Hyperspectral image (HSI) classification faces challenges such as high-dimensional data, limited training samples, and spectral redundancy, which often lead to overfitting and insufficient generalization capability. This paper proposes a novel MVNet network architecture that integrates 3D-CNN's local feature extraction, Transformer's global modeling, and Mamba's linear complexity sequence modeling capabilities, achieving efficient spatial-spectral feature extraction and fusion. MVNet features a redesigned dual-branch Mamba module, including a State Space Model (SSM) branch and a non-SSM branch employing 1D convolution with SiLU activation, enhancing modeling of both short-range and long-range dependencies while reducing computational latency in traditional Mamba. The optimized HSI-MambaVision Mixer module overcomes the unidirectional limitation of causal convolution, capturing bidirectional spatial-spectral dependencies in a single forward pass through decoupled attention that focuses on high-value features, alleviating parameter redundancy and the curse of dimensionality. On IN, UP, and KSC datasets, MVNet outperforms mainstream hyperspectral image classification methods in both classification accuracy and computational efficiency, demonstrating robust capability in processing complex HSI data.
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 significant advancement in this field. Vision Mamba demonstrates excellence in modeling long-range dependencies with linear complexity, a crucial advantage for image restoration tasks. Despite its strengths, Vision Mamba encounters challenges in low-level vision tasks, including computational complexity that scales with the number of scanning sequences and local pixel forgetting. To address these limitations, this study introduces Efficient All-Around Mamba (EAMamba), an enhanced framework that incorporates a Multi-Head Selective Scan Module (MHSSM) with an all-around scanning mechanism. MHSSM efficiently aggregates multiple scanning sequences, which avoids increases in computational complexity and parameter count. The all-around scanning strategy implements multiple patterns to capture holistic information and resolves the local pixel forgetting issue. Our experimental evaluations validate these innovations across several restoration tasks, including super resolution, denoising, deblurring, and dehazing. The results validate that EAMamba achieves a significant 31-89% reduction in FLOPs while maintaining favorable performance compared to existing low-level Vision Mamba methods.
Sequence models like Transformers and RNNs often overallocate attention to irrelevant context, leading to noisy intermediate representations. This degrades LLM capabilities by promoting hallucinations, weakening long-range and retrieval abilities, and reducing robustness. Recent work has shown that differential design can mitigate this issue in Transformers, improving their effectiveness across various applications. In this paper, we explore whether these techniques, originally developed for Transformers, can be applied to Mamba, a recent architecture based on selective state-space layers that achieves Transformer-level performance with greater efficiency. We show that a naive adaptation of differential design to Mamba is insufficient and requires careful architectural modifications. To address this, we introduce a novel differential mechanism for Mamba, empirically validated on language modeling benchmarks, demonstrating improved retrieval capabilities and superior performance over vanilla Mamba. Finally, we conduct extensive ablation studies and empirical analyses to justify our design choices and provide evidence that our approach effectively mitigates the overallocation problem in Mamba-based models. Our code is publicly available.
Low-dose computed tomography (LDCT) reduces radiation exposure but often degrades image quality, potentially compromising diagnostic accuracy. Existing deep learning-based denoising methods focus primarily on pixel-level mappings, overlooking the potential benefits of high-level semantic guidance. Recent advances in vision-language models (VLMs) suggest that language can serve as a powerful tool for capturing structured semantic information, offering new opportunities to improve LDCT reconstruction. In this paper, we introduce LangMamba, a Language-driven Mamba framework for LDCT denoising that leverages VLM-derived representations to enhance supervision from normal-dose CT (NDCT). LangMamba follows a two-stage learning strategy. First, we pre-train a Language-guided AutoEncoder (LangAE) that leverages frozen VLMs to map NDCT images into a semantic space enriched with anatomical information. Second, we synergize LangAE with two key components to guide LDCT denoising: Semantic-Enhanced Efficient Denoiser (SEED), which enhances NDCT-relevant local semantic while capturing global features with efficient Mamba mechanism, and Language-engaged Dual-space Alignment (LangDA) Loss, which ensures that denoised images align with NDCT in both perceptual and semantic spaces. Extensive experiments on two public datasets demonstrate that LangMamba outperforms conventional state-of-the-art methods, significantly improving detail preservation and visual fidelity. Remarkably, LangAE exhibits strong generalizability to unseen datasets, thereby reducing training costs. Furthermore, LangDA loss improves explainability by integrating language-guided insights into image reconstruction and offers a plug-and-play fashion. Our findings shed new light on the potential of language as a supervisory signal to advance LDCT denoising. The code is publicly available on https://github.com/hao1635/LangMamba.
Modern recommendation systems face significant challenges in processing multimodal sequential data, particularly in temporal dynamics modeling and information flow coordination. Traditional approaches struggle with distribution discrepancies between heterogeneous features and noise interference in multimodal signals. We propose \textbf{FindRec}~ (\textbf{F}lexible unified \textbf{in}formation \textbf{d}isentanglement for multi-modal sequential \textbf{Rec}ommendation), introducing a novel "information flow-control-output" paradigm. The framework features two key innovations: (1) A Stein kernel-based Integrated Information Coordination Module (IICM) that theoretically guarantees distribution consistency between multimodal features and ID streams, and (2) A cross-modal expert routing mechanism that adaptively filters and combines multimodal features based on their contextual relevance. Our approach leverages multi-head subspace decomposition for routing stability and RBF-Stein gradient for unbiased distribution alignment, enhanced by linear-complexity Mamba layers for efficient temporal modeling. Extensive experiments on three real-world datasets demonstrate FindRec's superior performance over state-of-the-art baselines, particularly in handling long sequences and noisy multimodal inputs. Our framework achieves both improved recommendation accuracy and enhanced model interpretability through its modular design. The implementation code is available anonymously online for easy reproducibility~\footnote{https://github.com/Applied-Machine-Learning-Lab/FindRec}.
Polyp segmentation in colonoscopy images is crucial for early detection and diagnosis of colorectal cancer. However, this task remains a significant challenge due to the substantial variations in polyp shape, size, and color, as well as the high similarity between polyps and surrounding tissues, often compounded by indistinct boundaries. While existing encoder-decoder CNN and transformer-based approaches have shown promising results, they struggle with stable segmentation performance on polyps with weak or blurry boundaries. These methods exhibit limited abilities to distinguish between polyps and non-polyps and capture essential boundary cues. Moreover, their generalizability still falls short of meeting the demands of real-time clinical applications. To address these limitations, we propose SAM-MaGuP, a groundbreaking approach for robust polyp segmentation. By incorporating a boundary distillation module and a 1D-2D Mamba adapter within the Segment Anything Model (SAM), SAM-MaGuP excels at resolving weak boundary challenges and amplifies feature learning through enriched global contextual interactions. Extensive evaluations across five diverse datasets reveal that SAM-MaGuP outperforms state-of-the-art methods, achieving unmatched segmentation accuracy and robustness. Our key innovations, a Mamba-guided boundary prior and a 1D-2D Mamba block, set a new benchmark in the field, pushing the boundaries of polyp segmentation to new heights.
Combining traditional RGB cameras with bio-inspired event cameras for robust object tracking has garnered increasing attention in recent years. However, most existing multimodal tracking algorithms depend heavily on high-complexity Vision Transformer architectures for feature extraction and fusion across modalities. This not only leads to substantial computational overhead but also limits the effectiveness of cross-modal interactions. In this paper, we propose an efficient RGB-Event object tracking framework based on the linear-complexity Vision Mamba network, termed Mamba-FETrack V2. Specifically, we first design a lightweight Prompt Generator that utilizes embedded features from each modality, together with a shared prompt pool, to dynamically generate modality-specific learnable prompt vectors. These prompts, along with the modality-specific embedded features, are then fed into a Vision Mamba-based FEMamba backbone, which facilitates prompt-guided feature extraction, cross-modal interaction, and fusion in a unified manner. Finally, the fused representations are passed to the tracking head for accurate target localization. Extensive experimental evaluations on multiple RGB-Event tracking benchmarks, including short-term COESOT dataset and long-term datasets, i.e., FE108 and FELT V2, demonstrate the superior performance and efficiency of the proposed tracking framework. The source code and pre-trained models will be released on https://github.com/Event-AHU/Mamba_FETrack
We present the first work demonstrating that a pure Mamba block can achieve efficient Dense Global Fusion, meanwhile guaranteeing top performance for camera-LiDAR multi-modal 3D object detection. Our motivation stems from the observation that existing fusion strategies are constrained by their inability to simultaneously achieve efficiency, long-range modeling, and retaining complete scene information. Inspired by recent advances in state-space models (SSMs) and linear attention, we leverage their linear complexity and long-range modeling capabilities to address these challenges. However, this is non-trivial since our experiments reveal that simply adopting efficient linear-complexity methods does not necessarily yield improvements and may even degrade performance. We attribute this degradation to the loss of height information during multi-modal alignment, leading to deviations in sequence order. To resolve this, we propose height-fidelity LiDAR encoding that preserves precise height information through voxel compression in continuous space, thereby enhancing camera-LiDAR alignment. Subsequently, we introduce the Hybrid Mamba Block, which leverages the enriched height-informed features to conduct local and global contextual learning. By integrating these components, our method achieves state-of-the-art performance with the top-tire NDS score of 75.0 on the nuScenes validation benchmark, even surpassing methods that utilize high-resolution inputs. Meanwhile, our method maintains efficiency, achieving faster inference speed than most recent state-of-the-art methods.
With the advent of new sequence models like Mamba and xLSTM, several studies have shown that these models match or outperform state-of-the-art models in single-channel speech enhancement, automatic speech recognition, and self-supervised audio representation learning. However, prior research has demonstrated that sequence models like LSTM and Mamba tend to overfit to the training set. To address this issue, previous works have shown that adding self-attention to LSTMs substantially improves generalization performance for single-channel speech enhancement. Nevertheless, neither the concept of hybrid Mamba and time-frequency attention models nor their generalization performance have been explored for speech enhancement. In this paper, we propose a novel hybrid architecture, MambAttention, which combines Mamba and shared time- and frequency-multi-head attention modules for generalizable single-channel speech enhancement. To train our model, we introduce VoiceBank+Demand Extended (VB-DemandEx), a dataset inspired by VoiceBank+Demand but with more challenging noise types and lower signal-to-noise ratios. Trained on VB-DemandEx, our proposed MambAttention model significantly outperforms existing state-of-the-art LSTM-, xLSTM-, Mamba-, and Conformer-based systems of similar complexity across all reported metrics on two out-of-domain datasets: DNS 2020 and EARS-WHAM_v2, while matching their performance on the in-domain dataset VB-DemandEx. Ablation studies highlight the role of weight sharing between the time- and frequency-multi-head attention modules for generalization performance. Finally, we explore integrating the shared time- and frequency-multi-head attention modules with LSTM and xLSTM, which yields a notable performance improvement on the out-of-domain datasets. However, our MambAttention model remains superior on both out-of-domain datasets across all reported evaluation metrics.
Magnetic Resonance Imaging (MRI) reconstruction is essential in medical diagnostics. As the latest generative models, diffusion models (DMs) have struggled to produce high-fidelity images due to their stochastic nature in image domains. Latent diffusion models (LDMs) yield both compact and detailed prior knowledge in latent domains, which could effectively guide the model towards more effective learning of the original data distribution. Inspired by this, we propose Multi-domain Diffusion Prior Guidance (MDPG) provided by pre-trained LDMs to enhance data consistency in MRI reconstruction tasks. Specifically, we first construct a Visual-Mamba-based backbone, which enables efficient encoding and reconstruction of under-sampled images. Then pre-trained LDMs are integrated to provide conditional priors in both latent and image domains. A novel Latent Guided Attention (LGA) is proposed for efficient fusion in multi-level latent domains. Simultaneously, to effectively utilize a prior in both the k-space and image domain, under-sampled images are fused with generated full-sampled images by the Dual-domain Fusion Branch (DFB) for self-adaption guidance. Lastly, to further enhance the data consistency, we propose a k-space regularization strategy based on the non-auto-calibration signal (NACS) set. Extensive experiments on two public MRI datasets fully demonstrate the effectiveness of the proposed methodology. The code is available at https://github.com/Zolento/MDPG.
Breast cancer remains a leading cause of mortality worldwide and is typically detected via screening programs where healthy people are invited in regular intervals. Automated risk prediction approaches have the potential to improve this process by facilitating dynamically screening of high-risk groups. While most models focus solely on the most recent screening, there is growing interest in exploiting temporal information to capture evolving trends in breast tissue, as inspired by clinical practice. Early methods typically relied on two time steps, and although recent efforts have extended this to multiple time steps using Transformer architectures, challenges remain in fully harnessing the rich temporal dynamics inherent in longitudinal imaging data. In this work, we propose to instead leverage Vision Mamba RNN (VMRNN) with a state-space model (SSM) and LSTM-like memory mechanisms to effectively capture nuanced trends in breast tissue evolution. To further enhance our approach, we incorporate an asymmetry module that utilizes a Spatial Asymmetry Detector (SAD) and Longitudinal Asymmetry Tracker (LAT) to identify clinically relevant bilateral differences. This integrated framework demonstrates notable improvements in predicting cancer onset, especially for the more challenging high-density breast cases and achieves superior performance at extended time points (years four and five), highlighting its potential to advance early breast cancer recognition and enable more personalized screening strategies. Our code is available at https://github.com/Mortal-Suen/VMRA-MaR.git.
In medical imaging, 4D MRI enables dynamic 3D visualization, yet the trade-off between spatial and temporal resolution requires prolonged scan time that can compromise temporal fidelity--especially during rapid, large-amplitude motion. Traditional approaches typically rely on registration-based interpolation to generate intermediate frames. However, these methods struggle with large deformations, resulting in misregistration, artifacts, and diminished spatial consistency. To address these challenges, we propose TSSC-Net, a novel framework that generates intermediate frames while preserving spatial consistency. To improve temporal fidelity under fast motion, our diffusion-based temporal super-resolution network generates intermediate frames using the start and end frames as key references, achieving 6x temporal super-resolution in a single inference step. Additionally, we introduce a novel tri-directional Mamba-based module that leverages long-range contextual information to effectively resolve spatial inconsistencies arising from cross-slice misalignment, thereby enhancing volumetric coherence and correcting cross-slice errors. Extensive experiments were performed on the public ACDC cardiac MRI dataset and a real-world dynamic 4D knee joint dataset. The results demonstrate that TSSC-Net can generate high-resolution dynamic MRI from fast-motion data while preserving structural fidelity and spatial consistency.
Recently, non-convolutional models such as the Vision Transformer (ViT) and Vision Mamba (Vim) have achieved remarkable performance in computer vision tasks. However, their reliance on fixed-size patches often results in excessive encoding of background regions and omission of critical local details, especially when informative objects are sparsely distributed. To address this, we introduce a fully differentiable Dynamic Adaptive Region Tokenizer (DART), which adaptively partitions images into content-dependent patches of varying sizes. DART combines learnable region scores with piecewise differentiable quantile operations to allocate denser tokens to information-rich areas. Despite introducing only approximately 1 million (1M) additional parameters, DART improves accuracy by 2.1% on DeiT (ImageNet-1K). Unlike methods that uniformly increase token density to capture fine-grained details, DART offers a more efficient alternative, achieving 45% FLOPs reduction with superior performance. Extensive experiments on DeiT, Vim, and VideoMamba confirm that DART consistently enhances accuracy while incurring minimal or even reduced computational overhead. Code is available at https://github.com/HCPLab-SYSU/DART.
Within the family of convolutional neural networks, InceptionNeXt has shown excellent competitiveness in image classification and a number of downstream tasks. Built on parallel one-dimensional strip convolutions, however, it suffers from limited ability of capturing spatial dependencies along different dimensions and fails to fully explore spatial modeling in local neighborhood. Besides, inherent locality constraints of convolution operations are detrimental to effective global context modeling. To overcome these limitations, we propose a novel backbone architecture termed InceptionMamba in this study. More specifically, the traditional one-dimensional strip convolutions are replaced by orthogonal band convolutions in our InceptionMamba to achieve cohesive spatial modeling. Furthermore, global contextual modeling can be achieved via a bottleneck Mamba module, facilitating enhanced cross-channel information fusion and enlarged receptive field. Extensive evaluations on classification and various downstream tasks demonstrate that the proposed InceptionMamba achieves state-of-the-art performance with superior parameter and computational efficiency. The source code will be available at https://github.com/Wake1021/InceptionMamba.
Multivariate long-term and efficient time series forecasting is a key requirement for a variety of practical applications, and there are complex interleaving time dynamics in time series data that require decomposition modeling. Traditional time series decomposition methods are single and rely on fixed rules, which are insufficient for mining the potential information of the series and adapting to the dynamic characteristics of complex series. On the other hand, the Transformer-based models for time series forecasting struggle to effectively model long sequences and intricate dynamic relationships due to their high computational complexity. To overcome these limitations, we introduce KARMA, with an Adaptive Time Channel Decomposition module (ATCD) to dynamically extract trend and seasonal components. It further integrates a Hybrid Frequency-Time Decomposition module (HFTD) to further decompose Series into frequency-domain and time-domain. These components are coupled with multi-scale Mamba-based KarmaBlock to efficiently process global and local information in a coordinated manner. Experiments on eight real-world datasets from diverse domains well demonstrated that KARMA significantly outperforms mainstream baseline methods in both predictive accuracy and computational efficiency. Code and full results are available at this repository: https://github.com/yedadasd/KARMA
Most post-disaster damage classifiers succeed only when destructive forces leave clear spectral or structural signatures -- conditions rarely present after inundation. Consequently, existing models perform poorly at identifying flood-related building damages. The model presented in this study, Flood-DamageSense, addresses this gap as the first deep-learning framework purpose-built for building-level flood-damage assessment. The architecture fuses pre- and post-event SAR/InSAR scenes with very-high-resolution optical basemaps and an inherent flood-risk layer that encodes long-term exposure probabilities, guiding the network toward plausibly affected structures even when compositional change is minimal. A multimodal Mamba backbone with a semi-Siamese encoder and task-specific decoders jointly predicts (1) graded building-damage states, (2) floodwater extent, and (3) building footprints. Training and evaluation on Hurricane Harvey (2017) imagery from Harris County, Texas -- supported by insurance-derived property-damage extents -- show a mean F1 improvement of up to 19 percentage points over state-of-the-art baselines, with the largest gains in the frequently misclassified "minor" and "moderate" damage categories. Ablation studies identify the inherent-risk feature as the single most significant contributor to this performance boost. An end-to-end post-processing pipeline converts pixel-level outputs to actionable, building-scale damage maps within minutes of image acquisition. By combining risk-aware modeling with SAR's all-weather capability, Flood-DamageSense delivers faster, finer-grained, and more reliable flood-damage intelligence to support post-disaster decision-making and resource allocation.
Video Frame Interpolation (VFI) is a fundamental Low-Level Vision (LLV) task that synthesizes intermediate frames between existing ones while maintaining spatial and temporal coherence. VFI techniques have evolved from classical motion compensation-based approach to deep learning-based approach, including kernel-, flow-, hybrid-, phase-, GAN-, Transformer-, Mamba-, and more recently diffusion model-based approach. We introduce AceVFI, the most comprehensive survey on VFI to date, covering over 250+ papers across these approaches. We systematically organize and describe VFI methodologies, detailing the core principles, design assumptions, and technical characteristics of each approach. We categorize the learning paradigm of VFI methods namely, Center-Time Frame Interpolation (CTFI) and Arbitrary-Time Frame Interpolation (ATFI). We analyze key challenges of VFI such as large motion, occlusion, lighting variation, and non-linear motion. In addition, we review standard datasets, loss functions, evaluation metrics. We examine applications of VFI including event-based, cartoon, medical image VFI and joint VFI with other LLV tasks. We conclude by outlining promising future research directions to support continued progress in the field. This survey aims to serve as a unified reference for both newcomers and experts seeking a deep understanding of modern VFI landscapes.
In long-term time series forecasting, different variables often influence the target variable over distinct time intervals, a challenge known as the multi-delay issue. Traditional models typically process all variables or time points uniformly, which limits their ability to capture complex variable relationships and obtain non-trivial time representations. To address this issue, we propose TimePro, an innovative Mamba-based model that constructs variate- and time-aware hyper-states. Unlike conventional approaches that merely transfer plain states across variable or time dimensions, TimePro preserves the fine-grained temporal features of each variate token and adaptively selects the focused time points to tune the plain state. The reconstructed hyper-state can perceive both variable relationships and salient temporal information, which helps the model make accurate forecasting. In experiments, TimePro performs competitively on eight real-world long-term forecasting benchmarks with satisfactory linear complexity. Code is available at https://github.com/xwmaxwma/TimePro.
Sequence modeling is currently dominated by causal transformer architectures that use softmax self-attention. Although widely adopted, transformers require scaling memory and compute linearly during inference. A recent stream of work linearized the softmax operation, resulting in powerful recurrent neural network (RNN) models with constant memory and compute costs such as DeltaNet, Mamba or xLSTM. These models can be unified by noting that their recurrent layer dynamics can all be derived from an in-context regression objective, approximately optimized through an online learning rule. Here, we join this line of work and introduce a numerically stable, chunkwise parallelizable version of the recently proposed Mesa layer (von Oswald et al., 2024), and study it in language modeling at the billion-parameter scale. This layer again stems from an in-context loss, but which is now minimized to optimality at every time point using a fast conjugate gradient solver. Through an extensive suite of experiments, we show that optimal test-time training enables reaching lower language modeling perplexity and higher downstream benchmark performance than previous RNNs, especially on tasks requiring long context understanding. This performance gain comes at the cost of additional flops spent during inference time. Our results are therefore intriguingly related to recent trends of increasing test-time compute to improve performance -- here by spending compute to solve sequential optimization problems within the neural network itself.
State-space models (SSMs) offer a promising architecture for sequence modeling, providing an alternative to Transformers by replacing expensive self-attention with linear recurrences. In this paper, we propose a simple yet effective trick to enhance SSMs within given computational budgets by sparsifying them. Our intuition is that tokens in SSMs are highly redundant due to gradual recurrent updates, and dense recurrence operations block the delivery of past information. In particular, we observe that upper layers of SSMs tend to be more redundant as they encode global information, while lower layers encode local information. Motivated by this, we introduce Simba, a hierarchical sparsification method for SSMs based on token pruning. Simba sparsifies upper layers more than lower layers, encouraging the upper layers to behave like highways. To achieve this, we propose a novel token pruning criterion for SSMs, measuring the global impact of tokens on the final output by accumulating local recurrences. We demonstrate that Simba outperforms the baseline model, Mamba, with the same FLOPS in various natural language tasks. Moreover, we illustrate the effect of highways, showing that Simba not only enhances efficiency but also improves the information flow across long sequences. Code is available at https://github.com/woominsong/Simba.