{"total":130,"rows":[{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673,"area":null},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598,"area":null},{"id":"2407.08608","title":"FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision","created":"2024-07-11","cited_by_count":519,"area":null},{"id":"2305.17118","title":"Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time","created":"2023-05-26","cited_by_count":439,"area":"inference"},{"id":"2501.00663","title":"Titans: Learning to Memorize at Test Time","created":"2024-12-31","cited_by_count":328,"area":"lr"},{"id":"2306.07629","title":"SqueezeLLM: Dense-and-Sparse Quantization","created":"2023-06-13","cited_by_count":294,"area":null},{"id":"2310.17157","title":"Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time","created":"2023-10-26","cited_by_count":252,"area":null},{"id":"2304.12210","title":"A Cookbook of Self-Supervised Learning","created":"2023-04-24","cited_by_count":250,"area":null},{"id":"2405.16444","title":"CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion","created":"2024-05-26","cited_by_count":223,"area":"inference"},{"id":"2312.04985","title":"SparQ Attention: Bandwidth-Efficient LLM Inference","created":"2023-12-08","cited_by_count":119,"area":"inference"},{"id":"2410.16179","title":"MagicPIG: LSH Sampling for Efficient LLM Generation","created":"2024-10-21","cited_by_count":111,"area":null},{"id":"2302.13214","title":"Fast Attention Requires Bounded Entries","created":"2023-02-26","cited_by_count":102,"area":null},{"id":"2304.06819","title":"Modeling Dense Multimodal Interactions Between Biological Pathways and Histology for Survival Prediction","created":"2023-04-13","cited_by_count":92,"area":null},{"id":"2310.05869","title":"HyperAttention: Long-context Attention in Near-Linear Time","created":"2023-10-09","cited_by_count":85,"area":null},{"id":"2112.00029","title":"Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models","created":"2021-11-30","cited_by_count":76,"area":null},{"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,"area":"inference"},{"id":"2311.12351","title":"Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Survey","created":"2023-11-21","cited_by_count":72,"area":null},{"id":"2407.21018","title":"ThinK: Thinner Key Cache by Query-Driven Pruning","created":"2024-07-30","cited_by_count":68,"area":"lr"},{"id":"2402.03804","title":"ReLU$^2$ Wins: Discovering Efficient Activation Functions for Sparse LLMs","created":"2024-02-06","cited_by_count":67,"area":null},{"id":"2302.02451","title":"KDEformer: Accelerating Transformers via Kernel Density Estimation","created":"2023-02-05","cited_by_count":58,"area":null},{"id":"2406.16747","title":"Sparser is Faster and Less is More: Efficient Sparse Attention for Long-Range Transformers","created":"2024-06-24","cited_by_count":52,"area":null},{"id":"2306.07050","title":"Revisiting Token Pruning for Object Detection and Instance Segmentation","created":"2023-06-12","cited_by_count":50,"area":"inference"},{"id":"2206.06072","title":"Rank Diminishing in Deep Neural Networks","created":"2022-06-13","cited_by_count":47,"area":null},{"id":"2405.19592","title":"Why Larger Language Models Do In-context Learning Differently?","created":"2024-05-30","cited_by_count":45,"area":null},{"id":"2406.02214","title":"SLTrain: a sparse plus low-rank approach for parameter and memory efficient pretraining","created":"2024-06-04","cited_by_count":45,"area":null},{"id":"2408.07092","title":"Post-Training Sparse Attention with Double Sparsity","created":"2024-08-11","cited_by_count":45,"area":null},{"id":"2303.15725","title":"Solving Regularized Exp, Cosh and Sinh Regression Problems","created":"2023-03-28","cited_by_count":44,"area":null},{"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,"area":null},{"id":"2304.13276","title":"The Closeness of In-Context Learning and Weight Shifting for Softmax Regression","created":"2023-04-26","cited_by_count":41,"area":null},{"id":"2403.19888","title":"MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selection","created":"2024-03-29","cited_by_count":40,"area":"ssm"},{"id":"2406.15486","title":"SampleAttention: Near-Lossless Acceleration of Long Context LLM Inference with Adaptive Structured Sparse Attention","created":"2024-06-17","cited_by_count":39,"area":null},{"id":"2210.06640","title":"Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2404.03827","title":"Uniform Memory Retrieval with Larger Capacity for Modern Hopfield Models","created":"2024-04-04","cited_by_count":38,"area":null},{"id":"2304.04397","title":"Randomized and Deterministic Attention Sparsification Algorithms for Over-parameterized Feature Dimension","created":"2023-04-10","cited_by_count":37,"area":null},{"id":"2408.12186","title":"Transformers are Minimax Optimal Nonparametric In-Context Learners","created":"2024-08-22","cited_by_count":37,"area":null},{"id":"2311.05908","title":"FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores","created":"2023-11-10","cited_by_count":33,"area":null},{"id":"2204.04667","title":"Linear Complexity Randomized Self-attention Mechanism","created":"2022-04-10","cited_by_count":31,"area":null},{"id":"2209.09570","title":"Adaptable Butterfly Accelerator for Attention-based NNs via Hardware and Algorithm Co-design","created":"2022-09-20","cited_by_count":31,"area":null},{"id":"2303.05955","title":"Neuron Structure Modeling for Generalizable Remote Physiological Measurement","created":"2023-03-10","cited_by_count":31,"area":null},{"id":"2211.05109","title":"ViTALiTy: Unifying Low-rank and Sparse Approximation for Vision Transformer Acceleration with a Linear Taylor Attention","created":"2022-11-09","cited_by_count":29,"area":null},{"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,"area":null},{"id":"2211.10526","title":"Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference","created":"2022-11-18","cited_by_count":28,"area":null},{"id":"2410.10254","title":"LoLCATs: On Low-Rank Linearizing of Large Language Models","created":"2024-10-14","cited_by_count":27,"area":null},{"id":"2304.03589","title":"On Efficient Training of Large-Scale Deep Learning Models: A Literature Review","created":"2023-04-07","cited_by_count":26,"area":null},{"id":"2308.12247","title":"How to Protect Copyright Data in Optimization of Large Language Models?","created":"2023-08-23","cited_by_count":26,"area":null},{"id":"2305.02538","title":"Cuttlefish: Low-Rank Model Training without All the Tuning","created":"2023-05-04","cited_by_count":25,"area":null},{"id":"2302.04542","title":"Efficient Attention via Control Variates","created":"2023-02-09","cited_by_count":23,"area":null},{"id":"2509.07120","title":"Block-Sparse Global Attention for Efficient Multi-View Geometry Transformers","created":"2025-09-08","cited_by_count":23,"area":null},{"id":"2308.14304","title":"Solving Attention Kernel Regression Problem via Pre-conditioner","created":"2023-08-28","cited_by_count":20,"area":null},{"id":"2405.16325","title":"SLoPe: Double-Pruned Sparse Plus Lazy Low-Rank Adapter Pretraining of LLMs","created":"2024-05-25","cited_by_count":20,"area":null},{"id":"2504.05646","title":"Lattice: Learning to Efficiently Compress the Memory","created":"2025-04-08","cited_by_count":19,"area":null},{"id":"2504.16922","title":"Generalized Neighborhood Attention: Multi-dimensional Sparse Attention at the Speed of Light","created":"2025-04-23","cited_by_count":18,"area":null},{"id":"2411.12892","title":"Selective Attention: Enhancing Transformer through Principled Context Control","created":"2024-11-19","cited_by_count":16,"area":null},{"id":"2505.17495","title":"ProxySPEX: Inference-Efficient Interpretability via Sparse Feature Interactions in LLMs","created":"2025-05-23","cited_by_count":16,"area":null},{"id":"2510.10129","title":"CacheClip: Accelerating RAG with Effective KV Cache Reuse","created":"2025-10-11","cited_by_count":16,"area":"rag"},{"id":"2306.06446","title":"ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer","created":"2023-06-10","cited_by_count":15,"area":"moe"},{"id":"2310.11685","title":"Why Softmax Attention Outperforms Linear Attention","created":"2023-10-18","cited_by_count":15,"area":null},{"id":"2302.11051","title":"Fusion of Global and Local Knowledge for Personalized Federated Learning","created":"2023-02-21","cited_by_count":14,"area":null},{"id":"2305.17235","title":"COMCAT: Towards Efficient Compression and Customization of Attention-Based Vision Models","created":"2023-05-26","cited_by_count":14,"area":null},{"id":"2404.10407","title":"Comprehensive Survey of Model Compression and Speed up for Vision Transformers","created":"2024-04-16","cited_by_count":14,"area":null},{"id":"2501.10885","title":"CEReBrO: Compact Encoder for Representations of Brain Oscillations Using Efficient Alternating Attention","created":"2025-01-18","cited_by_count":14,"area":null},{"id":"2310.12442","title":"Efficient Long-Range Transformers: You Need to Attend More, but Not Necessarily at Every Layer","created":"2023-10-19","cited_by_count":13,"area":null},{"id":"2405.00314","title":"Model Quantization and Hardware Acceleration for Vision Transformers: A Comprehensive Survey","created":"2024-05-01","cited_by_count":13,"area":null},{"id":"2504.14051","title":"CAOTE: KV Cache Selection for LLMs via Attention Output Error-Based Token Eviction","created":"2025-04-18","cited_by_count":13,"area":"inference"},{"id":"2203.01178","title":"DCT-Former: Efficient Self-Attention with Discrete Cosine Transform","created":"2022-03-02","cited_by_count":12,"area":null},{"id":"2402.12535","title":"Locality-Sensitive Hashing-Based Efficient Point Transformer with Applications in High-Energy Physics","created":"2024-02-19","cited_by_count":12,"area":null},{"id":"2403.01273","title":"NoMAD-Attention: Efficient LLM Inference on CPUs Through Multiply-add-free Attention","created":"2024-03-02","cited_by_count":12,"area":"inference"},{"id":"2502.13870","title":"SPEX: Scaling Feature Interaction Explanations for LLMs","created":"2025-02-19","cited_by_count":12,"area":null},{"id":"2505.23666","title":"LoLA: Low-Rank Linear Attention With Sparse Caching","created":"2025-05-29","cited_by_count":12,"area":null},{"id":"2207.10284","title":"Multi Resolution Analysis (MRA) for Approximate Self-Attention","created":"2022-07-21","cited_by_count":11,"area":null},{"id":"2311.15157","title":"Advancing Vision Transformers with Group-Mix Attention","created":"2023-11-26","cited_by_count":11,"area":null},{"id":"2210.07661","title":"CAB: Comprehensive Attention Benchmarking on Long Sequence Modeling","created":"2022-10-14","cited_by_count":10,"area":null},{"id":"2310.01777","title":"SEA: Sparse Linear Attention with Estimated Attention Mask","created":"2023-10-03","cited_by_count":10,"area":null},{"id":"2208.09015","title":"Treeformer: Dense Gradient Trees for Efficient Attention Computation","created":"2022-08-18","cited_by_count":9,"area":null},{"id":"2308.09372","title":"Which Transformer to Favor: A Comparative Analysis of Efficiency in Vision Transformers","created":"2023-08-18","cited_by_count":9,"area":null},{"id":"2407.05941","title":"Pruning One More Token is Enough: Leveraging Latency-Workload Non-Linearities for Vision Transformers on the Edge","created":"2024-07-01","cited_by_count":9,"area":"inference"},{"id":"2506.08001","title":"Reparameterized LLM Training via Orthogonal Equivalence Transformation","created":"2025-06-09","cited_by_count":9,"area":null},{"id":"2303.11525","title":"Sparse-IFT: Sparse Iso-FLOP Transformations for Maximizing Training Efficiency","created":"2023-03-21","cited_by_count":8,"area":null},{"id":"2506.03275","title":"Chipmunk: Training-Free Acceleration of Diffusion Transformers with Dynamic Column-Sparse Deltas","created":"2025-06-03","cited_by_count":8,"area":"diffusion"},{"id":"2208.03367","title":"Sublinear Time Algorithm for Online Weighted Bipartite Matching","created":"2022-08-05","cited_by_count":7,"area":null},{"id":"2502.12063","title":"Low-Rank Thinning","created":"2025-02-17","cited_by_count":7,"area":null},{"id":"2402.07443","title":"The I/O Complexity of Attention, or How Optimal is Flash Attention?","created":"2024-02-12","cited_by_count":6,"area":null},{"id":"2402.18508","title":"Orchid: Flexible and Data-Dependent Convolution for Sequence Modeling","created":"2024-02-28","cited_by_count":6,"area":null},{"id":"2404.09707","title":"Adaptive Patching for High-resolution Image Segmentation with Transformers","created":"2024-04-15","cited_by_count":6,"area":null},{"id":"2512.21691","title":"Analyzing the Mechanism of Attention Collapse in VGGT from a Dynamics Perspective","created":"2025-12-25","cited_by_count":6,"area":null},{"id":"2602.10056","title":"WildCat: Near-Linear Attention in Theory and Practice","created":"2026-02-10","cited_by_count":6,"area":null},{"id":"2602.12271","title":"MonarchRT: Efficient Attention for Real-Time Video Generation","created":"2026-02-12","cited_by_count":6,"area":"diffusion"},{"id":"2502.09647","title":"Unveiling Simplicities of Attention: Adaptive Long-Context Head Identification","created":"2025-02-11","cited_by_count":5,"area":null},{"id":"2502.15955","title":"Compression Barriers for Autoregressive Transformers","created":"2025-02-21","cited_by_count":5,"area":"inference"},{"id":"2505.18698","title":"MonarchAttention: Zero-Shot Conversion to Fast, Hardware-Aware Structured Attention","created":"2025-05-24","cited_by_count":5,"area":null},{"id":"2508.00367","title":"Representation Shift: Unifying Token Compression with FlashAttention","created":"2025-08-01","cited_by_count":5,"area":"inference"},{"id":"2509.05276","title":"SpikingBrain: Spiking Brain-inspired Large Models","created":"2025-09-05","cited_by_count":5,"area":null},{"id":"2512.23852","title":"Trellis: Learning to Compress Key-Value Memory in Attention Models","created":"2025-12-29","cited_by_count":5,"area":null},{"id":"2602.05929","title":"KV-CoRE: Benchmarking Data-Dependent Low-Rank Compressibility of KV-Caches in LLMs","created":"2026-02-05","cited_by_count":5,"area":"inference"},{"id":"2603.05500","title":"POET-X: Memory-efficient LLM Training by Scaling Orthogonal Transformation","created":"2026-03-05","cited_by_count":5,"area":null},{"id":"2211.16368","title":"DBA: Efficient Transformer with Dynamic Bilinear Low-Rank Attention","created":"2022-11-24","cited_by_count":4,"area":null},{"id":"2507.23539","title":"Improved Algorithms for Kernel Matrix-Vector Multiplication Under Sparsity Assumptions","created":"2025-07-31","cited_by_count":4,"area":null},{"id":"2510.11924","title":"Inpainting the Neural Picture: Inferring Unrecorded Brain Area Dynamics from Multi-Animal Datasets","created":"2025-10-13","cited_by_count":4,"area":null},{"id":"2202.00834","title":"Nonlinear Initialization Methods for Low-Rank Neural Networks","created":"2022-02-02","cited_by_count":3,"area":null},{"id":"2306.15799","title":"FLuRKA: Fast and accurate unified Low-Rank & Kernel Attention","created":"2023-06-27","cited_by_count":3,"area":null}],"next_cursor":"100"}