Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 61 for “"Mamba"”.
-
Online Decision Mamba
… online fine-tuning. We introduce Online Decision Mamba (ODM), an architecture that replaces the attention mechanism in Online Decision Transformers (ODT) with the Mamba module to improve long-context sequence modeling and overall RL performance. We performed in-depth evaluations on MuJoCo (OpenAI …
-
A novel framework for dynamic graph representation learning with mamba
… thesis compares transformer approaches with the Mamba architecture-a linear-complexity state-space model—for temporal graph embedding.</p><p>Two frameworks are proposed: DG-Mamba and GDG-Mamba. DG-Mamba uses standard GCN-based spatial encoding, while GDG-Mamba incorporates domain-aware edge …
-
Novel Sparse Adaptive Token Mamba Models for Remote Sensing Imagery Classification
… State Space Models (SSMs), particularly the Mamba architecture, offer a linear-complexity alternative for long-range modeling. However, conventional Mamba implementations rely on fixed tokenization strategies that are not designed for the spatial–spectral–temporal heterogeneity of remote …
-
Performance profiling and activity-based state pruning for efficient Mamba inference
… on long-context tasks. Among these models, Mamba has attracted significant attention for its linear-time sequence modeling capability. However, the internal performance characteristics of Mamba-based architectures remain insufficiently understood, particularly with respect to runtime …
-
SMaT-HSI: Structure-aware Mamba-Transformer Hybrid Model for Hyperspectral Image Classification
… inherent in hyperspectral data. Recently, Mamba, a state-space model (SSM)-based architecture, has shown promise in sequence modeling by efficiently capturing long-range dependencies with linear computational complexity. A comprehensive comparison of CNN-based, transformer-based, and …
-
Multi-Object Tracking using Mamba and an Investigation into Data Association Strategies
… in state-space models (SSMs), particularly Mamba, we propose a novel learning-based architecture for motion prediction that combines the strengths of Mamba and self-attention layers to effectively capture non-linear motion patterns within the Tracking-By-Detection (TBD) paradigm. Mamba's …
-
SepMAMBAM: A Compute-Efficient, High-Performance Mamba-Based Network for Speech Separation
… To address these limitations, we propose SepMAMBAM, an early split separator that integrates the Mamba state-space model with convolutional block attention modules (CBAM). In our design, the encoder is composed of UMC (Unidirectional Mamba + CBAM) blocks that extract and refine mixture …
-
Segmentation intelligente en imagerie médicale: application aux scanners thoraciques pour la détection du cancer du poumon
… des architectures de type " Transformer" et " Mamba" . Dans un premier temps, une revue de littérature approfondie sur les approches d'apprentissage profond pour la détection et la segmentation du cancer du poumon est présentée, mettant en évidence les défis et les avancées récentes. Nous …
-
Molecular Targets of Atropine- and Mamba Toxin 3-Mediated Inhibition of Form-Deprivation Myopia in the Chick: A Case of Mistaken Receptor Identity?
… that mAChRs are responsible for atropine- and mamba toxin 3-mediated myopia-inhibition in the chick. First, I demonstrate that alpha2-adrenoceptor (ADRA2) agonists can dose-dependently inhibit FDM. Second, I show that myopia-inhibiting mAChR antagonists can bind to, and block signalling by, …
-
Unified driving maneuver detection and classification from monocular video
… combines a Selective State Space Model (Mamba) for linear-time causal temporal modeling (O(L)) with a dual-pathway feature fusion mechanism that pairs a primary visual representation with an image-derived ego-trajectory branch. The visual pathway extracts spatio-temporal appearance …
-
Emerging Architectures for Chemical Language Modeling
… the decoder-only Transformer and the Mamba architecture, and a conventional Recurrent Neural Network with LSTM cells. The investigation explores how choices in training data, including a targeted medicinal dataset (ChEMBL) and a chemically broad dataset (PubChem), as well as data …
-
Efficient and Interpretable Representations: From Medical Representation Learning to Vision-Language Multimodal Representation Engineering
… architectures. We first investigate Vision Mamba architectures for medical applications. For histopathology, we adapt Vision Mamba within the DINO self-supervised learning framework, achieving an 8.21 AUC point improvement over Vision Transformers with comparable parameters on lymph node …
-
Vokalų ištraukimas iš muzikinių failų /
… MB-RoFormer, ”Windowed-sink” MB-RoFormer, and Mamba blocks. Experiments were conducted with four architecture groups with variations: Unet with trans former blocks (three variations), ”Windowed-sink” MB-RoFormer, MB-RoFormer (two variations), and MB-RoFormer with Mamba blocks (two …
-
Tramba: A Hybrid Architecture for Table Understanding
… vision architecture that integrates the Vision Mamba encoder with the Detection Transformer (DETR) framework to address the tasks of table detection and structure recognition. Leveraging Mamba’s state space modeling, which reduces computational complexity from O(N^2) to O(N), the proposed …
-
INSTRUMENT-TISSUE-GUIDED SURGICAL ACTION TRIPLET DETECTION VIA TEXTUAL-TEMPORAL TRAIL EXPLORATION
… class perception. Besides, we introduce a Mamba-enhanced Spatial-temporal Perception (MSP) decoder, which weaves Mamba and Transformer blocks to explore subject- and object-aware spatial and temporal information to improve the accuracy of action triplet detection in longtime sequence …
-
Thermochemical and Continuum Modeling to Understand the Chemical Composition of PWR Fuel CRUD
… into the multiphysics continuum modeling code MAMBA. An assessment of the kinetic rates of the reactions are determined by Bayesian calibration of the MAMBA model using observational data from CRUD samples. The modeling is able to demonstrate the composition of CRUD scrapes obtained from plant …
-
Drone detection using state space models /
… real-time drone detection tasks by integrating VMamba modules into the YOLO26 architecture. Several hybrid YOLO26-VMamba models were created by inserting vision selective scan (VSS) blocks into different parts of the YOLO26 model, including the backbone, neck and as a replacement for the …
Page 1 of 4