{"list":"other","total":64,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"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":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"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":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"2211.05102","title":"Efficiently Scaling Transformer Inference","created":"2022-11-09","cited_by_count":539},{"id":"2003.05997","title":"Efficient Content-Based Sparse Attention with Routing Transformers","created":"2020-03-12","cited_by_count":471},{"id":"2102.03902","title":"Nystr\\\"omformer: A Nystr\\\"om-Based Algorithm for Approximating Self-Attention","created":"2021-02-07","cited_by_count":471},{"id":"1506.07503","title":"Attention-Based Models for Speech Recognition","created":"2015-06-24","cited_by_count":401},{"id":"2103.02143","title":"Random Feature Attention","created":"2021-03-03","cited_by_count":354},{"id":"2111.07624","title":"Attention Mechanisms in Computer Vision: A Survey","created":"2021-11-15","cited_by_count":232},{"id":"2405.12981","title":"Reducing Transformer Key-Value Cache Size with Cross-Layer Attention","created":"2024-05-21","cited_by_count":131},{"id":"2403.09054","title":"Keyformer: KV Cache Reduction through Key Tokens Selection for Efficient Generative Inference","created":"2024-03-14","cited_by_count":126},{"id":"2302.13214","title":"Fast Attention Requires Bounded Entries","created":"2023-02-26","cited_by_count":102},{"id":"2310.05869","title":"HyperAttention: Long-context Attention in Near-Linear Time","created":"2023-10-09","cited_by_count":85},{"id":"1603.08675","title":"Quantum Recommendation Systems","created":"2016-03-29","cited_by_count":70},{"id":"1812.03584","title":"q-means: A quantum algorithm for unsupervised machine learning","created":"2018-12-10","cited_by_count":55},{"id":"2410.03111","title":"LoRC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression Strategy","created":"2024-10-04","cited_by_count":51},{"id":"2010.05315","title":"SMYRF: Efficient Attention using Asymmetric Clustering","created":"2020-10-11","cited_by_count":43},{"id":"2502.14051","title":"RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression","created":"2025-02-19","cited_by_count":41},{"id":"2304.02207","title":"Algorithm and Hardness for Dynamic Attention Maintenance in Large Language Models","created":"2023-04-05","cited_by_count":37},{"id":"2310.01655","title":"PolySketchFormer: Fast Transformers via Sketching Polynomial Kernels","created":"2023-10-02","cited_by_count":36},{"id":"2307.07970","title":"New Bounds for Matrix Multiplication: from Alpha to Omega","created":"2023-07-16","cited_by_count":34},{"id":"1911.00111","title":"Quantum Wasserstein Generative Adversarial Networks","created":"2019-10-31","cited_by_count":33},{"id":"2302.11068","title":"Low Rank Matrix Completion via Robust Alternating Minimization in Nearly Linear Time","created":"2023-02-21","cited_by_count":31},{"id":"1705.01843","title":"Quantum SDP-Solvers: Better upper and lower bounds","created":"2017-05-04","cited_by_count":27},{"id":"2404.16349","title":"More Asymmetry Yields Faster Matrix Multiplication","created":"2024-04-25","cited_by_count":27},{"id":"2502.03805","title":"CriticalKV: Optimizing KV Cache Eviction from an Output Perturbation Perspective","created":"2025-02-06","cited_by_count":26},{"id":"2402.06082","title":"SubGen: Token Generation in Sublinear Time and Memory","created":"2024-02-08","cited_by_count":21},{"id":"2308.14304","title":"Solving Attention Kernel Regression Problem via Pre-conditioner","created":"2023-08-28","cited_by_count":20},{"id":"1809.00643","title":"Convex optimization using quantum oracles","created":"2018-09-03","cited_by_count":19},{"id":"1904.02276","title":"Sublinear quantum algorithms for training linear and kernel-based classifiers","created":"2019-04-04","cited_by_count":19},{"id":"2210.10173","title":"Faster Matrix Multiplication via Asymmetric Hashing","created":"2022-10-18","cited_by_count":19},{"id":"2410.10165","title":"HSR-Enhanced Sparse Attention Acceleration","created":"2024-10-14","cited_by_count":19},{"id":"1808.09266","title":"A Quantum Interior Point Method for LPs and SDPs","created":"2018-08-28","cited_by_count":17},{"id":"1708.07788","title":"Stability of the Lanczos Method for Matrix Function Approximation","created":"2017-08-25","cited_by_count":16},{"id":"2111.09787","title":"Near-Optimal Quantum Algorithms for Multivariate Mean Estimation","created":"2021-11-18","cited_by_count":16},{"id":"1809.01731","title":"Quantum algorithms and lower bounds for convex optimization","created":"2018-09-04","cited_by_count":15},{"id":"2308.01582","title":"Quantum speedups for stochastic optimization","created":"2023-08-03","cited_by_count":12},{"id":"2110.13086","title":"Quantum Algorithms and Lower Bounds for Linear Regression with Norm Constraints","created":"2021-10-25","cited_by_count":11},{"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":"1911.07306","title":"Quantum Speedup for Graph Sparsification, Cut Approximation and Laplacian Solving","created":"2019-11-17","cited_by_count":8},{"id":"2306.02826","title":"Near-Optimal Quantum Coreset Construction Algorithms for Clustering","created":"2023-06-05","cited_by_count":6},{"id":"2412.16187","title":"HashEvict: A Pre-Attention KV Cache Eviction Strategy using Locality-Sensitive Hashing","created":"2024-12-13","cited_by_count":6},{"id":"1908.06720","title":"Quantum algorithms for Second-Order Cone Programming and Support Vector Machines","created":"2019-08-19","cited_by_count":4},{"id":"2406.03006","title":"Quantum Algorithms and Lower Bounds for Finite-Sum Optimization","created":"2024-06-05","cited_by_count":4},{"id":"2507.23539","title":"Improved Algorithms for Kernel Matrix-Vector Multiplication Under Sparsity Assumptions","created":"2025-07-31","cited_by_count":4},{"id":"2311.03215","title":"Quantum speedups for linear programming via interior point methods","created":"2023-11-06","cited_by_count":3},{"id":"2410.05462","title":"LevAttention: Time, Space, and Streaming Efficient Algorithm for Heavy Attentions","created":"2024-10-07","cited_by_count":3},{"id":"2011.12823","title":"Quantum algorithms for matrix scaling and matrix balancing","created":"2020-11-25","cited_by_count":2},{"id":"2110.03879","title":"Explaining the Attention Mechanism of End-to-End Speech Recognition Using Decision Trees","created":"2021-10-08","cited_by_count":2},{"id":"2410.21550","title":"Deterministic complexity analysis of Hermitian eigenproblems","created":"2024-10-28","cited_by_count":2},{"id":"2503.11108","title":"Time and Memory Trade-off of KV-Cache Compression in Tensor Transformer Decoding","created":"2025-03-14","cited_by_count":2},{"id":"2402.12745","title":"Near-Optimal Quantum Algorithm for Minimizing the Maximal Loss","created":"2024-02-20","cited_by_count":1}],"next_cursor":null}