{"list":"other","total":61,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"1806.07366","title":"Neural Ordinary Differential Equations","created":"2018-06-19","cited_by_count":3779},{"id":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"1802.05957","title":"Spectral Normalization for Generative Adversarial Networks","created":"2018-02-16","cited_by_count":1636},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827},{"id":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"id":"1912.09363","title":"Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting","created":"2019-12-19","cited_by_count":761},{"id":"2011.04006","title":"Long Range Arena: A Benchmark for Efficient Transformers","created":"2020-11-08","cited_by_count":700},{"id":"1303.5778","title":"Speech Recognition with Deep Recurrent Neural Networks","created":"2013-03-22","cited_by_count":669},{"id":"2307.08621","title":"Retentive Network: A Successor to Transformer for Large Language Models","created":"2023-07-17","cited_by_count":613},{"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":"2212.14052","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","created":"2022-12-28","cited_by_count":499},{"id":"2206.11893","title":"On the Parameterization and Initialization of Diagonal State Space Models","created":"2022-06-23","cited_by_count":424},{"id":"2401.04722","title":"U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation","created":"2024-01-09","cited_by_count":419},{"id":"2303.06349","title":"Resurrecting Recurrent Neural Networks for Long Sequences","created":"2023-03-11","cited_by_count":408},{"id":"2302.10866","title":"Hyena Hierarchy: Towards Larger Convolutional Language Models","created":"2023-02-21","cited_by_count":393},{"id":"2206.13947","title":"Long Range Language Modeling via Gated State Spaces","created":"2022-06-27","cited_by_count":265},{"id":"2406.02818","title":"Chain of Agents: Large Language Models Collaborating on Long-Context Tasks","created":"2024-06-04","cited_by_count":206},{"id":"2209.10655","title":"Mega: Moving Average Equipped Gated Attention","created":"2022-09-21","cited_by_count":179},{"id":"2209.12951","title":"Liquid Structural State-Space Models","created":"2022-09-26","cited_by_count":136},{"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":"2404.07904","title":"HGRN2: Gated Linear RNNs with State Expansion","created":"2024-04-11","cited_by_count":127},{"id":"2405.16712","title":"Zamba: A Compact 7B SSM Hybrid Model","created":"2024-05-26","cited_by_count":124},{"id":"2404.06564","title":"MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection","created":"2024-04-09","cited_by_count":113},{"id":"2311.04823","title":"Hierarchically Gated Recurrent Neural Network for Sequence Modeling","created":"2023-11-08","cited_by_count":102},{"id":"2411.13676","title":"Hymba: A Hybrid-head Architecture for Small Language Models","created":"2024-11-20","cited_by_count":99},{"id":"2403.13600","title":"VL-Mamba: Exploring State Space Models for Multimodal Learning","created":"2024-03-20","cited_by_count":93},{"id":"2404.09498","title":"FusionMamba: Dynamic Feature Enhancement for Multimodal Image Fusion with Mamba","created":"2024-04-15","cited_by_count":81},{"id":"2403.00762","title":"Point Cloud Mamba: Point Cloud Learning via State Space Model","created":"2024-03-01","cited_by_count":66},{"id":"2105.05246","title":"Spectral Normalisation for Deep Reinforcement Learning: an Optimisation Perspective","created":"2021-05-11","cited_by_count":65},{"id":"2404.07839","title":"RecurrentGemma: Moving Past Transformers for Efficient Open Language Models","created":"2024-04-11","cited_by_count":64},{"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":"2404.15956","title":"A Survey on Visual Mamba","created":"2024-04-24","cited_by_count":50},{"id":"2305.04749","title":"Toeplitz Neural Network for Sequence Modeling","created":"2023-05-08","cited_by_count":43},{"id":"2404.18861","title":"Visual Mamba: A Survey and New Outlooks","created":"2024-04-29","cited_by_count":41},{"id":"2310.02367","title":"Linear Recurrent Units for Sequential Recommendation","created":"2023-10-03","cited_by_count":32},{"id":"2405.18014","title":"Coupled Mamba: Enhanced Multi-modal Fusion with Coupled State Space Model","created":"2024-05-28","cited_by_count":31},{"id":"2311.14495","title":"StableSSM: Alleviating the Curse of Memory in State-space Models through Stable Reparameterization","created":"2023-11-24","cited_by_count":30},{"id":"2107.02248","title":"A comparison of LSTM and GRU networks for learning symbolic sequences","created":"2021-07-05","cited_by_count":24},{"id":"2404.07794","title":"DGMamba: Domain Generalization via Generalized State Space Model","created":"2024-04-11","cited_by_count":21},{"id":"2406.16808","title":"Exploring the Capability of Mamba in Speech Applications","created":"2024-06-24","cited_by_count":20},{"id":"2310.19694","title":"Convolutional State Space Models for Long-Range Spatiotemporal Modeling","created":"2023-10-30","cited_by_count":19},{"id":"2410.02362","title":"A Comprehensive Survey of Mamba Architectures for Medical Image Analysis: Classification, Segmentation, Restoration and Beyond","created":"2024-10-03","cited_by_count":16},{"id":"2405.16440","title":"MambaTS: Improved Selective State Space Models for Long-term Time Series Forecasting","created":"2024-05-26","cited_by_count":14},{"id":"2406.03430","title":"Computation-Efficient Era: A Comprehensive Survey of State Space Models in Medical Image Analysis","created":"2024-06-05","cited_by_count":14},{"id":"2406.15131","title":"KalMamba: Towards Efficient Probabilistic State Space Models for RL under Uncertainty","created":"2024-06-21","cited_by_count":9},{"id":"2412.14847","title":"A Survey of RWKV","created":"2024-12-19","cited_by_count":6},{"id":"2407.09375","title":"HiPPO-Prophecy: State-Space Models can Provably Learn Dynamical Systems in Context","created":"2024-07-12","cited_by_count":3},{"id":"2502.01673","title":"Multilingual State Space Models for Structured Question Answering in Indic Languages","created":"2025-02-01","cited_by_count":3},{"id":"2503.10474","title":"Applying Tabular Deep Learning Models to Estimate Crash Injury Types of Young Motorcyclists","created":"2025-03-13","cited_by_count":2},{"id":"2503.11003","title":"Crash Severity Analysis of Child Bicyclists using Arm-Net and MambaNet","created":"2025-03-14","cited_by_count":2},{"id":"2109.02032","title":"Soft Hierarchical Graph Recurrent Networks for Many-Agent Partially Observable Environments","created":"2021-09-05","cited_by_count":1}],"next_cursor":null}