{"list":"other","total":77,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"1506.04214","title":"Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting","created":"2015-06-13","cited_by_count":1436},{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827},{"id":"2307.08621","title":"Retentive Network: A Successor to Transformer for Large Language Models","created":"2023-07-17","cited_by_count":613},{"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":"2403.19887","title":"Jamba: A Hybrid Transformer-Mamba Language Model","created":"2024-03-28","cited_by_count":401},{"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":"1606.01933","title":"A Decomposable Attention Model for Natural Language Inference","created":"2016-06-06","cited_by_count":215},{"id":"2402.03302","title":"Swin-UMamba: Mamba-based UNet with ImageNet-based pretraining","created":"2024-02-05","cited_by_count":179},{"id":"1710.05941","title":"Searching for Activation Functions","created":"2017-10-16","cited_by_count":169},{"id":"2402.10739","title":"PointMamba: A Simple State Space Model for Point Cloud Analysis","created":"2024-02-16","cited_by_count":167},{"id":"2402.05079","title":"Mamba-UNet: UNet-Like Pure Visual Mamba for Medical Image Segmentation","created":"2024-02-07","cited_by_count":133},{"id":"2102.02611","title":"CKConv: Continuous Kernel Convolution For Sequential Data","created":"2021-02-04","cited_by_count":120},{"id":"2404.03425","title":"ChangeMamba: Remote Sensing Change Detection With Spatiotemporal State Space Model","created":"2024-04-04","cited_by_count":120},{"id":"2105.14103","title":"An Attention Free Transformer","created":"2021-05-28","cited_by_count":112},{"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":"2204.01692","title":"Long Movie Clip Classification with State-Space Video Models","created":"2022-04-04","cited_by_count":106},{"id":"2403.19654","title":"RSMamba: Remote Sensing Image Classification with State Space Model","created":"2024-03-28","cited_by_count":95},{"id":"2403.11423","title":"VmambaIR: Visual State Space Model for Image Restoration","created":"2024-03-18","cited_by_count":90},{"id":"2403.03849","title":"MedMamba: Vision Mamba for Medical Image Classification","created":"2024-03-06","cited_by_count":88},{"id":"2403.06800","title":"MambaMIL: Enhancing Long Sequence Modeling with Sequence Reordering in Computational Pathology","created":"2024-03-11","cited_by_count":88},{"id":"2402.05892","title":"Mamba-ND: Selective State Space Modeling for Multi-Dimensional Data","created":"2024-02-08","cited_by_count":84},{"id":"2404.02668","title":"RS-Mamba for Large Remote Sensing Image Dense Prediction","created":"2024-04-03","cited_by_count":81},{"id":"2402.15584","title":"State Space Models for Event Cameras","created":"2024-02-23","cited_by_count":75},{"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":"2401.04081","title":"MoE-Mamba: Efficient Selective State Space Models with Mixture of Experts","created":"2024-01-08","cited_by_count":60},{"id":"2403.02148","title":"MiM-ISTD: Mamba-in-Mamba for Efficient Infrared Small Target Detection","created":"2024-03-04","cited_by_count":60},{"id":"2404.09476","title":"FreqMamba: Viewing Mamba from a Frequency Perspective for Image Deraining","created":"2024-04-15","cited_by_count":57},{"id":"2403.18795","title":"Gamba: Marry Gaussian Splatting with Mamba for single view 3D reconstruction","created":"2024-03-27","cited_by_count":56},{"id":"1804.11188","title":"Can recurrent neural networks warp time?","created":"2018-03-23","cited_by_count":55},{"id":"2403.05246","title":"LightM-UNet: Mamba Assists in Lightweight UNet for Medical Image Segmentation","created":"2024-03-08","cited_by_count":54},{"id":"2401.14168","title":"Vivim: a Video Vision Mamba for Medical Video Segmentation","created":"2024-01-25","cited_by_count":52},{"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":"2402.05608","title":"Scalable Diffusion Models with State Space Backbone","created":"2024-02-08","cited_by_count":45},{"id":"2403.20035","title":"UltraLight VM-UNet: Parallel Vision Mamba Significantly Reduces Parameters for Skin Lesion Segmentation","created":"2024-03-29","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":"2403.19888","title":"MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selection","created":"2024-03-29","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":"2402.01771","title":"BlackMamba: Mixture of Experts for State-Space Models","created":"2024-02-01","cited_by_count":37},{"id":"2404.01705","title":"Samba: Semantic Segmentation of Remotely Sensed Images with State Space Model","created":"2024-04-02","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":"2403.16536","title":"VMRNN: Integrating Vision Mamba and LSTM for Efficient and Accurate Spatiotemporal Forecasting","created":"2024-03-25","cited_by_count":35},{"id":"2403.07332","title":"LKM-UNet: Large Kernel Vision Mamba UNet for Medical Image Segmentation","created":"2024-03-12","cited_by_count":34},{"id":"2404.02457","title":"RS3Mamba: Visual State Space Model for Remote Sensing Images Semantic Segmentation","created":"2024-04-03","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":"2404.01174","title":"SpikeMba: Multi-Modal Spiking Saliency Mamba for Temporal Video Grounding","created":"2024-04-01","cited_by_count":25},{"id":"2402.08506","title":"P-Mamba: Marrying Perona Malik Diffusion with Mamba for Efficient Pediatric Echocardiographic Left Ventricular Segmentation","created":"2024-02-13","cited_by_count":21},{"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":"2402.07245","title":"Semi-Mamba-UNet: Pixel-Level Contrastive and Pixel-Level Cross-Supervised Visual Mamba-based UNet for Semi-Supervised Medical Image Segmentation","created":"2024-02-11","cited_by_count":20},{"id":"2402.18451","title":"MambaMIR: An Arbitrary-Masked Mamba for Joint Medical Image Reconstruction and Uncertainty Estimation","created":"2024-02-28","cited_by_count":19},{"id":"2404.01065","title":"T-Mamba: A unified framework with Long-Range Dependency in dual-domain for 2D & 3D Tooth Segmentation","created":"2024-04-01","cited_by_count":17},{"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":"2404.00272","title":"HSIMamba: Hyperpsectral Imaging Efficient Feature Learning with Bidirectional State Space for Classification","created":"2024-03-30","cited_by_count":14},{"id":"2402.06378","title":"FD-Vision Mamba for Endoscopic Exposure Correction","created":"2024-02-09","cited_by_count":13},{"id":"2403.13660","title":"ProMamba: Prompt-Mamba for polyp segmentation","created":"2024-03-20","cited_by_count":12},{"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":"2403.20183","title":"HARMamba: Efficient and Lightweight Wearable Sensor Human Activity Recognition Based on Bidirectional Mamba","created":"2024-03-29","cited_by_count":12},{"id":"2403.08479","title":"MD-Dose: A diffusion model based on the Mamba for radiation dose prediction","created":"2024-03-13","cited_by_count":11},{"id":"2403.05146","title":"Motion-Guided Dual-Camera Tracker for Endoscope Tracking and Motion Analysis in a Mechanical Gastric Simulator","created":"2024-03-08","cited_by_count":10},{"id":"2403.08330","title":"Activating Wider Areas in Image Super-Resolution","created":"2024-03-13","cited_by_count":10},{"id":"2403.17432","title":"Integrating Mamba Sequence Model and Hierarchical Upsampling Network for Accurate Semantic Segmentation of Multiple Sclerosis Legion","created":"2024-03-26","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":"2403.17902","title":"Serpent: Scalable and Efficient Image Restoration via Multi-scale Structured State Space Models","created":"2024-03-26","cited_by_count":7}],"next_cursor":null}