Papers State Space Models
“State Space Models” 태그가 달린 논문 923편 · 필터 해제
Precision Spatio-Temporal Feature Fusion for Robust Remote Sensing Change Detection
Remote sensing change detection is vital for monitoring environmental and urban transformations but faces challenges like manual feature extraction and sensitivity to noise. Traditional methods and early deep learning mo…
Change DetectionState Space ModelsOptimal Sensor Scheduling and Selection for Continuous-Discrete Kalman Filtering with Auxiliary Dynamics
We study the Continuous-Discrete Kalman Filter (CD-KF) for State-Space Models (SSMs) where continuous-time dynamics are observed via multiple sensors with discrete, irregularly timed measurements. Our focus extends to sc…
SchedulingState Space ModelsBridging Robustness and Generalization Against Word Substitution Attacks in NLP via the Growth Bound Matrix Approach
Despite advancements in Natural Language Processing (NLP), models remain vulnerable to adversarial attacks, such as synonym substitutions. While prior work has focused on improving robustness for feed-forward and convolu…
Adversarial DefenseAdversarial RobustnessState Space ModelsQS4D: Quantization-aware training for efficient hardware deployment of structured state-space sequential models
Structured State Space models (SSM) have recently emerged as a new class of deep learning models, particularly well-suited for processing long sequences. Their constant memory footprint, in contrast to the linearly scali…
Computational EfficiencyEdge-computingQuantizationState Space ModelsMambaFusion: Height-Fidelity Dense Global Fusion for Multi-modal 3D Object Detection
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 fro…
3D Object DetectionAttributeLong-range modelingMamba+3Adaptive Gate-Aware Mamba Networks for Magnetic Resonance Fingerprinting
Magnetic Resonance Fingerprinting (MRF) enables fast quantitative imaging by matching signal evolutions to a predefined dictionary. However, conventional dictionary matching suffers from exponential growth in computation…
Magnetic Resonance FingerprintingMambaSSIMState Space ModelsUnderstanding and Improving Length Generalization in Recurrent Models
Recently, recurrent models such as state space models and linear attention have become popular due to their linear complexity in the sequence length. Thanks to their recurrent nature, in principle they can process arbitr…
2kState Space ModelsHolistic Surgical Phase Recognition with Hierarchical Input Dependent State Space Models
Surgical workflow analysis is essential in robot-assisted surgeries, yet the long duration of such procedures poses significant challenges for comprehensive video analysis. Recent approaches have predominantly relied on …
State Space ModelsSurgical phase recognitionEAGLE: An Efficient Global Attention Lesion Segmentation Model for Hepatic Echinococcosis
Hepatic echinococcosis (HE) is a widespread parasitic disease in underdeveloped pastoral areas with limited medical resources. While CNN-based and Transformer-based models have been widely applied to medical image segmen…
Image SegmentationLesion SegmentationMambaMedical Image Segmentation+2Memba: Membrane-driven Parameter-Efficient Fine-Tuning for Mamba
State Space Models (SSMs) have emerged as powerful alternatives to attention-based Transformers, with Mamba demonstrating impressive efficiency and scalability. As these models grow increasingly larger, the need for Para…
Mambaparameter-efficient fine-tuningState Space ModelsState-Space Models in Efficient Whispered and Multi-dialect Speech Recognition
Whispered speech recognition presents significant challenges for conventional automatic speech recognition systems, particularly when combined with dialect variation. However, utilizing an efficient method to solve this …
Automatic Speech RecognitionDiversityMambaspeech-recognition+2FlowRAM: Grounding Flow Matching Policy with Region-Aware Mamba Framework for Robotic Manipulation
Robotic manipulation in high-precision tasks is essential for numerous industrial and real-world applications where accuracy and speed are required. Yet current diffusion-based policy learning methods generally suffer fr…
Computational EfficiencyDenoisingMambaState Space ModelsIn-Context Learning for Gradient-Free Receiver Adaptation: Principles, Applications, and Theory
In recent years, deep learning has facilitated the creation of wireless receivers capable of functioning effectively in conditions that challenge traditional model-based designs. Leveraging programmable hardware architec…
In-Context LearningMeta-LearningState Space ModelsLoRA-Mixer: Coordinate Modular LoRA Experts Through Serial Attention Routing
Recent efforts to combine low-rank adaptation (LoRA) with mixture-of-experts (MoE) for adapting large language models (LLMs) to multiple tasks still exhibit prevailing limitations: they either swap entire attention/feed-…
ARCCoLAGSM8KHumanEval+4MT-PCR: A Hybrid Mamba-Transformer with Spatial Serialization for Hierarchical Point Cloud Registration
Point cloud registration (PCR) is a fundamental task in 3D computer vision and robotics. Most existing learning-based PCR methods rely on Transformers, which suffer from quadratic computational complexity. This limitatio…
GPUMambaPoint Cloud RegistrationState Space ModelsQuantizing Small-Scale State-Space Models for Edge AI
State-space models (SSMs) have recently gained attention in deep learning for their ability to efficiently model long-range dependencies, making them promising candidates for edge-AI applications. In this paper, we analy…
QuantizationState Space ModelsSequential-Parallel Duality in Prefix Scannable Models
Modern neural sequence models are designed to meet the dual mandate of parallelizable training and fast sequential inference. Recent developments have given rise to various models, such as Gated Linear Attention (GLA) an…
Language ModelingLanguage ModellingMambaState Space ModelsTransXSSM: A Hybrid Transformer State Space Model with Unified Rotary Position Embedding
Transformers exhibit proficiency in capturing long-range dependencies, whereas State Space Models (SSMs) facilitate linear-time sequence modeling. Notwithstanding their synergistic potential, the integration of these arc…
4kLanguage ModelingLanguage ModellingPosition+1SparseSSM: Efficient Selective Structured State Space Models Can Be Pruned in One-Shot
State-space language models such as Mamba match Transformer quality while permitting linear complexity inference, yet still comprise billions of parameters that hinder deployment. Existing one-shot pruning methods are ta…
MambaState Space ModelsW4S4: WaLRUS Meets S4 for Long-Range Sequence Modeling
State Space Models (SSMs) have emerged as powerful components for sequence modeling, enabling efficient handling of long-range dependencies via linear recurrence and convolutional computation. However, their effectivenes…
State Space Models