{"list":"other","total":108,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2401.09417","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","created":"2024-01-17","cited_by_count":1056},{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969},{"id":"2302.00093","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","created":"2023-01-31","cited_by_count":841},{"id":"2205.12454","title":"Recipe for a General, Powerful, Scalable Graph Transformer","created":"2022-05-25","cited_by_count":713},{"id":"2110.13985","title":"Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers","created":"2021-10-26","cited_by_count":608},{"id":"2008.07669","title":"HiPPO: Recurrent Memory with Optimal Polynomial Projections","created":"2020-08-17","cited_by_count":605},{"id":"1911.06455","title":"Graph Transformer Networks","created":"2019-11-06","cited_by_count":523},{"id":"2212.14052","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","created":"2022-12-28","cited_by_count":499},{"id":"2401.04722","title":"U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation","created":"2024-01-09","cited_by_count":419},{"id":"2302.10866","title":"Hyena Hierarchy: Towards Larger Convolutional Language Models","created":"2023-02-21","cited_by_count":393},{"id":"2402.15648","title":"MambaIR: A Simple Baseline for Image Restoration with State-Space Model","created":"2024-02-23","cited_by_count":352},{"id":"2403.06977","title":"VideoMamba: State Space Model for Efficient Video Understanding","created":"2024-03-11","cited_by_count":328},{"id":"2402.02491","title":"VM-UNet: Vision Mamba UNet for Medical Image Segmentation","created":"2024-02-04","cited_by_count":287},{"id":"2401.13560","title":"SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image Segmentation","created":"2024-01-24","cited_by_count":266},{"id":"2206.08164","title":"Long Range Graph Benchmark","created":"2022-06-16","cited_by_count":263},{"id":"2303.10993","title":"A Survey on Oversmoothing in Graph Neural Networks","created":"2023-03-20","cited_by_count":247},{"id":"2402.19427","title":"Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models","created":"2024-02-29","cited_by_count":242},{"id":"2403.09338","title":"LocalMamba: Visual State Space Model with Windowed Selective Scan","created":"2024-03-14","cited_by_count":236},{"id":"1908.11775","title":"Transformer Dissection: A Unified Understanding of Transformer's Attention via the Lens of Kernel","created":"2019-08-30","cited_by_count":213},{"id":"2402.03302","title":"Swin-UMamba: Mamba-based UNet with ImageNet-based pretraining","created":"2024-02-05","cited_by_count":179},{"id":"2402.10739","title":"PointMamba: A Simple State Space Model for Point Cloud Analysis","created":"2024-02-16","cited_by_count":167},{"id":"2302.02941","title":"On Over-Squashing in Message Passing Neural Networks: The Impact of Width, Depth, and Topology","created":"2023-02-06","cited_by_count":166},{"id":"2403.09977","title":"EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba","created":"2024-03-15","cited_by_count":146},{"id":"2405.07992","title":"MambaOut: Do We Really Need Mamba for Vision?","created":"2024-05-13","cited_by_count":143},{"id":"2402.00789","title":"Graph-Mamba: Towards Long-Range Graph Sequence Modeling with Selective State Spaces","created":"2024-02-01","cited_by_count":134},{"id":"2402.05079","title":"Mamba-UNet: UNet-Like Pure Visual Mamba for Medical Image Segmentation","created":"2024-02-07","cited_by_count":133},{"id":"2404.03425","title":"ChangeMamba: Remote Sensing Change Detection With Spatiotemporal State Space Model","created":"2024-04-04","cited_by_count":120},{"id":"2403.11144","title":"Is Mamba Effective for Time Series Forecasting?","created":"2024-03-17","cited_by_count":114},{"id":"2403.03234","title":"Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling","created":"2024-03-05","cited_by_count":113},{"id":"2403.07487","title":"Motion Mamba: Efficient and Long Sequence Motion Generation","created":"2024-03-12","cited_by_count":112},{"id":"2403.09626","title":"Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding","created":"2024-03-14","cited_by_count":108},{"id":"2403.14520","title":"Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference","created":"2024-03-21","cited_by_count":97},{"id":"2403.19654","title":"RSMamba: Remote Sensing Image Classification with State Space Model","created":"2024-03-28","cited_by_count":95},{"id":"2403.13600","title":"VL-Mamba: Exploring State Space Models for Multimodal Learning","created":"2024-03-20","cited_by_count":93},{"id":"2405.19707","title":"DeMamba: AI-Generated Video Detection on Million-Scale GenVideo Benchmark","created":"2024-05-30","cited_by_count":92},{"id":"2403.03849","title":"MedMamba: Vision Mamba for Medical Image Classification","created":"2024-03-06","cited_by_count":88},{"id":"2402.08678","title":"Graph Mamba: Towards Learning on Graphs with State Space Models","created":"2024-02-13","cited_by_count":86},{"id":"2402.12192","title":"Pan-Mamba: Effective pan-sharpening with State Space Model","created":"2024-02-19","cited_by_count":73},{"id":"2403.06467","title":"Point Mamba: A Novel Point Cloud Backbone Based on State Space Model with Octree-Based Ordering Strategy","created":"2024-03-11","cited_by_count":73},{"id":"2405.14224","title":"DiM: Diffusion Mamba for Efficient High-Resolution Image Synthesis","created":"2024-05-23","cited_by_count":72},{"id":"2403.00762","title":"Point Cloud Mamba: Point Cloud Learning via State Space Model","created":"2024-03-01","cited_by_count":66},{"id":"2403.09898","title":"TimeMachine: A Time Series is Worth 4 Mambas for Long-term Forecasting","created":"2024-03-14","cited_by_count":64},{"id":"2302.06646","title":"Simple Hardware-Efficient Long Convolutions for Sequence Modeling","created":"2023-02-13","cited_by_count":62},{"id":"2405.06573","title":"An Investigation of Incorporating Mamba for Speech Enhancement","created":"2024-05-10","cited_by_count":62},{"id":"2403.02148","title":"MiM-ISTD: Mamba-in-Mamba for Efficient Infrared Small Target Detection","created":"2024-03-04","cited_by_count":60},{"id":"2405.03349","title":"Retinexmamba: Retinex-based Mamba for Low-light Image Enhancement","created":"2024-05-06","cited_by_count":59},{"id":"2401.14168","title":"Vivim: a Video Vision Mamba for Medical Video Segmentation","created":"2024-01-25","cited_by_count":52},{"id":"2212.10544","title":"Pretraining Without Attention","created":"2022-12-20","cited_by_count":51},{"id":"2406.04207","title":"CDMamba: Incorporating Local Clues into Mamba for Remote Sensing Image Binary Change Detection","created":"2024-06-06","cited_by_count":48},{"id":"2403.09471","title":"MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models","created":"2024-03-14","cited_by_count":46},{"id":"2402.03526","title":"nnMamba: 3D Biomedical Image Segmentation, Classification and Landmark Detection with State Space Model","created":"2024-02-05","cited_by_count":45},{"id":"2403.18257","title":"Dual-path Mamba: Short and Long-term Bidirectional Selective Structured State Space Models for Speech Separation","created":"2024-03-27","cited_by_count":45},{"id":"2402.04139","title":"U-shaped Vision Mamba for Single Image Dehazing","created":"2024-02-06","cited_by_count":40},{"id":"2403.09157","title":"VM-UNET-V2 Rethinking Vision Mamba UNet for Medical Image Segmentation","created":"2024-03-14","cited_by_count":39},{"id":"2403.17839","title":"ReMamber: Referring Image Segmentation with Mamba Twister","created":"2024-03-26","cited_by_count":38},{"id":"2212.08136","title":"Efficient Long Sequence Modeling via State Space Augmented Transformer","created":"2022-12-15","cited_by_count":37},{"id":"2405.11831","title":"SSAMBA: Self-Supervised Audio Representation Learning with Mamba State Space Model","created":"2024-05-20","cited_by_count":37},{"id":"2403.13642","title":"H-vmunet: High-order Vision Mamba UNet for Medical Image Segmentation","created":"2024-03-20","cited_by_count":35},{"id":"2404.08406","title":"MambaDFuse: A Mamba-based Dual-phase Model for Multi-modality Image Fusion","created":"2024-04-12","cited_by_count":35},{"id":"2404.02457","title":"RS3Mamba: Visual State Space Model for Remote Sensing Images Semantic Segmentation","created":"2024-04-03","cited_by_count":33},{"id":"2405.19450","title":"FourierMamba: Fourier Learning Integration with State Space Models for Image Deraining","created":"2024-05-29","cited_by_count":33},{"id":"2402.10887","title":"Weak-Mamba-UNet: Visual Mamba Makes CNN and ViT Work Better for Scribble-based Medical Image Segmentation","created":"2024-02-16","cited_by_count":29},{"id":"2403.07675","title":"Multichannel Long-Term Streaming Neural Speech Enhancement for Static and Moving Speakers","created":"2024-03-12","cited_by_count":28},{"id":"2406.06086","title":"RawBMamba: End-to-End Bidirectional State Space Model for Audio Deepfake Detection","created":"2024-06-10","cited_by_count":27},{"id":"2403.03900","title":"Mamba4Rec: Towards Efficient Sequential Recommendation with Selective State Space Models","created":"2024-03-06","cited_by_count":26},{"id":"2405.15463","title":"PoinTramba: A Hybrid Transformer-Mamba Framework for Point Cloud Analysis","created":"2024-05-24","cited_by_count":26},{"id":"2406.01159","title":"Dimba: Transformer-Mamba Diffusion Models","created":"2024-06-03","cited_by_count":26},{"id":"2403.12418","title":"STG-Mamba: Spatial-Temporal Graph Learning via Selective State Space Model","created":"2024-03-19","cited_by_count":24},{"id":"2405.11449","title":"NetMamba: Efficient Network Traffic Classification via Pre-training Unidirectional Mamba","created":"2024-05-19","cited_by_count":24},{"id":"2106.01202","title":"Framing RNN as a kernel method: A neural ODE approach","created":"2021-06-02","cited_by_count":23},{"id":"2402.15761","title":"Res-VMamba: Fine-Grained Food Category Visual Classification Using Selective State Space Models with Deep Residual Learning","created":"2024-02-24","cited_by_count":22},{"id":"2403.00818","title":"DenseMamba: State Space Models with Dense Hidden Connection for Efficient Large Language Models","created":"2024-02-26","cited_by_count":22},{"id":"2403.05795","title":"ClinicalMamba: A Generative Clinical Language Model on Longitudinal Clinical Notes","created":"2024-03-09","cited_by_count":22},{"id":"2404.05522","title":"3DMambaIPF: A State Space Model for Iterative Point Cloud Filtering via Differentiable Rendering","created":"2024-04-08","cited_by_count":21},{"id":"2405.15881","title":"Scaling Diffusion Mamba with Bidirectional SSMs for Efficient Image and Video Generation","created":"2024-05-24","cited_by_count":21},{"id":"2405.12003","title":"Mamba-in-Mamba: Centralized Mamba-Cross-Scan in Tokenized Mamba Model for Hyperspectral Image Classification","created":"2024-05-20","cited_by_count":18},{"id":"2404.14757","title":"SST: Multi-Scale Hybrid Mamba-Transformer Experts for Time Series Forecasting","created":"2024-04-23","cited_by_count":16},{"id":"2403.16520","title":"CMViM: Contrastive Masked Vim Autoencoder for 3D Multi-modal Representation Learning for AD classification","created":"2024-03-25","cited_by_count":15},{"id":"2406.07050","title":"DualMamba: A Lightweight Spectral-Spatial Mamba-Convolution Network for Hyperspectral Image Classification","created":"2024-06-11","cited_by_count":15},{"id":"2405.10030","title":"RSDehamba: Lightweight Vision Mamba for Remote Sensing Satellite Image Dehazing","created":"2024-05-16","cited_by_count":14},{"id":"2406.01028","title":"LLEMamba: Low-Light Enhancement via Relighting-Guided Mamba with Deep Unfolding Network","created":"2024-06-03","cited_by_count":14},{"id":"2402.06378","title":"FD-Vision Mamba for Endoscopic Exposure Correction","created":"2024-02-09","cited_by_count":13},{"id":"2402.18959","title":"MambaStock: Selective state space model for stock prediction","created":"2024-02-29","cited_by_count":13},{"id":"2404.07645","title":"Simba: Mamba augmented U-ShiftGCN for Skeletal Action Recognition in Videos","created":"2024-04-11","cited_by_count":13},{"id":"2403.17701","title":"Rotate to Scan: UNet-like Mamba with Triplet SSM Module for Medical Image Segmentation","created":"2024-03-26","cited_by_count":12},{"id":"2404.09293","title":"A Novel State Space Model with Local Enhancement and State Sharing for Image Fusion","created":"2024-04-14","cited_by_count":11},{"id":"2405.14338","title":"MAMBA4D: Efficient Long-Sequence Point Cloud Video Understanding with Disentangled Spatial-Temporal State Space Models","created":"2024-05-23","cited_by_count":11},{"id":"2403.08330","title":"Activating Wider Areas in Image Super-Resolution","created":"2024-03-13","cited_by_count":10},{"id":"2401.17919","title":"LOCOST: State-Space Models for Long Document Abstractive Summarization","created":"2024-01-31","cited_by_count":8},{"id":"2404.07106","title":"3DMambaComplete: Exploring Structured State Space Model for Point Cloud Completion","created":"2024-04-10","cited_by_count":8},{"id":"2406.05316","title":"CMamba: Channel Correlation Enhanced State Space Models for Multivariate Time Series Forecasting","created":"2024-06-08","cited_by_count":8}],"next_cursor":"100"}