{"total":76,"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":"2309.12307","title":"LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models","created":"2023-09-21","cited_by_count":244,"area":null},{"id":"2311.06243","title":"Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization","created":"2023-11-10","cited_by_count":114,"area":null},{"id":"2204.00595","title":"Monarch: Expressive Structured Matrices for Efficient and Accurate Training","created":"2022-04-01","cited_by_count":106,"area":null},{"id":"2302.13214","title":"Fast Attention Requires Bounded Entries","created":"2023-02-26","cited_by_count":102,"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":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"area":null},{"id":"2302.06646","title":"Simple Hardware-Efficient Long Convolutions for Sequence Modeling","created":"2023-02-13","cited_by_count":62,"area":null},{"id":"2302.02451","title":"KDEformer: Accelerating Transformers via Kernel Density Estimation","created":"2023-02-05","cited_by_count":58,"area":null},{"id":"2306.08645","title":"Training-free Diffusion Model Adaptation for Variable-Sized Text-to-Image Synthesis","created":"2023-06-14","cited_by_count":56,"area":"diffusion"},{"id":"2207.04606","title":"SparseTIR: Composable Abstractions for Sparse Compilation in Deep Learning","created":"2022-07-11","cited_by_count":47,"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":"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":"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":"2311.05908","title":"FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores","created":"2023-11-10","cited_by_count":33,"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":"2206.01299","title":"Fine-tuning Language Models over Slow Networks using Activation Compression with Guarantees","created":"2022-06-02","cited_by_count":30,"area":null},{"id":"2211.14227","title":"Bypass Exponential Time Preprocessing: Fast Neural Network Training via Weight-Data Correlation Preprocessing","created":"2022-11-25","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":"2303.10464","title":"SPDF: Sparse Pre-training and Dense Fine-tuning for Large Language Models","created":"2023-03-18","cited_by_count":28,"area":null},{"id":"2502.10940","title":"CoLA: Compute-Efficient Pre-Training of LLMs via Low-Rank Activation","created":"2025-02-16","cited_by_count":28,"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":"2404.04316","title":"Parameter Efficient Quasi-Orthogonal Fine-Tuning via Givens Rotation","created":"2024-04-05","cited_by_count":21,"area":null},{"id":"2410.19034","title":"Mixture of Parrots: Experts improve memorization more than reasoning","created":"2024-10-24","cited_by_count":21,"area":"moe"},{"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":"2209.04766","title":"Towards Sparsification of Graph Neural Networks","created":"2022-09-11","cited_by_count":18,"area":null},{"id":"2512.02541","title":"AVGGT: Rethinking Global Attention for Accelerating VGGT","created":"2025-12-02","cited_by_count":16,"area":null},{"id":"2310.11685","title":"Why Softmax Attention Outperforms Linear Attention","created":"2023-10-18","cited_by_count":15,"area":null},{"id":"2405.14377","title":"CoMERA: Computing- and Memory-Efficient Training via Rank-Adaptive Tensor Optimization","created":"2024-05-23","cited_by_count":15,"area":null},{"id":"2405.17484","title":"Bridging The Gap between Low-rank and Orthogonal Adaptation via Householder Reflection Adaptation","created":"2024-05-24","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":"2210.10737","title":"RSC: Accelerating Graph Neural Networks Training via Randomized Sparse Computations","created":"2022-10-19","cited_by_count":12,"area":null},{"id":"2305.11203","title":"PDP: Parameter-free Differentiable Pruning is All You Need","created":"2023-05-18","cited_by_count":12,"area":null},{"id":"2404.08634","title":"When Attention Collapses: How Degenerate Layers in LLMs Enable Smaller, Stronger Models","created":"2024-04-12","cited_by_count":12,"area":null},{"id":"2506.05333","title":"Kinetics: Rethinking Test-Time Scaling Laws","created":"2025-06-05","cited_by_count":12,"area":"lr"},{"id":"2311.15157","title":"Advancing Vision Transformers with Group-Mix Attention","created":"2023-11-26","cited_by_count":11,"area":null},{"id":"2406.10019","title":"Group and Shuffle: Efficient Structured Orthogonal Parametrization","created":"2024-06-14","cited_by_count":11,"area":null},{"id":"2508.02668","title":"LOST: Low-rank and Sparse Pre-training for Large Language Models","created":"2025-08-04","cited_by_count":10,"area":null},{"id":"2305.15265","title":"Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model","created":"2023-05-24","cited_by_count":9,"area":null},{"id":"2403.07953","title":"Enabling Unstructured Sparse Acceleration on Structured Sparse Accelerators","created":"2024-03-12","cited_by_count":8,"area":null},{"id":"2304.05511","title":"Training Large Language Models Efficiently with Sparsity and Dataflow","created":"2023-04-11","cited_by_count":7,"area":null},{"id":"2305.12544","title":"Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models","created":"2023-05-21","cited_by_count":7,"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":"2405.17025","title":"SWAT: Scalable and Efficient Window Attention-based Transformers Acceleration on FPGAs","created":"2024-05-27","cited_by_count":6,"area":null},{"id":"2301.03573","title":"Balance is Essence: Accelerating Sparse Training via Adaptive Gradient Correction","created":"2023-01-09","cited_by_count":5,"area":null},{"id":"2310.18882","title":"Differentiable Learning of Generalized Structured Matrices for Efficient Deep Neural Networks","created":"2023-10-29","cited_by_count":5,"area":null},{"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":"2211.16368","title":"DBA: Efficient Transformer with Dynamic Bilinear Low-Rank Attention","created":"2022-11-24","cited_by_count":4,"area":null},{"id":"2312.11135","title":"Linear Attention via Orthogonal Memory","created":"2023-12-18","cited_by_count":4,"area":null},{"id":"2506.11449","title":"Dynamic Sparse Training of Diagonally Sparse Networks","created":"2025-06-13","cited_by_count":4,"area":null},{"id":"2205.14014","title":"What Dense Graph Do You Need for Self-Attention?","created":"2022-05-27","cited_by_count":3,"area":null},{"id":"2303.16999","title":"PopSparse: Accelerated block sparse matrix multiplication on IPU","created":"2023-03-29","cited_by_count":3,"area":null},{"id":"2410.21262","title":"BLAST: Block-Level Adaptive Structured Matrices for Efficient Deep Neural Network Inference","created":"2024-10-28","cited_by_count":3,"area":null},{"id":"2512.06353","title":"TreeQ: Pushing the Quantization Boundary of Diffusion Transformer via Tree-Structured Mixed-Precision Search","created":"2025-12-06","cited_by_count":3,"area":"diffusion"},{"id":"2601.22275","title":"VMonarch: Efficient Video Diffusion Transformers with Structured Attention","created":"2026-01-29","cited_by_count":3,"area":"diffusion"},{"id":"2310.19214","title":"Factor Fitting, Rank Allocation, and Partitioning in Multilevel Low Rank Matrices","created":"2023-10-30","cited_by_count":2,"area":null},{"id":"2312.00412","title":"SCHEME: Scalable Channel Mixer for Vision Transformers","created":"2023-12-01","cited_by_count":2,"area":null},{"id":"2409.17216","title":"Data-Centric AI Governance: Addressing the Limitations of Model-Focused Policies","created":"2024-09-25","cited_by_count":2,"area":null},{"id":"2503.21928","title":"An Efficient Training Algorithm for Models with Block-wise Sparsity","created":"2025-03-27","cited_by_count":2,"area":null},{"id":"2210.14012","title":"Gradient-based Weight Density Balancing for Robust Dynamic Sparse Training","created":"2022-10-25","cited_by_count":1,"area":null},{"id":"2510.03678","title":"Towards Sampling Data Structures for Tensor Products in Turnstile Streams","created":"2025-10-04","cited_by_count":1,"area":null},{"id":"2211.16578","title":"ButterflyNet2D: Bridging Classical Methods and Neural Network Methods in Image Processing","created":"2022-11-29","cited_by_count":0,"area":null},{"id":"2309.08946","title":"Reducing Memory Requirements for the IPU using Butterfly Factorizations","created":"2023-09-16","cited_by_count":0,"area":null},{"id":"2311.18735","title":"Dimension Mixer: Group Mixing of Input Dimensions for Efficient Function Approximation","created":"2023-11-30","cited_by_count":0,"area":null},{"id":"2405.15013","title":"Fast Inference with Kronecker-Sparse Matrices","created":"2024-05-23","cited_by_count":0,"area":null},{"id":"2410.04342","title":"Accelerating Inference of Networks in the Frequency Domain","created":"2024-10-06","cited_by_count":0,"area":null},{"id":"2506.00424","title":"COGNATE: Acceleration of Sparse Tensor Programs on Emerging Hardware using Transfer Learning","created":"2025-05-31","cited_by_count":0,"area":null},{"id":"2510.11192","title":"Efficient In-Memory Acceleration of Sparse Block Diagonal LLMs","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2510.14812","title":"SHUFFLESPARSE: Learned Shuffles for Structured Sparse Networks","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2510.17734","title":"Efficient Tensor Completion Algorithms for Highly Oscillatory Operators","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2610.02882","title":"DyRA: Dynamic Residual Approximation for Efficient Matrix Multiplication in DNNs","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}