{"total":16,"rows":[{"id":"2105.03824","title":"FNet: Mixing Tokens with Fourier Transforms","created":"2021-05-09","cited_by_count":347,"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":"2210.06640","title":"Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2103.15798","title":"Rethinking Neural Operations for Diverse Tasks","created":"2021-03-29","cited_by_count":18,"area":null},{"id":"2403.07221","title":"LookupFFN: Making Transformers Compute-lite for CPU inference","created":"2024-03-12","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":"2402.18508","title":"Orchid: Flexible and Data-Dependent Convolution for Sequence Modeling","created":"2024-02-28","cited_by_count":6,"area":null},{"id":"2109.11928","title":"Is the Number of Trainable Parameters All That Actually Matters?","created":"2021-09-24","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":"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":"2508.03222","title":"Revisiting Deep Information Propagation: Fractal Frontier and Finite-size Effects","created":"2025-08-05","cited_by_count":2,"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":"2407.13726","title":"Compressing Structured Tensor Algebra","created":"2024-07-18","cited_by_count":0,"area":null},{"id":"2502.00585","title":"Converting Transformers into DGNNs Form","created":"2025-02-01","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":"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}