{"total":40,"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":"2105.03824","title":"FNet: Mixing Tokens with Fourier Transforms","created":"2021-05-09","cited_by_count":347,"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":"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":"2110.13981","title":"CHIP: CHannel Independence-based Pruning for Compact Neural Networks","created":"2021-10-26","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":"2503.06027","title":"Empowering Edge Intelligence: A Comprehensive Survey on On-Device AI Models","created":"2025-03-08","cited_by_count":46,"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":"2107.14444","title":"Manipulating Identical Filter Redundancy for Efficient Pruning on Deep and Complicated CNN","created":"2021-07-30","cited_by_count":9,"area":null},{"id":"2106.02241","title":"ERNIE-Tiny : A Progressive Distillation Framework for Pretrained Transformer Compression","created":"2021-06-04","cited_by_count":8,"area":null},{"id":"2101.09650","title":"GST: Group-Sparse Training for Accelerating Deep Reinforcement Learning","created":"2021-01-24","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":"2503.18368","title":"MoST: Efficient Monarch Sparse Tuning for 3D Representation Learning","created":"2025-03-24","cited_by_count":6,"area":null},{"id":"2102.07071","title":"Doping: A technique for efficient compression of LSTM models using sparse structured additive matrices","created":"2021-02-14","cited_by_count":5,"area":null},{"id":"2112.11438","title":"Mixed Precision Low-bit Quantization of Neural Network Language Models for Speech Recognition","created":"2021-11-29","cited_by_count":5,"area":null},{"id":"2406.17740","title":"Structured Unrestricted-Rank Matrices for Parameter Efficient Fine-tuning","created":"2024-06-25","cited_by_count":5,"area":null},{"id":"2311.10807","title":"SENetV2: Aggregated dense layer for channelwise and global representations","created":"2023-11-17","cited_by_count":3,"area":null},{"id":"2406.15881","title":"Fast Tree-Field Integrators: From Low Displacement Rank to Topological Transformers","created":"2024-06-22","cited_by_count":3,"area":null},{"id":"2409.03945","title":"TropNNC: Structured Neural Network Compression Using Tropical Geometry","created":"2024-09-05","cited_by_count":3,"area":null},{"id":"2111.14836","title":"Low-bit Quantization of Recurrent Neural Network Language Models Using Alternating Direction Methods of Multipliers","created":"2021-11-29","cited_by_count":2,"area":null},{"id":"2507.11688","title":"Composing Linear Layers from Irreducibles","created":"2025-07-15","cited_by_count":2,"area":null},{"id":"2601.22563","title":"EUGens: Efficient, Unified, and General Dense Layers","created":"2026-01-30","cited_by_count":2,"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":"2407.11763","title":"Enhancing Split Computing and Early Exit Applications through Predefined Sparsity","created":"2024-07-16","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":"2308.13343","title":"Squeeze aggregated excitation network","created":"2023-08-25","cited_by_count":0,"area":null},{"id":"2410.09771","title":"EUGens: Efficient, Unified, and General Dense Layers","created":"2024-10-13","cited_by_count":0,"area":null},{"id":"2503.17353","title":"NdLinear: Preserving Multi-Dimensional Structure for Parameter-Efficient Neural Networks","created":"2025-03-21","cited_by_count":0,"area":null},{"id":"2503.22074","title":"Penrose Tiled Low-Rank Compression and Section-Wise Q&A Fine-Tuning: A General Framework for Domain-Specific Large Language Model Adaptation","created":"2025-03-28","cited_by_count":0,"area":null},{"id":"2512.13480","title":"Element-wise Modulation of Random Matrices for Efficient Neural Layers","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2601.05379","title":"EdgeLDR: Quaternion Low-Displacement Rank Neural Networks for Edge-Efficient Deep Learning","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2603.24916","title":"Once-for-All Channel Mixers (HYPERTINYPW): Generative Compression for TinyML","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2604.17371","title":"Leveraging Kernel Symmetry for Joint Compression and Error Mitigation in Edge Model Transfer","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2605.00448","title":"Learning from Compressed CT: Feature Attention Style Transfer and Structured Factorized Projections for Resource-Efficient Medical Image Analysis","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2605.08171","title":"Communication Dynamics Neural Networks: FFT-Diagonalized Layers for Improved Hessian Conditioning at Reduced Parameter Count","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2605.16443","title":"Two-Valued Symmetric Circulant Matrices: Applications in Deep Learning","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2609.01550","title":"Linear Reusable Neural Bases Architecture for Network Compression","created":"2026-09-01","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}],"next_cursor":null}