{"total":32,"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":"2301.08727","title":"Neural Architecture Search: Insights from 1000 Papers","created":"2023-01-20","cited_by_count":139,"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":"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":"2103.15798","title":"Rethinking Neural Operations for Diverse Tasks","created":"2021-03-29","cited_by_count":18,"area":null},{"id":"2204.07554","title":"Efficient Architecture Search for Diverse Tasks","created":"2022-04-15","cited_by_count":18,"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":"2205.14082","title":"AANG: Automating Auxiliary Learning","created":"2022-05-27","cited_by_count":12,"area":null},{"id":"2209.13774","title":"ButterflyFlow: Building Invertible Layers with Butterfly Matrices","created":"2022-09-28","cited_by_count":12,"area":null},{"id":"2211.04422","title":"Black Box Lie Group Preconditioners for SGD","created":"2022-11-08","cited_by_count":9,"area":null},{"id":"2201.02715","title":"Low-Rank Constraints for Fast Inference in Structured Models","created":"2022-01-08","cited_by_count":8,"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":"2409.11772","title":"Symmetry-Based Structured Matrices for Efficient Approximately Equivariant Networks","created":"2024-09-18","cited_by_count":7,"area":null},{"id":"2204.07673","title":"Self-Similarity Priors: Neural Collages as Differentiable Fractal Representations","created":"2022-04-15","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":"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":"2109.11928","title":"Is the Number of Trainable Parameters All That Actually Matters?","created":"2021-09-24","cited_by_count":3,"area":null},{"id":"2202.00834","title":"Nonlinear Initialization Methods for Low-Rank Neural Networks","created":"2022-02-02","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":"2408.17383","title":"MoRe Fine-Tuning with 10x Fewer Parameters","created":"2024-08-30","cited_by_count":2,"area":null},{"id":"2503.12211","title":"Changing Base Without Losing Pace: A GPU-Efficient Alternative to MatMul in DNNs","created":"2025-03-15","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":"2311.08125","title":"Lite it fly: An All-Deformable-Butterfly Network","created":"2023-11-14","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":"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}],"next_cursor":null}