{"list":"other","total":147,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"2012.07436","title":"Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting","created":"2020-12-14","cited_by_count":2169},{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2110.04544","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","created":"2021-10-09","cited_by_count":1026},{"id":"1904.06690","title":"BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer","created":"2019-04-14","cited_by_count":964},{"id":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"id":"1902.07243","title":"Graph Neural Networks for Social Recommendation","created":"2019-02-19","cited_by_count":714},{"id":"2111.14819","title":"Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling","created":"2021-11-29","cited_by_count":653},{"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":"1912.12033","title":"Deep Learning for 3D Point Clouds: A Survey","created":"2019-12-27","cited_by_count":558},{"id":"1909.03211","title":"Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View","created":"2019-09-07","cited_by_count":545},{"id":"2106.04647","title":"Compacter: Efficient Low-Rank Hypercomplex Adapter Layers","created":"2021-06-08","cited_by_count":460},{"id":"2405.06211","title":"A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models","created":"2024-05-10","cited_by_count":452},{"id":"2206.11893","title":"On the Parameterization and Initialization of Diagonal State Space Models","created":"2022-06-23","cited_by_count":424},{"id":"2302.10866","title":"Hyena Hierarchy: Towards Larger Convolutional Language Models","created":"2023-02-21","cited_by_count":393},{"id":"1812.01243","title":"Efficient Attention: Attention with Linear Complexities","created":"2018-12-04","cited_by_count":368},{"id":"1708.02072","title":"Measuring Catastrophic Forgetting in Neural Networks","created":"2017-08-07","cited_by_count":360},{"id":"2403.06977","title":"VideoMamba: State Space Model for Efficient Video Understanding","created":"2024-03-11","cited_by_count":328},{"id":"1811.00855","title":"Session-based Recommendation with Graph Neural Networks","created":"2018-11-01","cited_by_count":312},{"id":"2402.02491","title":"VM-UNet: Vision Mamba UNet for Medical Image Segmentation","created":"2024-02-04","cited_by_count":287},{"id":"2307.03393","title":"Exploring the Potential of Large Language Models (LLMs) in Learning on Graphs","created":"2023-07-07","cited_by_count":274},{"id":"2104.11280","title":"Motion Representations for Articulated Animation","created":"2021-04-22","cited_by_count":255},{"id":"2403.09338","title":"LocalMamba: Visual State Space Model with Windowed Selective Scan","created":"2024-03-14","cited_by_count":236},{"id":"2407.08083","title":"MambaVision: A Hybrid Mamba-Transformer Vision Backbone","created":"2024-07-10","cited_by_count":224},{"id":"2402.01032","title":"Repeat After Me: Transformers are Better than State Space Models at Copying","created":"2024-02-01","cited_by_count":216},{"id":"2309.11497","title":"FreeU: Free Lunch in Diffusion U-Net","created":"2023-09-20","cited_by_count":196},{"id":"2307.02046","title":"Recommender Systems in the Era of Large Language Models (LLMs)","created":"2023-07-05","cited_by_count":189},{"id":"2404.08819","title":"The Illusion of State in State-Space Models","created":"2024-04-12","cited_by_count":187},{"id":"2402.03302","title":"Swin-UMamba: Mamba-based UNet with ImageNet-based pretraining","created":"2024-02-05","cited_by_count":179},{"id":"2403.09977","title":"EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba","created":"2024-03-15","cited_by_count":146},{"id":"2403.17695","title":"PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition","created":"2024-03-26","cited_by_count":141},{"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":"2201.05337","title":"A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models","created":"2022-01-14","cited_by_count":129},{"id":"2307.01881","title":"ProPILE: Probing Privacy Leakage in Large Language Models","created":"2023-07-04","cited_by_count":129},{"id":"2110.11945","title":"SOFT: Softmax-free Transformer with Linear Complexity","created":"2021-10-22","cited_by_count":128},{"id":"2106.06716","title":"DS-TransUNet:Dual Swin Transformer U-Net for Medical Image Segmentation","created":"2021-06-12","cited_by_count":126},{"id":"2404.03425","title":"ChangeMamba: Remote Sensing Change Detection With Spatiotemporal State Space Model","created":"2024-04-04","cited_by_count":120},{"id":"2403.09636","title":"Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference","created":"2024-03-14","cited_by_count":116},{"id":"2403.03234","title":"Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling","created":"2024-03-05","cited_by_count":113},{"id":"2404.06564","title":"MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection","created":"2024-04-09","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":"2406.04339","title":"RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation","created":"2024-06-06","cited_by_count":103},{"id":"2107.02192","title":"Long-Short Transformer: Efficient Transformers for Language and Vision","created":"2021-07-05","cited_by_count":102},{"id":"2405.16605","title":"Demystify Mamba in Vision: A Linear Attention Perspective","created":"2024-05-26","cited_by_count":102},{"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":"2107.06641","title":"Trustworthy AI: A Computational Perspective","created":"2021-07-12","cited_by_count":93},{"id":"2403.13600","title":"VL-Mamba: Exploring State Space Models for Multimodal Learning","created":"2024-03-20","cited_by_count":93},{"id":"2306.06615","title":"Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective","created":"2023-06-11","cited_by_count":92},{"id":"2403.11423","title":"VmambaIR: Visual State Space Model for Image Restoration","created":"2024-03-18","cited_by_count":90},{"id":"2403.13802","title":"ZigMa: A DiT-style Zigzag Mamba Diffusion Model","created":"2024-03-20","cited_by_count":84},{"id":"2206.00761","title":"On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting","created":"2022-06-01","cited_by_count":82},{"id":"2404.02668","title":"RS-Mamba for Large Remote Sensing Image Dense Prediction","created":"2024-04-03","cited_by_count":81},{"id":"2404.09498","title":"FusionMamba: Dynamic Feature Enhancement for Multimodal Image Fusion with Mamba","created":"2024-04-15","cited_by_count":81},{"id":"2403.02622","title":"World Models for Autonomous Driving: An Initial Survey","created":"2024-03-05","cited_by_count":80},{"id":"2207.00939","title":"An Empirical Survey on Long Document Summarization: Datasets, Models and Metrics","created":"2022-07-03","cited_by_count":74},{"id":"2402.12192","title":"Pan-Mamba: Effective pan-sharpening with State Space Model","created":"2024-02-19","cited_by_count":73},{"id":"2404.04256","title":"Sigma: Siamese Mamba Network for Multi-Modal Semantic Segmentation","created":"2024-04-05","cited_by_count":71},{"id":"2404.09146","title":"Fusion-Mamba for Cross-modality Object Detection","created":"2024-04-14","cited_by_count":67},{"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":"2405.14174","title":"Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model","created":"2024-05-23","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":"2405.12609","title":"Mamba in Speech: Towards an Alternative to Self-Attention","created":"2024-05-21","cited_by_count":60},{"id":"2012.00931","title":"Speaker Recognition Based on Deep Learning: An Overview","created":"2020-12-02","cited_by_count":59},{"id":"2404.09516","title":"State Space Model for New-Generation Network Alternative to Transformers: A Survey","created":"2024-04-15","cited_by_count":59},{"id":"2404.09476","title":"FreqMamba: Viewing Mamba from a Frequency Perspective for Image Deraining","created":"2024-04-15","cited_by_count":57},{"id":"2108.05552","title":"Graph Trend Filtering Networks for Recommendations","created":"2021-08-12","cited_by_count":53},{"id":"2401.14168","title":"Vivim: a Video Vision Mamba for Medical Video Segmentation","created":"2024-01-25","cited_by_count":52},{"id":"2404.15956","title":"A Survey on Visual Mamba","created":"2024-04-24","cited_by_count":50},{"id":"2209.03952","title":"TF-GridNet: Making Time-Frequency Domain Models Great Again for Monaural Speaker Separation","created":"2022-09-08","cited_by_count":48},{"id":"2402.05608","title":"Scalable Diffusion Models with State Space Backbone","created":"2024-02-08","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":"2004.14949","title":"SkipGNN: Predicting Molecular Interactions with Skip-Graph Networks","created":"2020-04-30","cited_by_count":44},{"id":"1912.00552","title":"Sparse Graph Attention Networks","created":"2019-12-02","cited_by_count":41},{"id":"2404.18861","title":"Visual Mamba: A Survey and New Outlooks","created":"2024-04-29","cited_by_count":41},{"id":"2405.14858","title":"Mamba-R: Vision Mamba ALSO Needs Registers","created":"2024-05-23","cited_by_count":41},{"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":"2404.08406","title":"MambaDFuse: A Mamba-based Dual-phase Model for Multi-modality Image Fusion","created":"2024-04-12","cited_by_count":35},{"id":"2406.10450","title":"TokenRec: Learning to Tokenize ID for LLM-based Generative Recommendation","created":"2024-06-15","cited_by_count":35},{"id":"2404.14928","title":"Graph Machine Learning in the Era of Large Language Models (LLMs)","created":"2024-04-23","cited_by_count":33},{"id":"1907.06853","title":"Deep Social Collaborative Filtering","created":"2019-07-16","cited_by_count":32},{"id":"2112.00791","title":"Controlling Conditional Language Models without Catastrophic Forgetting","created":"2021-12-01","cited_by_count":32},{"id":"2402.13973","title":"Linear-Time Graph Neural Networks for Scalable Recommendations","created":"2024-02-21","cited_by_count":31},{"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":"2305.19638","title":"A Unified Framework for U-Net Design and Analysis","created":"2023-05-31","cited_by_count":27},{"id":"2211.13290","title":"SEAT: Stable and Explainable Attention","created":"2022-11-23","cited_by_count":25},{"id":"2404.01174","title":"SpikeMba: Multi-Modal Spiking Saliency Mamba for Temporal Video Grounding","created":"2024-04-01","cited_by_count":25}],"next_cursor":"100"}