{"list":"other","total":54,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2012.07436","title":"Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting","created":"2020-12-14","cited_by_count":2169},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"2306.14048","title":"H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models","created":"2023-06-24","cited_by_count":832},{"id":"2301.10226","title":"A Watermark for Large Language Models","created":"2023-01-24","cited_by_count":725},{"id":"2012.09265","title":"Variational Quantum Algorithms","created":"2020-12-16","cited_by_count":692},{"id":"2003.05997","title":"Efficient Content-Based Sparse Attention with Routing Transformers","created":"2020-03-12","cited_by_count":471},{"id":"1902.10445","title":"Efficient Learning for Deep Quantum Neural Networks","created":"2019-02-27","cited_by_count":161},{"id":"2002.03231","title":"Soft Threshold Weight Reparameterization for Learnable Sparsity","created":"2020-02-08","cited_by_count":151},{"id":"2302.13214","title":"Fast Attention Requires Bounded Entries","created":"2023-02-26","cited_by_count":102},{"id":"2302.10870","title":"On Provable Copyright Protection for Generative Models","created":"2023-02-21","cited_by_count":98},{"id":"2111.12763","title":"Sparse is Enough in Scaling Transformers","created":"2021-11-24","cited_by_count":86},{"id":"1807.04271","title":"A quantum-inspired classical algorithm for recommendation systems","created":"2018-07-10","cited_by_count":70},{"id":"2302.02451","title":"KDEformer: Accelerating Transformers via Kernel Density Estimation","created":"2023-02-05","cited_by_count":58},{"id":"2304.10411","title":"Attention Scheme Inspired Softmax Regression","created":"2023-04-20","cited_by_count":49},{"id":"2209.08167","title":"Quantum Vision Transformers","created":"2022-09-16","cited_by_count":48},{"id":"2303.16504","title":"An Over-parameterized Exponential Regression","created":"2023-03-29","cited_by_count":45},{"id":"2010.05315","title":"SMYRF: Efficient Attention using Asymmetric Clustering","created":"2020-10-11","cited_by_count":43},{"id":"2304.13276","title":"The Closeness of In-Context Learning and Weight Shifting for Softmax Regression","created":"2023-04-26","cited_by_count":41},{"id":"1910.06151","title":"Sampling-based sublinear low-rank matrix arithmetic framework for dequantizing quantum machine learning","created":"2019-10-14","cited_by_count":37},{"id":"2304.02207","title":"Algorithm and Hardness for Dynamic Attention Maintenance in Large Language Models","created":"2023-04-05","cited_by_count":37},{"id":"2304.04397","title":"Randomized and Deterministic Attention Sparsification Algorithms for Over-parameterized Feature Dimension","created":"2023-04-10","cited_by_count":37},{"id":"2305.00660","title":"An Iterative Algorithm for Rescaled Hyperbolic Functions Regression","created":"2023-05-01","cited_by_count":35},{"id":"2110.04622","title":"Does Preprocessing Help Training Over-parameterized Neural Networks?","created":"2021-10-09","cited_by_count":32},{"id":"2303.03428","title":"Towards provably efficient quantum algorithms for large-scale machine-learning models","created":"2023-03-06","cited_by_count":32},{"id":"2305.20069","title":"A survey on the complexity of learning quantum states","created":"2023-05-31","cited_by_count":32},{"id":"2307.02419","title":"In-Context Learning for Attention Scheme: from Single Softmax Regression to Multiple Softmax Regression via a Tensor Trick","created":"2023-07-05","cited_by_count":32},{"id":"2306.04933","title":"InfoPrompt: Information-Theoretic Soft Prompt Tuning for Natural Language Understanding","created":"2023-06-08","cited_by_count":30},{"id":"2306.02295","title":"A Mathematical Abstraction for Balancing the Trade-off Between Creativity and Reality in Large Language Models","created":"2023-06-04","cited_by_count":29},{"id":"1705.01843","title":"Quantum SDP-Solvers: Better upper and lower bounds","created":"2017-05-04","cited_by_count":27},{"id":"2207.07563","title":"QSAN: A Near-term Achievable Quantum Self-Attention Network","created":"2022-07-14","cited_by_count":25},{"id":"2305.04701","title":"Differentially Private Attention Computation","created":"2023-05-08","cited_by_count":25},{"id":"2208.05395","title":"A Sublinear Adversarial Training Algorithm","created":"2022-08-10","cited_by_count":22},{"id":"2002.08240","title":"Quantum statistical query learning","created":"2020-02-19","cited_by_count":21},{"id":"1809.00643","title":"Convex optimization using quantum oracles","created":"2018-09-03","cited_by_count":19},{"id":"1811.04909","title":"Quantum-inspired low-rank stochastic regression with logarithmic dependence on the dimension","created":"2018-11-12","cited_by_count":18},{"id":"1808.09266","title":"A Quantum Interior Point Method for LPs and SDPs","created":"2018-08-28","cited_by_count":17},{"id":"1812.03089","title":"Quantum algorithms for feedforward neural networks","created":"2018-12-07","cited_by_count":14},{"id":"2009.06106","title":"Space-Efficient Interior Point Method, with applications to Linear Programming and Maximum Weight Bipartite Matching","created":"2020-09-13","cited_by_count":14},{"id":"1802.02325","title":"On The Hardness of Approximate and Exact (Bichromatic) Maximum Inner Product","created":"2018-02-07","cited_by_count":12},{"id":"2209.12897","title":"Quantum Speedups of Optimizing Approximately Convex Functions with Applications to Logarithmic Regret Stochastic Convex Bandits","created":"2022-09-26","cited_by_count":11},{"id":"2301.05605","title":"Differentially Private Continual Releases of Streaming Frequency Moment Estimations","created":"2023-01-13","cited_by_count":10},{"id":"1908.03903","title":"Quantum algorithm for estimating volumes of convex bodies","created":"2019-08-11","cited_by_count":8},{"id":"2002.05056","title":"Quantum Boosting","created":"2020-02-12","cited_by_count":8},{"id":"2009.07268","title":"An improved quantum-inspired algorithm for linear regression","created":"2020-09-15","cited_by_count":8},{"id":"2210.06539","title":"Quantum Algorithms for Sampling Log-Concave Distributions and Estimating Normalizing Constants","created":"2022-10-12","cited_by_count":8},{"id":"2107.09200","title":"A quantum algorithm for training wide and deep classical neural networks","created":"2021-07-19","cited_by_count":7}],"next_cursor":null}