Latest State Space Models (Mamba) Research Papers
The newest State Space Models (Mamba) papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks State Space Models (Mamba) so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.
Get the latest State Space Models (Mamba) papers in your inbox — free →Recent papers
- User-Centric Modeling of Transactional Sequences with Explainable State Space ModelsIvan Palagin · arXiv · Jul 22, 2026
We propose a hybrid approach for user-centric modeling of transactional event sequences that combines contrastive representation learning (CoLES) with State Space Models (SSMs). While contrastive methods yield high-quality compressed user r…
- An Exact Instrument for State Usage in Selective State-Space Models, and the Input-Driven Migration It RevealsRaktim Bhattacharya · arXiv · Jul 13, 2026
Selective state-space models such as Mamba route information through a bank of first-order modes whose input coupling is set by a learned selection mechanism. We give an exact instrument for measuring how a trained model uses these modes. B…
- A Sovereign, Open-Source Foundation Model for German and EnglishThe Soofi-Team, :, Benedikt Droste, David Fitzek et al. · arXiv · Jul 10, 2026
We present Soofi S 30B-A3B, a sovereign, open-source Mixture-of-Experts (MoE) hybrid Mamba Transformer foundation model for German and English. Its hybrid design activates only 3B of 30B parameters per token and keeps the inference cache ne…
- TriA Pipeline: A Large-Scale Automatic Audio Annotation Pipeline For Audio Classification In Specific ScenariosHong Lyu, Mingru Yang, Qianhua He, Yanxiong Li et al. · arXiv · Jul 7, 2026
There are some datasets of varying scales for audio classification (AC) applied to different tasks. However, annotated data is limited for most scenarios, such as domestic environments. To address this challenge, we propose an $\textbf{A}$u…
- Hedgementation = Hedgerow Segmentation: A Remote Sensing BenchmarkNathan Senyard, Salem Hamdani, Astrid Zhang, Derek Wang et al. · arXiv · Jun 22, 2026
We propose Hedgementation: a new benchmark to evaluate machine learning models for hedgerow mapping from remote sensing data at country scale and 10m$^2$ spatial resolution. We combine and harmonize multiple remote sensing data products and…
- Scaling Linear Mode Connectivity and Merging to Billion Parameter Pretrained TransformersTianyi Li, Zhiqiang Shen · arXiv · Jun 22, 2026
Linear mode connectivity (LMC) provides a promising foundation for understanding and merging independently trained neural networks, but existing methods typically optimize the interpolation path from only one model endpoint, limiting their …
- Ternary Mamba: Grouped Quantization-Aware Training of W1.58A16 State Space ModelsRamprasath Ganesaraja, Sahil Dilip Panse, Swathika N · arXiv · Jun 16, 2026
State Space Models (SSMs) such as Mamba-2 offer linear-time inference but their memory footprint limits edge deployment. Prior ternary SSM work (Slender-Mamba) trains from scratch on 150B tokens; we show a pretrained checkpoint suffices, re…
- S4oP: Operator-level Pruning of Structured State Space Models for Resource-Constrained DevicesMarco Deano, Filippo Ziche, Nicola Bombieri · arXiv · Jun 16, 2026
Structured State Space Models (SSMs), including the S4 and S4D architectures, have recently emerged as powerful alternatives to attention-based models for capturing long-range dependencies in sequential data. Despite their strong empirical …
- On Subquadratic Architectures: From Applications to PrinciplesAnamaria-Roberta Hartl, Levente Zólyomi, David Stap, Pieter-Jan Hoedt et al. · arXiv · Jun 10, 2026
Transformers dominate modern sequence modeling, but their quadratic attention incurs substantial computational cost. Subquadratic architectures offer a scalable alternative. However, it remains unclear which designs yield the most effective…
- Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding TasksMengyu Zheng, Kai Han, Boxun Li, Haiyang Xu et al. · arXiv · Jun 10, 2026
General-purpose agents such as OpenClaw are increasingly used as autonomous tool users, but their coding ability is difficult to measure under SWE-bench: a generic agent does not by itself satisfy the clean Docker workspace, patch, and pred…
- OncoTraj: a public benchmark for longitudinal resistance prediction in EGFR-mutant non-small-cell lung cancer on osimertinibAbhijoy Sarkar, Aarchi Singh Thakur · arXiv · Jun 9, 2026
Resistance to first-line osimertinib in EGFR-mutant non-small-cell lung cancer (NSCLC) is the canonical example of predictable clonal evolution under therapeutic pressure, yet no public benchmark exists for training or evaluating computatio…
- CaMBRAIN: Real-time, Continuous EEG Inference with Causal State Space ModelsAbhilash Durgam, Nyle Siddiqui, Jeffrey A. Chan-Santiago, Qiushi Fu et al. · arXiv · May 27, 2026
Electroencephalography (EEG) is a critical, non-invasive method to monitor electrical brain activity. EEGs can span anywhere from a couple seconds to multiple hours, posing a major hurdle for existing deep learning methods due to two major …
- Multi-Mixer Models: Flexible Sequence Modeling with Shared RepresentationsKevin Y. Li, Asher Trockman, Ananda Theertha Suresh, Ziteng Sun · arXiv · May 27, 2026
Softmax attention is the cornerstone of modern large language models, but its memory scales linearly and compute quadratically with sequence length. Linear recurrent models, such as linear attention and state space models, have become widel…
- DAMamba: Vision State Space Model with Dynamic Adaptive ScanTanzhe Li, Caoshuo Li, Jiayi Lyu, Hongjuan Pei et al. · NeurIPS 2025 poster · Sep 18, 2025
State space models (SSMs) have recently garnered significant attention in computer vision. However, due to the unique characteristics of image data, adapting SSMs from natural language processing to computer vision has not outperformed the …
- HG-Mamba: Heuristic-Guided State Space Model for Laparoscopic Image DesmokingShiweiWu, XiaoboZhu, Song Zhang, Yu An et al. · ICLR 2026 Conference Withdrawn Submission · Sep 16, 2025
Developing smoke removal algorithms for laparoscopic surgery is crucial for enhancing surgical visibility and supporting accurate intraoperative decision-making. Recently, Mamba, a representative state space model (SSM), has shown strong po…
- SF-Mamba: Rethinking State Space Model for VisionMasakazu Yoshimura, Teruaki Hayashi, Yuki Hoshino, Wei-Yao Wang et al. · Submitted to ICLR 2026 · Sep 14, 2025
The realm of Mamba for vision has been advanced in recent years to strike for the alternatives of Vision Transformers (ViTs) that suffer from the quadratic complexity. While the recurrent scanning mechanism of Mamba offers computational eff…
- EAMamba: Efficient All-Around Vision State Space Model for Image RestorationYu-Cheng Lin, Yu-Syuan Xu, Hao-Wei Chen, Hsien-Kai Kuo et al. · IEEE International Conference on Computer Vision · Jun 27, 2025
Image restoration is a key task in low-level computer vision that aims to reconstruct high-quality images from degraded inputs. The emergence of Vision Mamba, which draws inspiration from the advanced state space model Mamba, marks a signif…
- Incomplete Multi-modal Brain Tumor Segmentation via Learnable Sorting State Space ModelZheyu Zhang, Yayuan Lu, Feipeng Ma, Yueyi Zhang et al. · Computer Vision and Pattern Recognition · Jun 10, 2025
Brain tumor segmentation plays a crucial role in clinical diagnosis, yet the frequent unavailability of certain MRI modalities poses a significant challenge. In this paper, we introduce the Learnable Sorting State Space Model (LS3M), a nove…
- ProtMamba: a homology-aware but alignment-free protein state space modelDamiano Sgarbossa, Cyril Malbranke, Anne-Florence Bitbol · bioRxiv · Jun 1, 2025
Motivation Protein language models are enabling advances in elucidating the sequence-to-function mapping, and have important applications in protein design. Models based on multiple sequence alignments efficiently capture the evolutionary i…
- Dynamic Process Monitoring Using Total Multirate Linear Gaussian State Space ModelDonglei Zheng, Le Zhou, Yi Liu, Qiang Liu · IEEE Transactions on Industrial Informatics · Jun 1, 2025
Conventional data-driven dynamic process monitoring methods usually rely on data collected at a single sampling rate. The effectiveness of these approaches typically diminishes when analyzing data from multiple sampling rates. To address th…
- Sub-Sequential Physics-Informed Learning with State Space ModelChenhui Xu, Dancheng Liu, Yuting Hu, Jiajie Li et al. · ICML 2025 poster · May 1, 2025
Physics-Informed Neural Networks (PINNs) are a kind of deep-learning-based numerical solvers for partial differential equations (PDEs). Existing PINNs often suffer from failure modes of being unable to propagate patterns of initial conditio…
- StegMamba: Distortion-Free Immune-Cover for Multi-Image Steganography With State Space ModelTing Luo, Yuhang Zhou, Zhouyan He, Gangyi Jiang et al. · IEEE transactions on circuits and systems for video technology (Print) · May 1, 2025
Multi-image steganography ensures privacy protection while avoiding suspicion from third parties by embedding multiple secret images within a cover image. However, existing multi-image steganographic methods fail to model global spatial cor…
- Pamba: Enhancing Global Interaction in Point Clouds via State Space ModelZhuoyuan Li, Yubo Ai, Jiahao Lu, Chuxin Wang et al. · AAAI Conference on Artificial Intelligence · Apr 11, 2025
Transformers have demonstrated impressive results for 3D point cloud semantic segmentation. However, the quadratic complexity of transformer makes computation costs high, limiting the number of points that can be processed simultaneously an…
- PoseMamba: Monocular 3D Human Pose Estimation with Bidirectional Global-Local Spatio-Temporal State Space ModelYunlong Huang, Junshuo Liu, Ke Xian, Robert C. Qiu · AAAI Conference on Artificial Intelligence · Apr 11, 2025
Transformers have significantly advanced the field of 3D human pose estimation (HPE). However, existing transformer-based methods primarily use self-attention mechanisms for spatio-temporal modeling, leading to a quadratic complexity, unidi…
- DefMamba: Deformable Visual State Space ModelLeiye Liu, Miao Zhang, Jihao Yin, Tingwei Liu et al. · Computer Vision and Pattern Recognition · Apr 8, 2025
Recently, state space models (SSM), particularly Mamba, have attracted significant attention from scholars due to their ability to effectively balance computational efficiency and performance. However, most existing visual Mamba methods fla…
- InsectMamba: State Space Model with Adaptive Composite Features for Insect RecognitionQianning Wang, Yucheng Zhou, Zhixin Lai, Yucheng Zhou · IEEE International Conference on Acoustics, Speech, and Signal Processing · Apr 6, 2025
The recognition of insect pests is a critical task in agricultural technology, vital for ensuring food security and environmental sustainability. However, due to factors like high camouflage and species diversity, the complexity of pest ide…
- SaMam: Style-aware State Space Model for Arbitrary Image Style TransferHongda Liu, Longguang Wang, Ye Zhang, Ziru Yu et al. · Computer Vision and Pattern Recognition · Mar 20, 2025
Global effective receptive field plays a crucial role for image style transfer (ST) to obtain high-quality stylized results. However, existing ST backbones (e.g., CNNs and Transformers) suffer huge computational complexity to achieve global…
- Koopman-Constrained Hierarchical Deep State Space Model for Industrial Quality Prediction via Cloud-Edge Collaborative FrameworkQingkai Sui, Yalin Wang, Chenliang Liu, Minghao Han et al. · IEEE Transactions on Systems, Man, and Cybernetics: Systems · Feb 1, 2025
In cloud manufacturing of industrial processes, the accurate online prediction of product quality is the basis for realizing decision-making and control of the manufacturing process. However, frequent fluctuations in working conditions and …
- Directing Mamba to Complex Textures: An Efficient Texture-Aware State Space Model for Image RestorationLong Peng, Xin Di, Zhanfeng Feng, Wenbo Li et al. · International Joint Conference on Artificial Intelligence · Jan 27, 2025
Image restoration aims to recover details and enhance contrast in degraded images. With the growing demand for high-quality imaging (e.g., 4K and 8K), achieving a balance between restoration quality and computational efficiency has become i…
- CD-Lamba: Boosting Remote Sensing Change Detection via a Cross-Temporal Locally Adaptive State Space ModelZhenkai Wu, Xiaowen Ma, Rongrong Lian, Kai Zheng et al. · arXiv.org · Jan 26, 2025
Mamba, with its advantages of global perception and linear complexity, has been widely applied to identify changes of the target regions within the remote sensing (RS) images captured under complex scenarios and varied conditions. However, …