{"list":"other","total":79,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"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":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"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":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"1712.05884","title":"Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions","created":"2017-12-16","cited_by_count":804},{"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":"2011.04006","title":"Long Range Arena: A Benchmark for Efficient Transformers","created":"2020-11-08","cited_by_count":700},{"id":"1912.05671","title":"Linear Mode Connectivity and the Lottery Ticket Hypothesis","created":"2019-12-11","cited_by_count":637},{"id":"2005.00341","title":"Jukebox: A Generative Model for Music","created":"2020-04-30","cited_by_count":542},{"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":"2005.07683","title":"Movement Pruning: Adaptive Sparsity by Fine-Tuning","created":"2020-05-15","cited_by_count":403},{"id":"2302.10866","title":"Hyena Hierarchy: Towards Larger Convolutional Language Models","created":"2023-02-21","cited_by_count":393},{"id":"1910.06711","title":"MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis","created":"2019-10-08","cited_by_count":354},{"id":"2203.14343","title":"Diagonal State Spaces are as Effective as Structured State Spaces","created":"2022-03-27","cited_by_count":350},{"id":"2102.01192","title":"Generative Spoken Language Modeling from Raw Audio","created":"2021-02-01","cited_by_count":340},{"id":"1811.00002","title":"WaveGlow: A Flow-based Generative Network for Speech Synthesis","created":"2018-10-31","cited_by_count":309},{"id":"2206.13947","title":"Long Range Language Modeling via Gated State Spaces","created":"2022-06-27","cited_by_count":265},{"id":"1705.07565","title":"Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon","created":"2017-05-22","cited_by_count":221},{"id":"1802.08435","title":"Efficient Neural Audio Synthesis","created":"2018-02-23","cited_by_count":219},{"id":"1907.04840","title":"Sparse Networks from Scratch: Faster Training without Losing Performance","created":"2019-07-10","cited_by_count":213},{"id":"2304.01433","title":"TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddings","created":"2023-04-04","cited_by_count":202},{"id":"2306.15794","title":"HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution","created":"2023-06-27","cited_by_count":194},{"id":"2209.10655","title":"Mega: Moving Average Equipped Gated Attention","created":"2022-09-21","cited_by_count":179},{"id":"2202.09729","title":"It's Raw! Audio Generation with State-Space Models","created":"2022-02-20","cited_by_count":171},{"id":"1805.02867","title":"Online normalizer calculation for softmax","created":"2018-05-08","cited_by_count":162},{"id":"2006.03236","title":"Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language Processing","created":"2020-06-05","cited_by_count":162},{"id":"2106.12672","title":"Charformer: Fast Character Transformers via Gradient-based Subword Tokenization","created":"2021-06-23","cited_by_count":160},{"id":"2209.12951","title":"Liquid Structural State-Space Models","created":"2022-09-26","cited_by_count":136},{"id":"2110.15343","title":"Scatterbrain: Unifying Sparse and Low-rank Attention Approximation","created":"2021-10-28","cited_by_count":130},{"id":"2206.12037","title":"How to Train Your HiPPO: State Space Models with Generalized Orthogonal Basis Projections","created":"2022-06-24","cited_by_count":122},{"id":"2102.02611","title":"CKConv: Continuous Kernel Convolution For Sequential Data","created":"2021-02-04","cited_by_count":120},{"id":"2204.00595","title":"Monarch: Expressive Structured Matrices for Efficient and Accurate Training","created":"2022-04-01","cited_by_count":106},{"id":"2303.14526","title":"Selective Structured State-Spaces for Long-Form Video Understanding","created":"2023-03-25","cited_by_count":105},{"id":"2107.02192","title":"Long-Short Transformer: Efficient Transformers for Language and Vision","created":"2021-07-05","cited_by_count":102},{"id":"2106.01540","title":"Luna: Linear Unified Nested Attention","created":"2021-06-03","cited_by_count":96},{"id":"1909.11646","title":"High Fidelity Speech Synthesis with Adversarial Networks","created":"2019-09-25","cited_by_count":92},{"id":"2210.09298","title":"What Makes Convolutional Models Great on Long Sequence Modeling?","created":"2022-10-17","cited_by_count":87},{"id":"1903.05895","title":"Learning Fast Algorithms for Linear Transforms Using Butterfly Factorizations","created":"2019-03-14","cited_by_count":76},{"id":"2112.00029","title":"Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models","created":"2021-11-30","cited_by_count":76},{"id":"2103.14636","title":"A Practical Survey on Faster and Lighter Transformers","created":"2021-03-26","cited_by_count":73},{"id":"2110.08059","title":"FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes","created":"2021-10-15","cited_by_count":66},{"id":"1806.10474","title":"The challenge of realistic music generation: modelling raw audio at scale","created":"2018-06-26","cited_by_count":63},{"id":"2310.12109","title":"Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture","created":"2023-10-18","cited_by_count":63},{"id":"2302.06646","title":"Simple Hardware-Efficient Long Convolutions for Sequence Modeling","created":"2023-02-13","cited_by_count":62},{"id":"2303.09489","title":"Effectively Modeling Time Series with Simple Discrete State Spaces","created":"2023-03-16","cited_by_count":54},{"id":"2212.10544","title":"Pretraining Without Attention","created":"2022-12-20","cited_by_count":51},{"id":"2212.14427","title":"Efficient Movie Scene Detection using State-Space Transformers","created":"2022-12-29","cited_by_count":51},{"id":"1510.01722","title":"Structured Transforms for Small-Footprint Deep Learning","created":"2015-10-06","cited_by_count":42},{"id":"2012.14966","title":"Kaleidoscope: An Efficient, Learnable Representation For All Structured Linear Maps","created":"2020-12-29","cited_by_count":36},{"id":"2105.03322","title":"Are Pre-trained Convolutions Better than Pre-trained Transformers?","created":"2021-05-07","cited_by_count":27},{"id":"2306.05167","title":"Decision S4: Efficient Sequence-Based RL via State Spaces Layers","created":"2023-06-08","cited_by_count":26},{"id":"2105.12842","title":"A Full-Stack Search Technique for Domain Optimized Deep Learning Accelerators","created":"2021-05-26","cited_by_count":19},{"id":"2308.15291","title":"Towards quantitative precision for ECG analysis: Leveraging state space models, self-supervision and patient metadata","created":"2023-08-29","cited_by_count":15},{"id":"2305.12498","title":"Multi-Head State Space Model for Speech Recognition","created":"2023-05-21","cited_by_count":14},{"id":"1905.11722","title":"A Graph Theoretic Framework of Recomputation Algorithms for Memory-Efficient Backpropagation","created":"2019-05-28","cited_by_count":11},{"id":"2210.17098","title":"Structured State Space Decoder for Speech Recognition and Synthesis","created":"2022-10-31","cited_by_count":11},{"id":"2304.02330","title":"SMPConv: Self-moving Point Representations for Continuous Convolution","created":"2023-04-05","cited_by_count":6},{"id":"2104.11471","title":"tcFFT: Accelerating Half-Precision FFT through Tensor Cores","created":"2021-04-23","cited_by_count":5}],"next_cursor":null}