{"total":69,"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":"2302.10866","title":"Hyena Hierarchy: Towards Larger Convolutional Language Models","created":"2023-02-21","cited_by_count":393,"area":null},{"id":"2110.15343","title":"Scatterbrain: Unifying Sparse and Low-rank Attention Approximation","created":"2021-10-28","cited_by_count":130,"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":"2303.00980","title":"Learning to Grow Pretrained Models for Efficient Transformer Training","created":"2023-03-02","cited_by_count":83,"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":"2302.06646","title":"Simple Hardware-Efficient Long Convolutions for Sequence Modeling","created":"2023-02-13","cited_by_count":62,"area":null},{"id":"2506.04761","title":"Log-Linear Attention","created":"2025-06-05","cited_by_count":40,"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":"2312.00678","title":"The Efficiency Spectrum of Large Language Models: An Algorithmic Survey","created":"2023-12-01","cited_by_count":26,"area":null},{"id":"2103.15798","title":"Rethinking Neural Operations for Diverse Tasks","created":"2021-03-29","cited_by_count":18,"area":null},{"id":"2602.24281","title":"Memory Caching: RNNs with Growing Memory","created":"2026-02-27","cited_by_count":15,"area":null},{"id":"2101.03037","title":"Learning quantum data with the quantum Earth Mover's distance","created":"2021-01-08","cited_by_count":13,"area":null},{"id":"2209.13774","title":"ButterflyFlow: Building Invertible Layers with Butterfly Matrices","created":"2022-09-28","cited_by_count":12,"area":null},{"id":"2509.09679","title":"ButterflyQuant: Ultra-low-bit LLM Quantization through Learnable Orthogonal Butterfly Transforms","created":"2025-09-11","cited_by_count":10,"area":null},{"id":"2301.13856","title":"Simplex Random Features","created":"2023-01-31","cited_by_count":9,"area":null},{"id":"2501.19183","title":"Position: Curvature Matrices Should Be Democratized via Linear Operators","created":"2025-01-31","cited_by_count":9,"area":null},{"id":"2506.08001","title":"Reparameterized LLM Training via Orthogonal Equivalence Transformation","created":"2025-06-09","cited_by_count":9,"area":null},{"id":"2506.12383","title":"Scaling Probabilistic Circuits via Monarch Matrices","created":"2025-06-14","cited_by_count":9,"area":null},{"id":"2203.13556","title":"Deformable Butterfly: A Highly Structured and Sparse Linear Transform","created":"2022-03-25","cited_by_count":8,"area":null},{"id":"2309.03060","title":"CoLA: Exploiting Compositional Structure for Automatic and Efficient Numerical Linear Algebra","created":"2023-09-06","cited_by_count":7,"area":null},{"id":"2409.11772","title":"Symmetry-Based Structured Matrices for Efficient Approximately Equivariant Networks","created":"2024-09-18","cited_by_count":7,"area":null},{"id":"2305.15267","title":"Training Energy-Based Normalizing Flow with Score-Matching Objectives","created":"2023-05-24","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":"2409.18850","title":"Two Sparse Matrices are Better than One: Sparsifying Neural Networks with Double Sparse Factorization","created":"2024-09-27","cited_by_count":6,"area":null},{"id":"2503.18368","title":"MoST: Efficient Monarch Sparse Tuning for 3D Representation Learning","created":"2025-03-24","cited_by_count":6,"area":null},{"id":"2302.05045","title":"Exploiting Sparsity in Pruned Neural Networks to Optimize Large Model Training","created":"2023-02-10","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":"2603.05500","title":"POET-X: Memory-efficient LLM Training by Scaling Orthogonal Transformation","created":"2026-03-05","cited_by_count":5,"area":null},{"id":"2605.29843","title":"HARP: Hadamard-Preconditioned Adaptive Rotation Processor for Extreme LLM Quantization","created":"2026-05-28","cited_by_count":5,"area":null},{"id":"2410.03040","title":"Geometry is All You Need: A Unified Taxonomy of Matrix and Tensor Factorization for Compression of Generative Language Models","created":"2024-10-03","cited_by_count":4,"area":null},{"id":"2502.18394","title":"SPECTRE: An FFT-Based Efficient Drop-In Replacement to Self-Attention for Long Contexts","created":"2025-02-25","cited_by_count":4,"area":null},{"id":"2405.13155","title":"ReALLM: A general framework for LLM compression and fine-tuning","created":"2024-05-21","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":"2110.01230","title":"Efficient Identification of Butterfly Sparse Matrix Factorizations","created":"2021-10-04","cited_by_count":2,"area":null},{"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":"2406.16450","title":"Building on Efficient Foundations: Effectively Training LLMs with Structured Feedforward Layers","created":"2024-06-24","cited_by_count":2,"area":null},{"id":"2408.17383","title":"MoRe Fine-Tuning with 10x Fewer Parameters","created":"2024-08-30","cited_by_count":2,"area":null},{"id":"2409.15097","title":"Efficiently Dispatching Flash Attention For Partially Filled Attention Masks","created":"2024-09-23","cited_by_count":2,"area":null},{"id":"2508.03222","title":"Revisiting Deep Information Propagation: Fractal Frontier and Finite-size Effects","created":"2025-08-05","cited_by_count":2,"area":null},{"id":"2110.01235","title":"Identifiability in Two-Layer Sparse Matrix Factorization","created":"2021-10-04","cited_by_count":1,"area":null},{"id":"2206.12490","title":"Arithmetic Circuits, Structured Matrices and (not so) Deep Learning","created":"2022-06-24","cited_by_count":1,"area":null},{"id":"2212.06068","title":"Solving the Wide-band Inverse Scattering Problem via Equivariant Neural Networks","created":"2022-12-12","cited_by_count":1,"area":null},{"id":"2304.07234","title":"Can sparsity improve the privacy of neural networks?","created":"2023-04-11","cited_by_count":1,"area":null},{"id":"2510.25323","title":"CDFlow: Building Invertible Layers with Circulant and Diagonal Matrices","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2512.17344","title":"Governance-Aware Hybrid Fine-Tuning for Multilingual Large Language Models","created":"2025-12-19","cited_by_count":1,"area":null},{"id":"2601.04159","title":"ToTMNet: FFT-Accelerated Toeplitz Temporal Mixing Network for Lightweight Remote Photoplethysmography","created":"2026-01-07","cited_by_count":1,"area":null},{"id":"2602.18248","title":"Neural-HSS: Hierarchical Semi-Separable Neural PDE Solver","created":"2026-02-20","cited_by_count":1,"area":null},{"id":"2210.04807","title":"Efficient NTK using Dimensionality Reduction","created":"2022-10-10","cited_by_count":0,"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":"2305.13536","title":"Subspace-Configurable Networks","created":"2023-05-22","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":"2311.08125","title":"Lite it fly: An All-Deformable-Butterfly Network","created":"2023-11-14","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":"2507.18076","title":"Hybrid and Unitary PEFT for Resource-Efficient Large Language Models","created":"2025-07-24","cited_by_count":0,"area":null},{"id":"2509.07963","title":"Customizing the Inductive Biases of Softmax Attention using Structured Matrices","created":"2025-09-09","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":"2510.17734","title":"Efficient Tensor Completion Algorithms for Highly Oscillatory Operators","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2512.23905","title":"Rethinking Dense Linear Transformations: Stagewise Pairwise Mixing (SPM) for Near-Linear Training in Neural Networks","created":"2025-12-30","cited_by_count":0,"area":null},{"id":"2605.25344","title":"A Hamiltonian-Inspired Local-Operator Ansatz for Slimming Large Language Models","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2609.17298","title":"Quantum-Inspired Trainable and Parameter-Efficient Tensor Networks for Image Inpainting","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.18145","title":"Reaching Every Position Without Searching: Rotating Sparse Wiring on the Hypercube as a Substitute for Attention","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.27982","title":"Riemannian Structure and Optimization for a Class of Low-Parametric Orthogonal Matrices","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2610.13568","title":"Rationally Linearized MLPs","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.20303","title":"SpectrumQuant: Spectrum Alignment for LLM Quantization","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}