Methods › Mamba
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
Mamba
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.
In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 35 in the graph, strongest link: official). This answer is about arXiv:2312.00752, the paper the archive credits with this method.
Origin paper of this answer, arXiv:2312.00752 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 28 ran (of which 7 constructed an object rather than computing a result; 20 with no instrument failure: 0 honoured, 0 violated, 20 with no contract checked; 8 where Syntology's instrument failed) · 34 unverified (of 62 harvested samples) · 29 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 599 · with a code link: 272 · where Syntology ran a sample: 65 (56 with a run with no instrument failure, 9 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (65 of 599 tagged: 56 with a run with no instrument failure, 9 where every run was a failure of Syntology's instrument)
Page 1 of 6: papers 1 to 100 of 599, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
Differential Mamba 8 Jul 2025 · 1 repository · arXiv:2507.06204Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)
-
LangMamba: A Language-driven Mamba Framework for Low-dose CT Denoising with Vision-language Models 8 Jul 2025 · 1 repository · arXiv:2507.06140
-
FindRec: Stein-Guided Entropic Flow for Multi-Modal Sequential Recommendation 7 Jul 2025 · 1 repository · arXiv:2507.04651
-
MambaFusion: Height-Fidelity Dense Global Fusion for Multi-modal 3D Object Detection 6 Jul 2025 · 1 repository · arXiv:2507.04369Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified (of 10 harvested samples)
-
MVNet: Hyperspectral Remote Sensing Image Classification Based on Hybrid Mamba-Transformer Vision Backbone Architecture 6 Jul 2025 · 1 repository · arXiv:2507.04409
-
Mamba Guided Boundary Prior Matters: A New Perspective for Generalized Polyp Segmentation 2 Jul 2025 · 1 repository · arXiv:2507.01509
-
MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech Enhancement 1 Jul 2025 · 2 repositories · arXiv:2507.00966
-
Mamba-FETrack V2: Revisiting State Space Model for Frame-Event based Visual Object Tracking 30 Jun 2025 · 1 repository · arXiv:2506.23783
-
EAMamba: Efficient All-Around Vision State Space Model for Image Restoration 27 Jun 2025 · 1 repository · arXiv:2506.22246Syntology official (archive's flag): 12 ran · 12 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 9 where Syntology's instrument failed) · 3 unverified (of 15 harvested samples) · 15 pointer-only (licence)
-
EAGLE: An Efficient Global Attention Lesion Segmentation Model for Hepatic Echinococcosis 25 Jun 2025 · 0 repositories · arXiv:2506.20333
-
FlightKooba: A Fast Interpretable FTP Model 24 Jun 2025 · 0 repositories · arXiv:2506.19885
-
JCAPT: A Joint Modeling Approach for CAPT 24 Jun 2025 · 0 repositories · arXiv:2506.19315
-
Memba: Membrane-driven Parameter-Efficient Fine-Tuning for Mamba 22 Jun 2025 · 0 repositories · arXiv:2506.18184
-
VMRA-MaR: An Asymmetry-Aware Temporal Framework for Longitudinal Breast Cancer Risk Prediction 20 Jun 2025 · 1 repository · arXiv:2506.17412
-
EDNet: A Distortion-Agnostic Speech Enhancement Framework with Gating Mamba Mechanism and Phase Shift-Invariant Training 19 Jun 2025 · 0 repositories · arXiv:2506.16231
-
FADPNet: Frequency-Aware Dual-Path Network for Face Super-Resolution 17 Jun 2025 · 0 repositories · arXiv:2506.14121
-
MT-PCR: A Hybrid Mamba-Transformer with Spatial Serialization for Hierarchical Point Cloud Registration 16 Jun 2025 · 0 repositories · arXiv:2506.13183
-
Scaling Algorithm Distillation for Continuous Control with Mamba 16 Jun 2025 · 0 repositories · arXiv:2506.13892
-
Stereo sound event localization and detection based on PSELDnet pretraining and BiMamba sequence modeling 16 Jun 2025 · 0 repositories · arXiv:2506.13455
-
DART: Differentiable Dynamic Adaptive Region Tokenizer for Vision Transformer and Mamba 12 Jun 2025 · 1 repository · arXiv:2506.10390
-
M4V: Multi-Modal Mamba for Text-to-Video Generation 12 Jun 2025 · 0 repositories · arXiv:2506.10915
-
Sequential-Parallel Duality in Prefix Scannable Models 12 Jun 2025 · 0 repositories · arXiv:2506.10918
-
SparseSSM: Efficient Selective Structured State Space Models Can Be Pruned in One-Shot 11 Jun 2025 · 0 repositories · arXiv:2506.09613
-
ECMNet:Lightweight Semantic Segmentation with Efficient CNN-Mamba Network 10 Jun 2025 · 0 repositories · arXiv:2506.08629
-
InceptionMamba: An Efficient Hybrid Network with Large Band Convolution and Bottleneck Mamba 10 Jun 2025 · 1 repository · arXiv:2506.08735
-
MLVTG: Mamba-Based Feature Alignment and LLM-Driven Purification for Multi-Modal Video Temporal Grounding 10 Jun 2025 · 0 repositories · arXiv:2506.08512
-
SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging 10 Jun 2025 · 0 repositories · arXiv:2506.08297Syntology 10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 3 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified (of 13 harvested samples) · 13 pointer-only (licence)
-
M2Restore: Mixture-of-Experts-based Mamba-CNN Fusion Framework for All-in-One Image Restoration 9 Jun 2025 · 0 repositories · arXiv:2506.07814
-
Flood-DamageSense: Multimodal Mamba with Multitask Learning for Building Flood Damage Assessment using SAR Remote Sensing Imagery 7 Jun 2025 · 1 repository · arXiv:2506.06667
-
DM-SegNet: Dual-Mamba Architecture for 3D Medical Image Segmentation with Global Context Modeling 5 Jun 2025 · 0 repositories · arXiv:2506.05297
-
MesaNet: Sequence Modeling by Locally Optimal Test-Time Training 5 Jun 2025 · 1 repository · arXiv:2506.05233Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)
-
MambaNeXt-YOLO: A Hybrid State Space Model for Real-time Object Detection 4 Jun 2025 · 0 repositories · arXiv:2506.03654
-
3D Skeleton-Based Action Recognition: A Review 1 Jun 2025 · 0 repositories · arXiv:2506.00915
-
General-purpose audio representation learning for real-world sound scenes 1 Jun 2025 · 0 repositories · arXiv:2506.00934
-
Mamba Drafters for Speculative Decoding 1 Jun 2025 · 0 repositories · arXiv:2506.01206
-
PARROT: Synergizing Mamba and Attention-based SSL Pre-Trained Models via Parallel Branch Hadamard Optimal Transport for Speech Emotion Recognition 1 Jun 2025 · 0 repositories · arXiv:2506.01138
-
ACM-UNet: Adaptive Integration of CNNs and Mamba for Efficient Medical Image Segmentation 30 May 2025 · 0 repositories · arXiv:2505.24481
-
Mamba Knockout for Unraveling Factual Information Flow 30 May 2025 · 1 repository · arXiv:2505.24244Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 6 harvested samples) · 1 pointer-only (licence)
-
Mamba Integrated with Physics Principles Masters Long-term Chaotic System Forecasting 29 May 2025 · 0 repositories · arXiv:2505.23863
-
RiverMamba: A State Space Model for Global River Discharge and Flood Forecasting 28 May 2025 · 0 repositories · arXiv:2505.22535Syntology 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 10 harvested samples)
-
HTMNet: A Hybrid Network with Transformer-Mamba Bottleneck Multimodal Fusion for Transparent and Reflective Objects Depth Completion 27 May 2025 · 0 repositories · arXiv:2505.20904
-
OccLE: Label-Efficient 3D Semantic Occupancy Prediction 27 May 2025 · 0 repositories · arXiv:2505.20617
-
Scaling Up Liquid-Resistance Liquid-Capacitance Networks for Efficient Sequence Modeling 27 May 2025 · 0 repositories · arXiv:2505.21717
-
Sparsified State-Space Models are Efficient Highway Networks 27 May 2025 · 1 repository · arXiv:2505.20698
-
Hierarchical Mamba Meets Hyperbolic Geometry: A New Paradigm for Structured Language Embeddings 25 May 2025 · 1 repository · arXiv:2505.18973
-
Latent Mamba Operator for Partial Differential Equations 25 May 2025 · 0 repositories · arXiv:2505.19105
-
TK-Mamba: Marrying KAN with Mamba for Text-Driven 3D Medical Image Segmentation 24 May 2025 · 1 repository · arXiv:2505.18525
-
EVM-Fusion: An Explainable Vision Mamba Architecture with Neural Algorithmic Fusion 23 May 2025 · 0 repositories · arXiv:2505.17367
-
Hybrid Mamba-Transformer Decoder for Error-Correcting Codes 23 May 2025 · 0 repositories · arXiv:2505.17834
-
Selection Mechanisms for Sequence Modeling using Linear State Space Models 23 May 2025 · 0 repositories · arXiv:2505.17932
-
Structured Linear CDEs: Maximally Expressive and Parallel-in-Time Sequence Models 23 May 2025 · 2 repositories · arXiv:2505.17761Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)
-
JanusDNA: A Powerful Bi-directional Hybrid DNA Foundation Model 22 May 2025 · 1 repository · arXiv:2505.17257Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples) · 2 pointer-only (licence)
-
PCMamba: Physics-Informed Cross-Modal State Space Model for Dual-Camera Compressive Hyperspectral Imaging 22 May 2025 · 0 repositories · arXiv:2505.16373
-
SAMba-UNet: Synergizing SAM2 and Mamba in UNet with Heterogeneous Aggregation for Cardiac MRI Segmentation 22 May 2025 · 0 repositories · arXiv:2505.16304
-
FR-Mamba: Time-Series Physical Field Reconstruction Based on State Space Model 21 May 2025 · 0 repositories · arXiv:2505.16083
-
HAMF: A Hybrid Attention-Mamba Framework for Joint Scene Context Understanding and Future Motion Representation Learning 21 May 2025 · 0 repositories · arXiv:2505.15703
-
Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought 21 May 2025 · 0 repositories · arXiv:2505.15431
-
Mechanistic evaluation of Transformers and state space models 21 May 2025 · 0 repositories · arXiv:2505.15105
-
RLBenchNet: The Right Network for the Right Reinforcement Learning Task 21 May 2025 · 1 repository · arXiv:2505.15040
-
SAMA-UNet: Enhancing Medical Image Segmentation with Self-Adaptive Mamba-Like Attention and Causal-Resonance Learning 21 May 2025 · 1 repository · arXiv:2505.15234
-
Scaling Vision Mamba Across Resolutions via Fractal Traversal 20 May 2025 · 0 repositories · arXiv:2505.14062
-
Selective Structured State Space for Multispectral-fused Small Target Detection 20 May 2025 · 0 repositories · arXiv:2505.14043
-
Mamba-Adaptor: State Space Model Adaptor for Visual Recognition 19 May 2025 · 0 repositories · arXiv:2505.12685
-
Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarking 19 May 2025 · 0 repositories · arXiv:2505.12667
-
SourceDetMamba: A Graph-aware State Space Model for Source Detection in Sequential Hypergraphs 19 May 2025 · 0 repositories · arXiv:2505.12910
-
GeoMaNO: Geometric Mamba Neural Operator for Partial Differential Equations 17 May 2025 · 0 repositories · arXiv:2505.12020
-
MedVKAN: Efficient Feature Extraction with Mamba and KAN for Medical Image Segmentation 17 May 2025 · 1 repository · arXiv:2505.11797
-
Multi-modal Collaborative Optimization and Expansion Network for Event-assisted Single-eye Expression Recognition 17 May 2025 · 1 repository · arXiv:2505.12007
-
WaLRUS: Wavelets for Long-range Representation Using SSMs 17 May 2025 · 0 repositories · arXiv:2505.12161
-
HSRMamba: Efficient Wavelet Stripe State Space Model for Hyperspectral Image Super-Resolution 16 May 2025 · 1 repository · arXiv:2505.11062
-
Hybrid-Emba3D: Geometry-Aware and Cross-Path Feature Hybrid Enhanced State Space Model for Point Cloud Classification 16 May 2025 · 1 repository · arXiv:2505.11099
-
Equal is Not Always Fair: A New Perspective on Hyperspectral Representation Non-Uniformity 16 May 2025 · 0 repositories · arXiv:2505.11267
-
HWA-UNETR: Hierarchical Window Aggregate UNETR for 3D Multimodal Gastric Lesion Segmentation 15 May 2025 · 1 repository · arXiv:2505.10464
-
Efficient Malicious UAV Detection Using Autoencoder-TSMamba Integration 14 May 2025 · 0 repositories · arXiv:2505.10585
-
Dyadic Mamba: Long-term Dyadic Human Motion Synthesis 14 May 2025 · 0 repositories · arXiv:2505.09827
-
Efficient LiDAR Reflectance Compression via Scanning Serialization 14 May 2025 · 0 repositories · arXiv:2505.09433
-
HMamba: Hyperbolic Mamba for Sequential Recommendation 14 May 2025 · 0 repositories · arXiv:2505.09205
-
A Mamba-based Network for Semi-supervised Singing Melody Extraction Using Confidence Binary Regularization 13 May 2025 · 1 repository · arXiv:2505.08681
-
Block-Biased Mamba for Long-Range Sequence Processing 13 May 2025 · 0 repositories · arXiv:2505.09022
-
Efficient Unstructured Pruning of Mamba State-Space Models for Resource-Constrained Environments 13 May 2025 · 0 repositories · arXiv:2505.08299
-
ReSurgSAM2: Referring Segment Anything in Surgical Video via Credible Long-term Tracking 13 May 2025 · 1 repository · arXiv:2505.08581
-
ABS-Mamba: SAM2-Driven Bidirectional Spiral Mamba Network for Medical Image Translation 12 May 2025 · 0 repositories · arXiv:2505.07687
-
Probing In-Context Learning: Impact of Task Complexity and Model Architecture on Generalization and Efficiency 10 May 2025 · 1 repository · arXiv:2505.06475
-
Topo-VM-UNetV2: Encoding Topology into Vision Mamba UNet for Polyp Segmentation 9 May 2025 · 0 repositories · arXiv:2505.06210
-
EDmamba: A Simple yet Effective Event Denoising Method with State Space Model 8 May 2025 · 0 repositories · arXiv:2505.05391
-
PillarMamba: Learning Local-Global Context for Roadside Point Cloud via Hybrid State Space Model 8 May 2025 · 0 repositories · arXiv:2505.05397
-
Cross-organ all-in-one parallel compressed sensing magnetic resonance imaging 7 May 2025 · 1 repository · arXiv:2505.04658
-
M2Rec: Multi-scale Mamba for Efficient Sequential Recommendation 7 May 2025 · 0 repositories · arXiv:2505.04445
-
SMMT: Siamese Motion Mamba with Self-attention for Thermal Infrared Target Tracking 7 May 2025 · 0 repositories · arXiv:2505.04088
-
WDMamba: When Wavelet Degradation Prior Meets Vision Mamba for Image Dehazing 7 May 2025 · 1 repository · arXiv:2505.04369
-
DiffVQA: Video Quality Assessment Using Diffusion Feature Extractor 6 May 2025 · 0 repositories · arXiv:2505.03261
-
Recall with Reasoning: Chain-of-Thought Distillation for Mamba's Long-Context Memory and Extrapolation 6 May 2025 · 0 repositories · arXiv:2505.03320
-
Text to Image Generation and Editing: A Survey 5 May 2025 · 0 repositories · arXiv:2505.02527
-
Meta-Black-Box-Optimization through Offline Q-function Learning 4 May 2025 · 1 repository · arXiv:2505.02010Syntology official (archive's flag): 4 ran · 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified (of 8 harvested samples) · 2 pointer-only (licence)
-
Design description of Wisdom Computing Persperctive 2 May 2025 · 0 repositories · arXiv:2505.03800
-
LMDepth: Lightweight Mamba-based Monocular Depth Estimation for Real-World Deployment 2 May 2025 · 0 repositories · arXiv:2505.00980
-
RD-UIE: Relation-Driven State Space Modeling for Underwater Image Enhancement 2 May 2025 · 1 repository · arXiv:2505.01224
-
Vision Mamba in Remote Sensing: A Comprehensive Survey of Techniques, Applications and Outlook 1 May 2025 · 1 repository · arXiv:2505.00630
-
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures 29 Apr 2025 · 0 repositories · arXiv:2504.20922
-
Mamba-Sea: A Mamba-based Framework with Global-to-Local Sequence Augmentation for Generalizable Medical Image Segmentation 24 Apr 2025 · 1 repository · arXiv:2504.17515
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.
Usage over time archive 2025-07-28
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