models](https://mlsanity.com/paper/2411.13676/) (2024)
- [A Primer on the Inner Workings of Transformer-based Language Models](https://mlsanity.com/paper/2405.00208/) (2024)
- [ZigMa: A DiT-style Zigzag Mamba Diffusion Model](https://mlsanity.com/paper/2403.13802/) (2024)
- [TimeMachine: A Time Series is Worth 4 Mambas for Long-term Forecasting](https://mlsanity.com/paper/2403.09898/) (2024)
- [State Space Model for New-Generation Network Alternative to Transformers: A Survey](https://mlsanity.com/paper/2404.09516/) (2024)
- [DeciMamba: Exploring the Length Extrapolation Potential of Mamba](https://mlsanity.com/paper/2406.14528/) (2024)
- [LongMamba: Enhancing Mamba's Long Context Capabilities via Training-Free Receptive Field Enlargement](https://mlsanity.com/paper/2504.16053/) (2025)
- [Visual Mamba: A Survey and New Outlooks](https://mlsanity.com/paper/2404.18861/) (2024)
- [MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selection](https://mlsanity.com/paper/2403.19888/) (2024)
- [Locating and Editing Factual Associations in Mamba](https://mlsanity.com/paper/2404.03646/) (2024)
- [MambaLRP: Explaining Selective State Space Sequence Models](https://mlsanity.com/paper/2406.07592/) (2024)
- [Towards Universality: Studying Mechanistic Similarity Across Language Model Architectures](https://mlsanity.com/paper/2410.06672/) (2024)
- [Exploring Token Pruning in Vision State Space Models](https://mlsanity.com/paper/2409.18962/) (2024)
- [Understanding the differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks](https://mlsanity.com/paper/2405.15731/) (2024)
- [VFIMamba: Video Frame Interpolation with State Space Models](https://mlsanity.com/paper/2407.02315/) (2024)
- [State Space Models as Foundation Models: A Control Theoretic Overview](https://mlsanity.com/paper/2403.16899/) (2024)
- [Mamba in Vision: A Comprehensive Survey of Techniques and Applications](https://mlsanity.com/paper/2410.03105/) (2024)
- [Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing](https://mlsanity.com/paper/2501.00658/) (2024)
- [Mimetic Initialization Helps State Space Models Learn to Recall](https://mlsanity.com/paper/2410.11135/) (2024)
- [Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism](https://mlsanity.com/paper/2504.18574/) (2025)
- [Hybrid Architectures for Language Models: Systematic Analysis and Design Insights](https://mlsanity.com/paper/2510.04800/) (2025)
- [Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation](https://mlsanity.com/paper/2405.16504/) (2024)
- [Deep Continuous-Time State-Space Models for Marked Event Sequences](https://mlsanity.com/paper/2412.19634/) (2024)
- [TSCMamba: Mamba Meets Multi-View Learning for Time Series Classification](https://mlsanity.com/paper/2406.04419/) (2024)
- [Provable Benefits of Complex Parameterizations for Structured State Space Models](https://mlsanity.com/paper/2410.14067/) (2024)
- [Advancing Intelligent Sequence Modeling: Evolution, Trade-offs, and Applications of State-Space Architectures from S4 to Mamba](https://mlsanity.com/paper/2503.18970/) (2025)

## Abstract (arXiv)

The Mamba layer offers an efficient selective state space model (SSM) that is highly effective in modeling multiple domains, including NLP, long-range sequence processing, and computer vision. Selective SSMs are viewed as dual models, in which one trains in parallel on the entire sequence via an IO-aware parallel scan, and deploys in an autoregressive manner. We add a third view and show that such models can be viewed as attention-driven models. This new perspective enables us to empirically and theoretically compare the underlying mechanisms to that of the self-attention layers in transformers and allows us to peer inside the inner workings of the Mamba model with explainability methods. Our code is publicly available.