{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"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":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"2408.03314","title":"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters","created":"2024-08-06","cited_by_count":1986},{"id":"1609.08144","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","created":"2016-09-26","cited_by_count":1475},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815},{"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":"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":"1710.01878","title":"To prune, or not to prune: exploring the efficacy of pruning for model compression","created":"2017-10-05","cited_by_count":603},{"id":"1911.11134","title":"Rigging the Lottery: Making All Tickets Winners","created":"2019-11-25","cited_by_count":495},{"id":"1609.07061","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","created":"2016-09-22","cited_by_count":426},{"id":"2206.11893","title":"On the Parameterization and Initialization of Diagonal State Space Models","created":"2022-06-23","cited_by_count":424},{"id":"1707.04780","title":"Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science","created":"2017-07-15","cited_by_count":328},{"id":"2007.12223","title":"The Lottery Ticket Hypothesis for Pre-trained BERT Networks","created":"2020-07-23","cited_by_count":275},{"id":"2003.02389","title":"Comparing Rewinding and Fine-tuning in Neural Network Pruning","created":"2020-03-05","cited_by_count":240},{"id":"2306.15794","title":"HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution","created":"2023-06-27","cited_by_count":194},{"id":"2004.09602","title":"Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation","created":"2020-04-20","cited_by_count":188},{"id":"2202.09729","title":"It's Raw! Audio Generation with State-Space Models","created":"2022-02-20","cited_by_count":171},{"id":"2005.13981","title":"The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Results","created":"2020-05-16","cited_by_count":133},{"id":"2303.03982","title":"Structured State Space Models for In-Context Reinforcement Learning","created":"2023-03-07","cited_by_count":111},{"id":"2111.03746","title":"Efficient Neuromorphic Signal Processing with Loihi 2","created":"2021-11-05","cited_by_count":96},{"id":"2310.04564","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models","created":"2023-10-06","cited_by_count":94},{"id":"2407.04153","title":"Mixture of A Million Experts","created":"2024-07-04","cited_by_count":72},{"id":"2402.03804","title":"ReLU$^2$ Wins: Discovering Efficient Activation Functions for Sparse LLMs","created":"2024-02-06","cited_by_count":67},{"id":"2303.11510","title":"ICASSP 2023 Deep Noise Suppression Challenge","created":"2023-03-21","cited_by_count":65},{"id":"2403.17844","title":"Mechanistic Design and Scaling of Hybrid Architectures","created":"2024-03-26","cited_by_count":59},{"id":"2101.01902","title":"Interspeech 2021 Deep Noise Suppression Challenge","created":"2021-01-06","cited_by_count":47},{"id":"2012.08749","title":"Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks","created":"2020-12-16","cited_by_count":40},{"id":"2307.11888","title":"Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvalues","created":"2023-07-21","cited_by_count":36},{"id":"2310.03251","title":"Efficient Video and Audio processing with Loihi 2","created":"2023-10-05","cited_by_count":29},{"id":"2009.06122","title":"ICASSP 2021 Deep Noise Suppression Challenge","created":"2020-09-14","cited_by_count":27},{"id":"2010.14495","title":"Are wider nets better given the same number of parameters?","created":"2020-10-27","cited_by_count":27},{"id":"2302.02596","title":"Ten Lessons We Have Learned in the New \"Sparseland\": A Short Handbook for Sparse Neural Network Researchers","created":"2023-02-06","cited_by_count":25},{"id":"2407.12397","title":"Mamba-PTQ: Outlier Channels in Recurrent Large Language Models","created":"2024-07-17","cited_by_count":15},{"id":"1611.02024","title":"Sigma Delta Quantized Networks","created":"2016-11-07","cited_by_count":13},{"id":"2304.14082","title":"JaxPruner: A concise library for sparsity research","created":"2023-04-27","cited_by_count":13},{"id":"2303.09503","title":"The Intel Neuromorphic DNS Challenge","created":"2023-03-16","cited_by_count":10},{"id":"2406.09477","title":"Q-S5: Towards Quantized State Space Models","created":"2024-06-13","cited_by_count":10},{"id":"2101.05453","title":"On the quantization of recurrent neural networks","created":"2021-01-14","cited_by_count":7},{"id":"2409.15022","title":"A Diagonal Structured State Space Model on Loihi 2 for Efficient Streaming Sequence Processing","created":"2024-09-23","cited_by_count":6},{"id":"2412.04358","title":"Approximate Top-$k$ for Increased Parallelism","created":"2024-12-05","cited_by_count":5},{"id":"2110.02402","title":"Language Modeling using LMUs: 10x Better Data Efficiency or Improved Scaling Compared to Transformers","created":"2021-10-05","cited_by_count":3},{"id":"2405.00433","title":"Weight Sparsity Complements Activity Sparsity in Neuromorphic Language Models","created":"2024-05-01","cited_by_count":1}],"next_cursor":null}