{"list":"other","total":75,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"2309.17453","title":"Efficient Streaming Language Models with Attention Sinks","created":"2023-09-29","cited_by_count":2186},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"2405.21060","title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","created":"2024-05-31","cited_by_count":1336},{"id":"2306.00978","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","created":"2023-06-01","cited_by_count":1298},{"id":"2301.00774","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","created":"2023-01-02","cited_by_count":1121},{"id":"2401.10774","title":"Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads","created":"2024-01-19","cited_by_count":843},{"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":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"2004.10568","title":"Up or Down? Adaptive Rounding for Post-Training Quantization","created":"2020-04-22","cited_by_count":621},{"id":"2003.03033","title":"What is the State of Neural Network Pruning?","created":"2020-03-06","cited_by_count":583},{"id":"2102.00554","title":"Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks","created":"2021-01-31","cited_by_count":527},{"id":"2407.08608","title":"FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision","created":"2024-07-11","cited_by_count":519},{"id":"2406.10774","title":"Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference","created":"2024-06-16","cited_by_count":501},{"id":"2006.05467","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","created":"2020-06-09","cited_by_count":479},{"id":"2102.05426","title":"BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction","created":"2021-02-10","cited_by_count":479},{"id":"2310.01801","title":"Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs","created":"2023-10-03","cited_by_count":474},{"id":"2002.07376","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","created":"2020-02-18","cited_by_count":471},{"id":"2302.10866","title":"Hyena Hierarchy: Towards Larger Convolutional Language Models","created":"2023-02-21","cited_by_count":393},{"id":"1811.03115","title":"Blockwise Parallel Decoding for Deep Autoregressive Models","created":"2018-11-07","cited_by_count":323},{"id":"2208.11580","title":"Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning","created":"2022-08-24","cited_by_count":322},{"id":"2404.16710","title":"LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding","created":"2024-04-25","cited_by_count":307},{"id":"2310.17157","title":"Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time","created":"2023-10-26","cited_by_count":252},{"id":"2310.06201","title":"Compressing Context to Enhance Inference Efficiency of Large Language Models","created":"2023-10-09","cited_by_count":189},{"id":"2204.09656","title":"A Fast Post-Training Pruning Framework for Transformers","created":"2022-03-29","cited_by_count":162},{"id":"2402.04347","title":"The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry","created":"2024-02-06","cited_by_count":120},{"id":"2102.08124","title":"Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N:M Transposable Masks","created":"2021-02-16","cited_by_count":103},{"id":"2302.13214","title":"Fast Attention Requires Bounded Entries","created":"2023-02-26","cited_by_count":102},{"id":"2404.11912","title":"TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding","created":"2024-04-18","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":"2402.09398","title":"Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference","created":"2024-02-14","cited_by_count":75},{"id":"2107.07467","title":"Only Train Once: A One-Shot Neural Network Training And Pruning Framework","created":"2021-07-15","cited_by_count":70},{"id":"2112.07628","title":"Training Multi-Layer Over-Parametrized Neural Network in Subquadratic Time","created":"2021-12-14","cited_by_count":62},{"id":"2006.11648","title":"Training (Overparametrized) Neural Networks in Near-Linear Time","created":"2020-06-20","cited_by_count":58},{"id":"2302.02451","title":"KDEformer: Accelerating Transformers via Kernel Density Estimation","created":"2023-02-05","cited_by_count":58},{"id":"2004.04250","title":"An Improved Cutting Plane Method for Convex Optimization, Convex-Concave Games and its Applications","created":"2020-04-08","cited_by_count":57},{"id":"1906.03728","title":"The Generalization-Stability Tradeoff In Neural Network Pruning","created":"2019-06-09","cited_by_count":54},{"id":"1905.04447","title":"Solving Empirical Risk Minimization in the Current Matrix Multiplication Time","created":"2019-05-11","cited_by_count":53},{"id":"2009.10217","title":"A Faster Interior Point Method for Semidefinite Programming","created":"2020-09-21","cited_by_count":53},{"id":"2406.03482","title":"QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead","created":"2024-06-05","cited_by_count":52},{"id":"2405.06640","title":"Linearizing Large Language Models","created":"2024-05-10","cited_by_count":51},{"id":"1910.11957","title":"A Deterministic Linear Program Solver in Current Matrix Multiplication Time","created":"2019-10-25","cited_by_count":42},{"id":"2402.04520","title":"On Computational Limits of Modern Hopfield Models: A Fine-Grained Complexity Analysis","created":"2024-02-07","cited_by_count":41},{"id":"2407.01079","title":"On Statistical Rates and Provably Efficient Criteria of Latent Diffusion Transformers (DiTs)","created":"2024-07-01","cited_by_count":40},{"id":"2404.03827","title":"Uniform Memory Retrieval with Larger Capacity for Modern Hopfield Models","created":"2024-04-04","cited_by_count":38},{"id":"2404.03828","title":"Outlier-Efficient Hopfield Layers for Large Transformer-Based Models","created":"2024-04-04","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":"2211.06033","title":"A Faster Small Treewidth SDP Solver","created":"2022-11-11","cited_by_count":36},{"id":"2312.17346","title":"STanHop: Sparse Tandem Hopfield Model for Memory-Enhanced Time Series Prediction","created":"2023-12-28","cited_by_count":35},{"id":"2307.07970","title":"New Bounds for Matrix Multiplication: from Alpha to Omega","created":"2023-07-16","cited_by_count":34},{"id":"2101.08208","title":"Solving SDP Faster: A Robust IPM Framework and Efficient Implementation","created":"2021-01-20","cited_by_count":33},{"id":"2405.05219","title":"Conv-Basis: A New Paradigm for Efficient Attention Inference and Gradient Computation in Transformers","created":"2024-05-08","cited_by_count":32},{"id":"2210.13738","title":"Pruning's Effect on Generalization Through the Lens of Training and Regularization","created":"2022-10-25","cited_by_count":31},{"id":"2309.07418","title":"A Fast Optimization View: Reformulating Single Layer Attention in LLM Based on Tensor and SVM Trick, and Solving It in Matrix Multiplication Time","created":"2023-09-14","cited_by_count":30},{"id":"2405.16411","title":"Training Tensor Attention Efficiently: From Cubic to Almost Linear Time","created":"2024-05-26","cited_by_count":30},{"id":"2006.08228","title":"Finding trainable sparse networks through Neural Tangent Transfer","created":"2020-06-15","cited_by_count":28},{"id":"2404.16349","title":"More Asymmetry Yields Faster Matrix Multiplication","created":"2024-04-25","cited_by_count":27},{"id":"2405.19325","title":"Nearest Neighbor Speculative Decoding for LLM Generation and Attribution","created":"2024-05-29","cited_by_count":25},{"id":"2210.12468","title":"Discrepancy Minimization in Input-Sparsity Time","created":"2022-10-22","cited_by_count":22},{"id":"2002.02304","title":"Solving Tall Dense Linear Programs in Nearly Linear Time","created":"2020-02-06","cited_by_count":21},{"id":"2402.06082","title":"SubGen: Token Generation in Sublinear Time and Memory","created":"2024-02-08","cited_by_count":21},{"id":"2406.05317","title":"LoCoCo: Dropping In Convolutions for Long Context Compression","created":"2024-06-08","cited_by_count":19},{"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":"1708.05622","title":"Improved Rectangular Matrix Multiplication using Powers of the Coppersmith-Winograd Tensor","created":"2017-08-18","cited_by_count":13},{"id":"2307.07735","title":"Faster Algorithms for Structured Linear and Kernel Support Vector Machines","created":"2023-07-15","cited_by_count":13},{"id":"2402.07443","title":"The I/O Complexity of Attention, or How Optimal is Flash Attention?","created":"2024-02-12","cited_by_count":6},{"id":"2408.07978","title":"Coupling without Communication and Drafter-Invariant Speculative Decoding","created":"2024-08-15","cited_by_count":6},{"id":"2307.06535","title":"Faster Rectangular Matrix Multiplication by Combination Loss Analysis","created":"2023-07-13","cited_by_count":5},{"id":"2301.00335","title":"Pruning Before Training May Improve Generalization, Provably","created":"2023-01-01","cited_by_count":3}],"next_cursor":null}