{"list":"other","total":86,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"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":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"2309.17453","title":"Efficient Streaming Language Models with Attention Sinks","created":"2023-09-29","cited_by_count":2186},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"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":"2406.12793","title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","created":"2024-06-18","cited_by_count":1121},{"id":"2402.13718","title":"$\\infty$Bench: Extending Long Context Evaluation Beyond 100K Tokens","created":"2024-02-21","cited_by_count":367},{"id":"2410.10819","title":"DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads","created":"2024-10-14","cited_by_count":288},{"id":"2110.10090","title":"Inductive Biases and Variable Creation in Self-Attention Mechanisms","created":"2021-10-19","cited_by_count":144},{"id":"2110.15343","title":"Scatterbrain: Unifying Sparse and Low-rank Attention Approximation","created":"2021-10-28","cited_by_count":130},{"id":"2502.20766","title":"FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference","created":"2025-02-28","cited_by_count":123},{"id":"2107.13163","title":"Statistically Meaningful Approximation: a Case Study on Approximating Turing Machines with Transformers","created":"2021-07-28","cited_by_count":102},{"id":"2302.13214","title":"Fast Attention Requires Bounded Entries","created":"2023-02-26","cited_by_count":102},{"id":"1810.07896","title":"Solving Linear Programs in the Current Matrix Multiplication Time","created":"2018-10-18","cited_by_count":100},{"id":"2310.05869","title":"HyperAttention: Long-context Attention in Near-Linear Time","created":"2023-10-09","cited_by_count":85},{"id":"2204.13807","title":"A very preliminary analysis of DALL-E 2","created":"2022-04-25","cited_by_count":82},{"id":"2112.00029","title":"Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models","created":"2021-11-30","cited_by_count":76},{"id":"2112.07628","title":"Training Multi-Layer Over-Parametrized Neural Network in Subquadratic Time","created":"2021-12-14","cited_by_count":62},{"id":"2302.02451","title":"KDEformer: Accelerating Transformers via Kernel Density Estimation","created":"2023-02-05","cited_by_count":58},{"id":"1905.04447","title":"Solving Empirical Risk Minimization in the Current Matrix Multiplication Time","created":"2019-05-11","cited_by_count":53},{"id":"2304.10411","title":"Attention Scheme Inspired Softmax Regression","created":"2023-04-20","cited_by_count":49},{"id":"2303.08117","title":"Do Transformers Parse while Predicting the Masked Word?","created":"2023-03-14","cited_by_count":48},{"id":"2403.01876","title":"D\\'ej\\`aVu: KV-cache Streaming for Fast, Fault-tolerant Generative LLM Serving","created":"2024-03-04","cited_by_count":48},{"id":"2007.02876","title":"A Mathematical Theory of Attention","created":"2020-07-06","cited_by_count":46},{"id":"1704.08246","title":"Relative Error Tensor Low Rank Approximation","created":"2017-04-26","cited_by_count":45},{"id":"2303.16504","title":"An Over-parameterized Exponential Regression","created":"2023-03-29","cited_by_count":45},{"id":"2004.07470","title":"Faster Dynamic Matrix Inverse for Faster LPs","created":"2020-04-16","cited_by_count":44},{"id":"2303.15725","title":"Solving Regularized Exp, Cosh and Sinh Regression Problems","created":"2023-03-28","cited_by_count":44},{"id":"2310.04064","title":"How to Capture Higher-order Correlations? Generalizing Matrix Softmax Attention to Kronecker Computation","created":"2023-10-06","cited_by_count":44},{"id":"2405.08944","title":"Challenges in Deploying Long-Context Transformers: A Theoretical Peak Performance Analysis","created":"2024-05-14","cited_by_count":44},{"id":"2010.05315","title":"SMYRF: Efficient Attention using Asymmetric Clustering","created":"2020-10-11","cited_by_count":43},{"id":"2103.07601","title":"Approximating How Single Head Attention Learns","created":"2021-03-13","cited_by_count":38},{"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":"2211.06033","title":"A Faster Small Treewidth SDP Solver","created":"2022-11-11","cited_by_count":36},{"id":"2305.00660","title":"An Iterative Algorithm for Rescaled Hyperbolic Functions Regression","created":"2023-05-01","cited_by_count":35},{"id":"2108.09420","title":"Fast Sketching of Polynomial Kernels of Polynomial Degree","created":"2021-08-21","cited_by_count":33},{"id":"2206.08898","title":"SimA: Simple Softmax-free Attention for Vision Transformers","created":"2022-06-17","cited_by_count":32},{"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":"2402.04497","title":"The Fine-Grained Complexity of Gradient Computation for Training Large Language Models","created":"2024-02-07","cited_by_count":30},{"id":"1712.09473","title":"Sketching for Kronecker Product Regression and P-splines","created":"2017-12-27","cited_by_count":29},{"id":"1909.13384","title":"Optimal Sketching for Kronecker Product Regression and Low Rank Approximation","created":"2019-09-29","cited_by_count":29},{"id":"2204.03209","title":"Speeding Up Sparsification using Inner Product Search Data Structures","created":"2022-04-07","cited_by_count":22},{"id":"2208.05395","title":"A Sublinear Adversarial Training Algorithm","created":"2022-08-10","cited_by_count":22},{"id":"2210.11542","title":"Sketching Meets Differential Privacy: Fast Algorithm for Dynamic Kronecker Projection Maintenance","created":"2022-10-20","cited_by_count":22},{"id":"1506.04448","title":"Fast and Guaranteed Tensor Decomposition via Sketching","created":"2015-06-14","cited_by_count":19},{"id":"2210.03961","title":"Dynamic Tensor Product Regression","created":"2022-10-08","cited_by_count":17},{"id":"2011.07471","title":"Tight Bounds for Adversarially Robust Streams and Sliding Windows via Difference Estimators","created":"2020-11-15","cited_by_count":16},{"id":"2307.08352","title":"Zero-th Order Algorithm for Softmax Attention Optimization","created":"2023-07-17","cited_by_count":16},{"id":"2405.12528","title":"SirLLM: Streaming Infinite Retentive LLM","created":"2024-05-21","cited_by_count":16},{"id":"2303.12298","title":"A General Algorithm for Solving Rank-one Matrix Sensing","created":"2023-03-22","cited_by_count":15},{"id":"2212.11408","title":"Adaptive and Dynamic Multi-Resolution Hashing for Pairwise Summations","created":"2022-12-21","cited_by_count":14},{"id":"2310.00726","title":"Improving Length-Generalization in Transformers via Task Hinting","created":"2023-10-01","cited_by_count":13},{"id":"2305.08367","title":"Toward Highly Efficient and Private Submodular Maximization via Matrix-Based Acceleration","created":"2023-05-15","cited_by_count":11},{"id":"1907.03197","title":"Composable Core-sets for Determinant Maximization: A Simple Near-Optimal Algorithm","created":"2019-07-06","cited_by_count":9},{"id":"2004.10969","title":"Non-Adaptive Adaptive Sampling on Turnstile Streams","created":"2020-04-23","cited_by_count":9},{"id":"2505.11892","title":"Fast RoPE Attention: Combining the Polynomial Method and Fast Fourier Transform","created":"2025-05-17","cited_by_count":9},{"id":"1406.4519","title":"DFacTo: Distributed Factorization of Tensors","created":"2014-06-17","cited_by_count":8},{"id":"2304.06594","title":"Solving Tensor Low Cycle Rank Approximation","created":"2023-04-13","cited_by_count":8},{"id":"1807.11648","title":"Composable Core-sets for Determinant Maximization Problems via Spectral Spanners","created":"2018-07-31","cited_by_count":7},{"id":"2503.04724","title":"LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM","created":"2025-03-06","cited_by_count":7},{"id":"2505.16284","title":"Only Large Weights (And Not Skip Connections) Can Prevent the Perils of Rank Collapse","created":"2025-05-22","cited_by_count":7},{"id":"2205.14816","title":"Fast Distance Oracles for Any Symmetric Norm","created":"2022-05-30","cited_by_count":6},{"id":"2308.08358","title":"Convergence of Two-Layer Regression with Nonlinear Units","created":"2023-08-16","cited_by_count":6},{"id":"2108.12017","title":"Truly Perfect Samplers for Data Streams and Sliding Windows","created":"2021-08-26","cited_by_count":5},{"id":"2309.05135","title":"Streaming Semidefinite Programs: $O(\\sqrt{n})$ Passes, Small Space and Fast Runtime","created":"2023-09-10","cited_by_count":5},{"id":"1309.0787","title":"Online Tensor Methods for Learning Latent Variable Models","created":"2013-09-03","cited_by_count":4},{"id":"1808.05497","title":"Perfect $L_p$ Sampling in a Data Stream","created":"2018-08-16","cited_by_count":4},{"id":"2207.07417","title":"Near-Linear Time and Fixed-Parameter Tractable Algorithms for Tensor Decompositions","created":"2022-07-15","cited_by_count":4},{"id":"2211.14825","title":"Dynamic Kernel Graph Sparsifiers","created":"2022-11-27","cited_by_count":4},{"id":"1502.05023","title":"A New Sampling Technique for Tensors","created":"2015-02-17","cited_by_count":2},{"id":"2207.07822","title":"Adaptive Sketches for Robust Regression with Importance Sampling","created":"2022-07-16","cited_by_count":2},{"id":"1907.02218","title":"Sampling Sketches for Concave Sublinear Functions of Frequencies","created":"2019-07-04","cited_by_count":1},{"id":"2407.04931","title":"Universal Perfect Samplers for Incremental Streams","created":"2024-07-06","cited_by_count":1},{"id":"2504.07237","title":"Perfect Sampling in Turnstile Streams Beyond Small Moments","created":"2025-04-09","cited_by_count":1}],"next_cursor":null}