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.

Recent papers

• A note on data-efficient finetuning of vision foundation models
  Niclas Hergenröther, Antonio Orvieto · arXiv · Oct 27, 2026

  Adapting foundation models to a new task within or beyond the training domain is the de facto standard for building specialized machine learning models. Recently, Visual Prompting (VP) has emerged as a promising technique for efficient know…

• A theory of noisy linear recurrent neural network learning dynamics
  John J. Vastola, Kanaka Rajan · arXiv · Oct 26, 2026

  Biological neural networks are noisy: their dynamics involve difficult-to-predict fluctuations which are likely due not just to chaos, but also to a variety of low-level biophysical processes. Despite the omnipresence of intrinsic noise, it…

• GraphCast-Mamba: Learning Non-Markovian Corrections for Weather Forecasting
  Ilya Vilkoviskiy, Liang-Hong Mo, Suozhi Huang, Dmitry A. Abanin · arXiv · Oct 20, 2026

  Unresolved atmospheric processes can introduce history dependence beyond the short input windows used by many weather forecasting models. We introduce GraphCast--Mamba, which augments a frozen, pretrained $1^\circ$ GraphCast backbone with a…

• Model- and Layer-Level Closed-Loop Forecasting with SSM-Based Spiking Neural Networks
  Erik Stolt, Sanja Karilanova, Ayca Ozcelikkale · arXiv · Oct 20, 2026

  Deep State-Space Models (Deep SSMs) have shown promising performance and computational benefits in processing of time-series data with complex temporal dependencies. Spiking neural networks (SNNs) constitute a biologically inspired class of…

• Kronecker Delta Rule for Long Context Linear Attention
  Anamaria-Roberta Hartl, Levente Zólyomi, Michael List, Günter Klambauer et al. · arXiv · Oct 19, 2026

  We propose KronLSTM, a linear attention architecture based on the Kronecker Delta Rule, a novel update rule for associative matrix memories. KronLSTM extends the xLSTM family with a memory-revision mechanism that corrects targeted associati…

• ReplaySSM: Cache SSM Inputs, Not State
  Ze-Wei Liou, Harris Nover, Amey Naik, Andrii Skliar et al. · arXiv · Oct 9, 2026

  State-space models (SSMs) maintain a fixed-size recurrent state, but reading and writing it at every decoding step can bottleneck hybrid models. This eager state management causes large state I/O with low arithmetic intensity, leaves specul…

• Decoupling Exploration from Optimization in RLVR
  Saif Punjwani, Micah Goldblum · arXiv · Oct 7, 2026

  Modern language models undergo reinforcement learning with verifiable rewards (RLVR) on top of already-trained checkpoints. A key promise of RLVR is the discovery of new reasoning strategies. In principle, a model can sample novel ideas abs…

• IdeaLens: Detecting AI Ideas in Long-form Writing
  Rishanth Rajendhran, Minjoon Choi, Jenna Russell, Ramya Namuduri et al. · arXiv · Oct 5, 2026

  While modern AI detectors identify who wrote the words, emerging policies on AI use increasingly hinge on a different question: who came up with the ideas? We introduce IdeaLens, a detector that identifies whether a document's ideas came fr…

• DR-net-Mamba: Selective State-Space Modeling for Long-Range ECG Time-Series Denoising
  Basile Morel, Samuel Ruiperez-Campillo, Andreas P. Streich, Julia E. Vogt et al. · arXiv · Sep 28, 2026

  Electrocardiogram (ECG) recordings are corrupted by non-stationary noise sources that degrade diagnostic reliability, particularly in ambulatory and long-duration recordings. Deep learning denoisers exist, but convolutional architectures ar…

• Non-Commutative State Tracking with Input-Dependent Low-Rank Updates in Mamba-3
  Hiroki Fujii, Masaki Yamakita · arXiv · Sep 23, 2026

  State tracking from sequential observations can require both retaining information and updating it by composing observed operations. We extend Mamba-3's diagonal transition with an input-dependent low-rank reflection term to support noncomm…

• hyperbolix: Hyperbolic Deep Learning in JAX
  Timo Klein, Thomas Lang, Yllka Velaj, Sebastian Tschiatschek · arXiv · Sep 23, 2026

  We present hyperbolix, an open-source library for hyperbolic deep learning in JAX, built on Flax NNX. To our knowledge, it is the first comprehensive, general-purpose hyperbolic deep learning library in JAX. It includes six manifolds with a…

• Adaptive Uncertainty-Aware Modeling and Stochastic Radial Basis Function Predictive Control for Personalized Fluid Resuscitation
  Elham Estiri, Hossein Mirinejad · arXiv · Sep 18, 2026

  This paper presents a novel framework integrating Bayesian physiological modeling with optimal control strategies to achieve uncertainty-aware, personalized hemodynamic regulation during fluid resuscitation. An uncertainty-aware variational…

• Selective Operation Quantization for Vision State Space Models
  Yinglong Li, Xiaoyu Liu, Yinuo Liao, Jiacheng Li et al. · LoViF Oral · Sep 8, 2026

  State Space Models (SSMs), as key components of Mamba, have gained increasing attention for vision models recently. Given the computational cost of deploying SSMs on resource-limited edge devices, Post-Training Quantization (PTQ) is a tech…

• LoRA-TSD: Tangent-Space Spectral Descent for LoRA via Muon-Style Updates
  Dmitrii Andriianov, Andrey Veprikov, Aleksandr Beznosikov · arXiv · Sep 2, 2026

  Low-rank adaptation (LoRA) is the standard way to fine-tune large models, yet when its two factors are trained independently, the update ignores the geometry of the low-rank weight change it induces. We introduce LoRA-TSD, an optimizer that…

• EAMamba: Efficient All-Around Vision State Space Model for Image Restoration
  Yu-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 Model
  Zhe-Yu Zhang, Yayuan Lu, Fei-Peng 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…

• Dynamic Process Monitoring Using Total Multirate Linear Gaussian State Space Model
  Dong-Lei 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…

• Semi-Supervised State-Space Model with Dynamic Stacking Filter for Real-World Video Deraining
  Shang-Quan Sun, Wen-Qi Ren, Ju-Xiang Zhou, Shu Wang et al. · Computer Vision and Pattern Recognition · May 22, 2025

  Significant progress has been made in video restoration under rainy conditions over the past decade, largely propelled by advancements in deep learning. Nevertheless, existing methods that depend on paired data struggle to generalize effect…

• StegMamba: Distortion-Free Immune-Cover for Multi-Image Steganography With State Space Model
  Ting Luo, Yu-Hang Zhou, Zhou-Yan He, Gang-Yi 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…

• DefMamba: Deformable Visual State Space Model
  Lei-Ye Liu, Miao Zhang, Jihao Yin, Ting-Wei 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…

• DAMamba: Vision State Space Model with Dynamic Adaptive Scan
  Tanzhe Li, Caoshuo Li, Jiayi Lyu, Hongjuan Pei et al. · Neural Information Processing Systems · Feb 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 …

• HSRMamba: Contextual Spatial-Spectral State Space Model for Single Hyperspectral Super-Resolution
  Shi Chen, L. Zhang, Liang-Pei Zhang · International Joint Conference on Artificial Intelligence · Jan 30, 2025

  Mamba has demonstrated exceptional performance in visual tasks due to its powerful global modeling capabilities and linear computational complexity, offering considerable potential in hyperspectral image super-resolution (HSISR). However, i…

• Directing Mamba to Complex Textures: An Efficient Texture-Aware State Space Model for Image Restoration
  Long Peng, Xin Di, Zhan-Feng 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…

• SSM2Mel: State Space Model to Reconstruct Mel Spectrogram from the EEG
  Cun-Hang Fan, Sheng Zhang, Jingjing Zhang, Zexu Pan et al. · IEEE International Conference on Acoustics, Speech, and Signal Processing · Jan 3, 2025

  Decoding speech from brain signals is a challenging research problem that holds significant importance for studying speech processing in the brain. Although breakthroughs have been made in reconstructing the mel spectrograms of audio stimul…

• GLVMamba: A Global–Local Visual State-Space Model for Remote Sensing Image Segmentation
  Hui-Hui Li, Huajian Pan, Xiao-Yong Liu, Jin-Chang Ren et al. · IEEE Transactions on Geoscience and Remote Sensing · Jan 1, 2025

  Semantic segmentation of remote sensing images (RSIs) has significant advances with the adoption of deep neural networks, taking the advantages of convolutional neural networks (CNNs) in local feature extraction with transformers in global …

• FMambaIR: A Hybrid State-Space Model and Frequency Domain for Image Restoration
  Xin Luan, Huijie Fan, Qiang Wang, Nan Yang et al. · IEEE Transactions on Geoscience and Remote Sensing · Jan 1, 2025

  With the development of deep learning, impressive progress has been made in the field of image restoration. The existing methods mainly rely on CNNs and Transformers to obtain multiscale feature information. However, these methods rarely in…

• A Lightweight Semantic Segmentation Network Based on Self-Attention Mechanism and State Space Model for Efficient Urban Scene Segmentation
  Langping Li, Ji-Zheng Yi, Hui Fan, Hui Lin · IEEE Transactions on Geoscience and Remote Sensing · Jan 1, 2025

  In the semantic segmentation of remote sensing images, methods based on convolutional neural networks (CNNs) and Transformers have been extensively studied. Nevertheless, CNN struggles to capture the global context due to its local feature …

• LCCDMamba: Visual State Space Model for Land Cover Change Detection of VHR Remote Sensing Images
  Jun Huang, Xiaochen Yuan, Chan-Tong Lam, Yapeng Wang et al. · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · Jan 1, 2025

  Land cover change detection (LCCD) is a crucial research topic for rational planning of land use and facilitation of sustainable land resource growth. However, due to the complexity of LCCD tasks, integrating global and local features and f…

• Mamba-CR: A State-Space Model for Remote Sensing Image Cloud Removal
  Chengyao Zhang, Feng-Yan Wang, Xu-Qing Zhang, Ming-Chang Wang et al. · IEEE Transactions on Geoscience and Remote Sensing · Jan 1, 2025

  Cloud removal is a critical step to improve the usability of cloud-contaminated remote sensing images. Deep learning methods based on convolutional neural networks (CNNs) and transformer architectures are widely used for cloud removal tasks…

• AfaMamba: Adaptive Feature Aggregation With Visual State Space Model for Remote Sensing Images Semantic Segmentation
  Hong-Kun Chen, Huilan Luo, Chanjuan Wang · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · Jan 1, 2025

  Remote sensing images semantic segmentation is typically challenging due to the complexity of land cover information. Existing convolutional neural network (CNN)-based models lack the capability to model long-range dependencies, while Trans…