{"total":19,"rows":[{"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":"2409.11772","title":"Symmetry-Based Structured Matrices for Efficient Approximately Equivariant Networks","created":"2024-09-18","cited_by_count":7,"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":"2405.15310","title":"Spectraformer: A Unified Random Feature Framework for Transformer","created":"2024-05-24","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":"2110.09374","title":"Ortho-Shot: Low Displacement Rank Regularization with Data Augmentation for Few-Shot Learning","created":"2021-10-18","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":"2505.00582","title":"Block Circulant Adapter for Large Language Models","created":"2025-05-01","cited_by_count":3,"area":null},{"id":"2112.02656","title":"Intrinisic Gradient Compression for Federated Learning","created":"2021-12-05","cited_by_count":2,"area":null},{"id":"2303.06797","title":"Multichannel Orthogonal Transform-Based Perceptron Layers for Efficient ResNets","created":"2023-03-13","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":"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":"2110.15440","title":"HD-cos Networks: Efficient Neural Architectures for Secure Multi-Party Computation","created":"2021-10-28","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":"2508.09153","title":"JustDense: Just using Dense instead of Sequence Mixer for Time Series analysis","created":"2025-08-04","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":"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}],"next_cursor":null}