{"list":"other","total":67,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"1906.02243","title":"Energy and Policy Considerations for Deep Learning in NLP","created":"2019-06-05","cited_by_count":1254},{"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":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788},{"id":"1804.03209","title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition","created":"2018-04-09","cited_by_count":752},{"id":"1612.08083","title":"Language Modeling with Gated Convolutional Networks","created":"2016-12-23","cited_by_count":702},{"id":"2011.04006","title":"Long Range Arena: A Benchmark for Efficient Transformers","created":"2020-11-08","cited_by_count":700},{"id":"1901.09948","title":"Surrogate Gradient Learning in Spiking Neural Networks","created":"2019-01-28","cited_by_count":626},{"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":"2102.03902","title":"Nystr\\\"omformer: A Nystr\\\"om-Based Algorithm for Approximating Self-Attention","created":"2021-02-07","cited_by_count":471},{"id":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463},{"id":"2206.11893","title":"On the Parameterization and Initialization of Diagonal State Space Models","created":"2022-06-23","cited_by_count":424},{"id":"2303.06349","title":"Resurrecting Recurrent Neural Networks for Long Sequences","created":"2023-03-11","cited_by_count":408},{"id":"1706.02609","title":"Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks","created":"2017-06-08","cited_by_count":406},{"id":"2302.10866","title":"Hyena Hierarchy: Towards Larger Convolutional Language Models","created":"2023-02-21","cited_by_count":393},{"id":"2203.14343","title":"Diagonal State Spaces are as Effective as Structured State Spaces","created":"2022-03-27","cited_by_count":350},{"id":"2105.03824","title":"FNet: Mixing Tokens with Fourier Transforms","created":"2021-05-09","cited_by_count":347},{"id":"2102.04159","title":"Deep Residual Learning in Spiking Neural Networks","created":"2021-02-08","cited_by_count":331},{"id":"2209.15425","title":"Spikformer: When Spiking Neural Network Meets Transformer","created":"2022-09-29","cited_by_count":271},{"id":"2109.12894","title":"Training Spiking Neural Networks Using Lessons From Deep Learning","created":"2021-09-27","cited_by_count":259},{"id":"1506.00019","title":"A Critical Review of Recurrent Neural Networks for Sequence Learning","created":"2015-05-29","cited_by_count":224},{"id":"1612.01064","title":"Trained Ternary Quantization","created":"2016-12-04","cited_by_count":208},{"id":"2207.04901","title":"Exploring Length Generalization in Large Language Models","created":"2022-07-11","cited_by_count":206},{"id":"1803.09574","title":"Long short-term memory and learning-to-learn in networks of spiking neurons","created":"2018-03-26","cited_by_count":181},{"id":"2209.10655","title":"Mega: Moving Average Equipped Gated Attention","created":"2022-09-21","cited_by_count":179},{"id":"2106.10165","title":"The Principles of Deep Learning Theory","created":"2021-06-18","cited_by_count":173},{"id":"2307.01694","title":"Spike-driven Transformer","created":"2023-07-04","cited_by_count":146},{"id":"2209.12951","title":"Liquid Structural State-Space Models","created":"2022-09-26","cited_by_count":136},{"id":"1504.00941","title":"A Simple Way to Initialize Recurrent Networks of Rectified Linear Units","created":"2015-04-03","cited_by_count":130},{"id":"1804.06028","title":"ListOps: A Diagnostic Dataset for Latent Tree Learning","created":"2018-04-17","cited_by_count":129},{"id":"2103.12593","title":"Accurate and efficient time-domain classification with adaptive spiking recurrent neural networks","created":"2021-03-12","cited_by_count":115},{"id":"2107.12375","title":"Geometric Deep Learning on Molecular Representations","created":"2021-07-26","cited_by_count":113},{"id":"2111.03746","title":"Efficient Neuromorphic Signal Processing with Loihi 2","created":"2021-11-05","cited_by_count":96},{"id":"2302.13939","title":"SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networks","created":"2023-02-27","cited_by_count":88},{"id":"2305.13304","title":"RecurrentGPT: Interactive Generation of (Arbitrarily) Long Text","created":"2023-05-22","cited_by_count":84},{"id":"2311.18257","title":"Diffusion Models Without Attention","created":"2023-11-30","cited_by_count":75},{"id":"2311.12351","title":"Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Survey","created":"2023-11-21","cited_by_count":72},{"id":"1610.10099","title":"Neural Machine Translation in Linear Time","created":"2016-10-31","cited_by_count":66},{"id":"1603.00391","title":"Noisy Activation Functions","created":"2016-03-01","cited_by_count":53},{"id":"2107.11906","title":"H-Transformer-1D: Fast One-Dimensional Hierarchical Attention for Sequences","created":"2021-07-25","cited_by_count":47},{"id":"2210.06583","title":"S4ND: Modeling Images and Videos as Multidimensional Signals Using State Spaces","created":"2022-10-12","cited_by_count":41},{"id":"2210.13107","title":"An Analytical Estimation of Spiking Neural Networks Energy Efficiency","created":"2022-10-24","cited_by_count":38},{"id":"2211.11176","title":"Modeling Multivariate Biosignals With Graph Neural Networks and Structured State Space Models","created":"2022-11-21","cited_by_count":29},{"id":"2301.11929","title":"Training Full Spike Neural Networks via Auxiliary Accumulation Pathway","created":"2023-01-27","cited_by_count":26},{"id":"2102.11417","title":"Parallelizing Legendre Memory Unit Training","created":"2021-02-22","cited_by_count":23},{"id":"2306.03693","title":"ESL-SNNs: An Evolutionary Structure Learning Strategy for Spiking Neural Networks","created":"2023-06-06","cited_by_count":23},{"id":"2309.03641","title":"Spiking Structured State Space Model for Monaural Speech Enhancement","created":"2023-09-07","cited_by_count":23},{"id":"1812.05981","title":"Why ReLU Units Sometimes Die: Analysis of Single-Unit Error Backpropagation in Neural Networks","created":"2018-12-14","cited_by_count":12},{"id":"2304.12776","title":"State Spaces Aren't Enough: Machine Translation Needs Attention","created":"2023-04-25","cited_by_count":9},{"id":"2201.11915","title":"The fine line between dead neurons and sparsity in binarized spiking neural networks","created":"2022-01-28","cited_by_count":8},{"id":"2303.10780","title":"A Comprehensive Review of Spiking Neural Networks: Interpretation, Optimization, Efficiency, and Best Practices","created":"2023-03-19","cited_by_count":8},{"id":"2010.01795","title":"DCT-SNN: Using DCT to Distribute Spatial Information over Time for Learning Low-Latency Spiking Neural Networks","created":"2020-10-05","cited_by_count":4},{"id":"2306.12666","title":"Accelerating SNN Training with Stochastic Parallelizable Spiking Neurons","created":"2023-06-22","cited_by_count":4}],"next_cursor":null}