{"list":"other","total":53,"rows":[{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"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":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827},{"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":"1410.5401","title":"Neural Turing Machines","created":"2014-10-20","cited_by_count":644},{"id":"2307.08621","title":"Retentive Network: A Successor to Transformer for Large Language Models","created":"2023-07-17","cited_by_count":613},{"id":"2312.06635","title":"Gated Linear Attention Transformers with Hardware-Efficient Training","created":"2023-12-11","cited_by_count":514},{"id":"2102.11174","title":"Linear Transformers Are Secretly Fast Weight Programmers","created":"2021-02-22","cited_by_count":502},{"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":"2303.06349","title":"Resurrecting Recurrent Neural Networks for Long Sequences","created":"2023-03-11","cited_by_count":408},{"id":"2105.08050","title":"Pay Attention to MLPs","created":"2021-05-17","cited_by_count":368},{"id":"2103.02143","title":"Random Feature Attention","created":"2021-03-03","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":"2206.13947","title":"Long Range Language Modeling via Gated State Spaces","created":"2022-06-27","cited_by_count":265},{"id":"2402.19427","title":"Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models","created":"2024-02-29","cited_by_count":242},{"id":"2202.08791","title":"cosFormer: Rethinking Softmax in Attention","created":"2022-02-17","cited_by_count":213},{"id":"2402.18668","title":"Simple linear attention language models balance the recall-throughput tradeoff","created":"2024-02-28","cited_by_count":208},{"id":"2005.00743","title":"Synthesizer: Rethinking Self-Attention in Transformer Models","created":"2020-05-02","cited_by_count":205},{"id":"2312.04927","title":"Zoology: Measuring and Improving Recall in Efficient Language Models","created":"2023-12-08","cited_by_count":204},{"id":"2202.10447","title":"Transformer Quality in Linear Time","created":"2022-02-21","cited_by_count":191},{"id":"2209.10655","title":"Mega: Moving Average Equipped Gated Attention","created":"2022-09-21","cited_by_count":179},{"id":"2201.03533","title":"SCROLLS: Standardized CompaRison Over Long Language Sequences","created":"2022-01-10","cited_by_count":170},{"id":"2404.05892","title":"Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence","created":"2024-04-08","cited_by_count":159},{"id":"1709.04057","title":"Parallelizing Linear Recurrent Neural Nets Over Sequence Length","created":"2017-09-12","cited_by_count":127},{"id":"2311.04823","title":"Hierarchically Gated Recurrent Neural Network for Sequence Modeling","created":"2023-11-08","cited_by_count":102},{"id":"1810.09536","title":"Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks","created":"2018-10-22","cited_by_count":101},{"id":"2210.10340","title":"The Devil in Linear Transformer","created":"2022-10-19","cited_by_count":98},{"id":"2403.01590","title":"The Hidden Attention of Mamba Models","created":"2024-03-03","cited_by_count":91},{"id":"2210.09298","title":"What Makes Convolutional Models Great on Long Sequence Modeling?","created":"2022-10-17","cited_by_count":87},{"id":"2401.04658","title":"Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models","created":"2024-01-09","cited_by_count":57},{"id":"2209.07484","title":"Hydra Attention: Efficient Attention with Many Heads","created":"2022-09-15","cited_by_count":55},{"id":"2212.10544","title":"Pretraining Without Attention","created":"2022-12-20","cited_by_count":51},{"id":"2311.01927","title":"GateLoop: Fully Data-Controlled Linear Recurrence for Sequence Modeling","created":"2023-11-03","cited_by_count":46},{"id":"2305.04749","title":"Toeplitz Neural Network for Sequence Modeling","created":"2023-05-08","cited_by_count":43},{"id":"2110.02488","title":"ABC: Attention with Bounded-memory Control","created":"2021-10-06","cited_by_count":36},{"id":"1804.04849","title":"The unreasonable effectiveness of the forget gate","created":"2018-04-13","cited_by_count":34},{"id":"2210.04243","title":"Fine-Tuning Pre-trained Transformers into Decaying Fast Weights","created":"2022-10-09","cited_by_count":26},{"id":"2212.00768","title":"Simplifying and Understanding State Space Models with Diagonal Linear RNNs","created":"2022-12-01","cited_by_count":23},{"id":"2403.16899","title":"State Space Models as Foundation Models: A Control Theoretic Overview","created":"2024-03-25","cited_by_count":19},{"id":"2310.15719","title":"AGaLiTe: Approximate Gated Linear Transformers for Online Reinforcement Learning","created":"2023-10-24","cited_by_count":6},{"id":"2312.11135","title":"Linear Attention via Orthogonal Memory","created":"2023-12-18","cited_by_count":4},{"id":"1808.09029","title":"Pyramidal Recurrent Unit for Language Modeling","created":"2018-08-27","cited_by_count":2}],"next_cursor":null}