</> Code with Papers by Syntology

Methods › Mamba

Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Mamba

599 papers tagged archive 2025-07-28

Introduced by Albert Gu et al. in Mamba: Linear-Time Sequence Modeling with Selective State Spaces

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module. Many subquadratic-time architectures such as linear attention, gated convolution and recurrent models, and structured state space models (SSMs) have been developed to address Transformers’ computational inefficiency on long sequences, but they have not performed as well as attention on important modalities such as language. We identify that a key weakness of such models is their inability to perform content-based reasoning, and make several improvements. First, simply letting the SSM parameters be functions of the input addresses their weakness with discrete modalities, allowing the model to selectively propagate or forget information along the sequence length dimension depending on the current token. Second, even though this change prevents the use of efficient convolutions, we design a hardware-aware parallel algorithm in recurrent mode. We integrate these selective SSMs into a simplified end-to-end neural network architecture without attention or even MLP blocks (Mamba). Mamba enjoys fast inference (5× higher throughput than Transformers) and linear scaling in sequence length, and its performance improves on real data up to million-length sequences. As a general sequence model backbone, Mamba achieves state-of-the-art performance across several modalities such as language, audio, and genomics. On language modeling, our Mamba-3B model outperforms Transformers of the same size and matches Transformers twice its size, both in pre-training and downstream evaluation.

PaperSourceSee Code · state-spaces/mamba

Papers archive 2025-07-28

30 shown of 599, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 384 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Mamba594
State Space Models163
Computational Efficiency62
Semantic Segmentation57
Segmentation37
Image Classification32
Image Segmentation32
Language Modelling32
Object Detection32
Language Modeling30
object-detection30
Decoder29
Medical Image Segmentation29
image-classification29
Time Series24
Super-Resolution23
GPU20
Autonomous Driving19
Time Series Forecasting19
Denoising17

Usage over time archive 2025-07-28

Papers per year tagged with Mamba: 2023 to 2025, peak 307 307 0 2023: 1 paper 2023 2024: 307 papers 2024 2025: 291 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (599 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

The archive places this method in no collection.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections