{"total":106,"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":"2312.06635","title":"Gated Linear Attention Transformers with Hardware-Efficient Training","created":"2023-12-11","cited_by_count":514,"area":"ssm"},{"id":"2212.14052","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","created":"2022-12-28","cited_by_count":499,"area":null},{"id":"2302.10866","title":"Hyena Hierarchy: Towards Larger Convolutional Language Models","created":"2023-02-21","cited_by_count":393,"area":null},{"id":"2404.10136","title":"Language Model Cascades: Token-level uncertainty and beyond","created":"2024-04-15","cited_by_count":121,"area":null},{"id":"2311.06243","title":"Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization","created":"2023-11-10","cited_by_count":114,"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":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"area":null},{"id":"2310.00120","title":"Multi-Grid Tensorized Fourier Neural Operator for High-Resolution PDEs","created":"2023-09-29","cited_by_count":68,"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":"2407.09941","title":"Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers","created":"2024-07-13","cited_by_count":44,"area":"ssm"},{"id":"2403.19888","title":"MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selection","created":"2024-03-29","cited_by_count":40,"area":"ssm"},{"id":"2506.04761","title":"Log-Linear Attention","created":"2025-06-05","cited_by_count":40,"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":"2311.05908","title":"FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores","created":"2023-11-10","cited_by_count":33,"area":null},{"id":"2402.06262","title":"On the Efficacy of Eviction Policy for Key-Value Constrained Generative Language Model Inference","created":"2024-02-09","cited_by_count":32,"area":"inference"},{"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":"2303.10464","title":"SPDF: Sparse Pre-training and Dense Fine-tuning for Large Language Models","created":"2023-03-18","cited_by_count":28,"area":null},{"id":"2406.06248","title":"Compute Better Spent: Replacing Dense Layers with Structured Matrices","created":"2024-06-10","cited_by_count":28,"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":"2302.02596","title":"Ten Lessons We Have Learned in the New \"Sparseland\": A Short Handbook for Sparse Neural Network Researchers","created":"2023-02-06","cited_by_count":25,"area":null},{"id":"2305.02538","title":"Cuttlefish: Low-Rank Model Training without All the Tuning","created":"2023-05-04","cited_by_count":25,"area":null},{"id":"2407.18158","title":"Unlocking Tokens as Data Points for Generalization Bounds on Larger Language Models","created":"2024-07-25","cited_by_count":25,"area":null},{"id":"2212.07477","title":"Guiding continuous operator learning through Physics-based boundary constraints","created":"2022-12-14","cited_by_count":21,"area":null},{"id":"2410.19034","title":"Mixture of Parrots: Experts improve memorization more than reasoning","created":"2024-10-24","cited_by_count":21,"area":"moe"},{"id":"2505.17761","title":"Structured Linear CDEs: Maximally Expressive and Parallel-in-Time Sequence Models","created":"2025-05-23","cited_by_count":18,"area":null},{"id":"2307.00526","title":"TensorGPT: Efficient Compression of Large Language Models based on Tensor-Train Decomposition","created":"2023-07-02","cited_by_count":17,"area":null},{"id":"2303.13755","title":"Sparsifiner: Learning Sparse Instance-Dependent Attention for Efficient Vision Transformers","created":"2023-03-24","cited_by_count":16,"area":null},{"id":"2602.24281","title":"Memory Caching: RNNs with Growing Memory","created":"2026-02-27","cited_by_count":15,"area":null},{"id":"2410.02117","title":"Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices","created":"2024-10-03","cited_by_count":13,"area":"moe"},{"id":"2210.10737","title":"RSC: Accelerating Graph Neural Networks Training via Randomized Sparse Computations","created":"2022-10-19","cited_by_count":12,"area":null},{"id":"2406.10019","title":"Group and Shuffle: Efficient Structured Orthogonal Parametrization","created":"2024-06-14","cited_by_count":11,"area":null},{"id":"2306.11250","title":"InRank: Incremental Low-Rank Learning","created":"2023-06-20","cited_by_count":10,"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":"2305.15265","title":"Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model","created":"2023-05-24","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":"2303.11525","title":"Sparse-IFT: Sparse Iso-FLOP Transformations for Maximizing Training Efficiency","created":"2023-03-21","cited_by_count":8,"area":null},{"id":"2403.11621","title":"Let's Focus on Neuron: Neuron-Level Supervised Fine-tuning for Large Language Model","created":"2024-03-18","cited_by_count":8,"area":null},{"id":"2502.01179","title":"Joint Localization and Activation Editing for Low-Resource Fine-Tuning","created":"2025-02-03","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":"2402.18508","title":"Orchid: Flexible and Data-Dependent Convolution for Sequence Modeling","created":"2024-02-28","cited_by_count":6,"area":null},{"id":"2404.09707","title":"Adaptive Patching for High-resolution Image Segmentation with Transformers","created":"2024-04-15","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":"2602.12271","title":"MonarchRT: Efficient Attention for Real-Time Video Generation","created":"2026-02-12","cited_by_count":6,"area":"diffusion"},{"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":"2410.02147","title":"Efficient Source-Free Time-Series Adaptation via Parameter Subspace Disentanglement","created":"2024-10-03","cited_by_count":4,"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":"2501.19107","title":"Brain network science modelling of sparse neural networks enables Transformers and LLMs to perform as fully connected","created":"2025-01-31","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":"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":"2505.00582","title":"Block Circulant Adapter for Large Language Models","created":"2025-05-01","cited_by_count":3,"area":null},{"id":"2506.02818","title":"ProcrustesGPT: Compressing LLMs with Structured Matrices and Orthogonal Transformations","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2512.06353","title":"TreeQ: Pushing the Quantization Boundary of Diffusion Transformer via Tree-Structured Mixed-Precision Search","created":"2025-12-06","cited_by_count":3,"area":"diffusion"},{"id":"2601.22275","title":"VMonarch: Efficient Video Diffusion Transformers with Structured Attention","created":"2026-01-29","cited_by_count":3,"area":"diffusion"},{"id":"2212.08330","title":"Convolution-enhanced Evolving Attention Networks","created":"2022-12-16","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":"2312.00412","title":"SCHEME: Scalable Channel Mixer for Vision Transformers","created":"2023-12-01","cited_by_count":2,"area":null},{"id":"2406.11307","title":"An Empirical Investigation of Matrix Factorization Methods for Pre-trained Transformers","created":"2024-06-17","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":"2604.05183","title":"OrthoFuse: Training-free Riemannian Fusion of Orthogonal Style-Concept Adapters for Diffusion Models","created":"2026-04-06","cited_by_count":2,"area":"diffusion"},{"id":"2206.12490","title":"Arithmetic Circuits, Structured Matrices and (not so) Deep Learning","created":"2022-06-24","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":"2304.07613","title":"STen: Productive and Efficient Sparsity in PyTorch","created":"2023-04-15","cited_by_count":1,"area":null},{"id":"2304.10553","title":"Sparsity in neural networks can improve their privacy","created":"2023-04-20","cited_by_count":1,"area":"safety"},{"id":"2503.01873","title":"Online Pseudo-average Shifting Attention(PASA) for Robust Low-precision LLM Inference: Algorithms and Numerical Analysis","created":"2025-02-26","cited_by_count":1,"area":null},{"id":"2506.01824","title":"A Quantum Information Theoretic Approach to Tractable Probabilistic Models","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2509.15113","title":"Low-rank surrogate modeling and stochastic zero-order optimization for training of neural networks with black-box layers","created":"2025-09-18","cited_by_count":1,"area":null},{"id":"2511.11641","title":"EcoSpa: Efficient Transformer Training with Coupled Sparsity","created":"2025-11-09","cited_by_count":1,"area":null},{"id":"2512.20861","title":"Memory-Efficient Acceleration of Block Low-Rank Foundation Models on Resource Constrained GPUs","created":"2025-12-24","cited_by_count":1,"area":null},{"id":"2207.00903","title":"A Structured Sparse Neural Network and Its Matrix Calculations Algorithm","created":"2022-07-02","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":"2403.00952","title":"MediSwift: Efficient Sparse Pre-trained Biomedical Language Models","created":"2024-03-01","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":"2502.00585","title":"Converting Transformers into DGNNs Form","created":"2025-02-01","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":"2505.22255","title":"Kronecker Factorization Improves Efficiency and Interpretability of Sparse Autoencoders","created":"2025-05-28","cited_by_count":0,"area":"mechinterp"},{"id":"2505.24241","title":"Advantageous Parameter Expansion Training Makes Better Large Language Models","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2506.13514","title":"TensorSLM: Energy-efficient Embedding Compression of Sub-billion Parameter Language Models on Low-end Devices","created":"2025-06-16","cited_by_count":0,"area":null},{"id":"2510.05175","title":"Exact Causal Attention with 10% Fewer Operations","created":"2025-10-05","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":"2511.16054","title":"Learning Tractable Distributions Of Language Model Continuations","created":"2025-11-20","cited_by_count":0,"area":null},{"id":"2601.13563","title":"ButterflyMoE: Compression-Scalable Ternary Experts via Structured Butterfly Orbits","created":"2026-01-20","cited_by_count":0,"area":"moe"},{"id":"2602.07070","title":"Hybrid Dual-Path Linear Transformations for Efficient Transformer Architectures","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2603.06746","title":"ButterflyViT: 354$\\times$ Expert Compression for Edge Vision Transformers","created":"2026-03-06","cited_by_count":0,"area":"moe"},{"id":"2604.04440","title":"Training Transformers in Cosine Coefficient Space","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2605.06628","title":"LiVeAction: a Lightweight, Versatile, and Asymmetric Neural Codec Design for Real-time Operation","created":"2026-05-07","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":"2605.09204","title":"LBI: Parallel Scan Backpropagation via Latent Bounded Interfaces","created":"2026-05-09","cited_by_count":0,"area":"ssm"},{"id":"2605.15916","title":"LoCO: Low-rank Compositional Rotation Fine-tuning","created":"2026-05-15","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":"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":"2609.27982","title":"Riemannian Structure and Optimization for a Class of Low-Parametric Orthogonal Matrices","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.30682","title":"Structure-Guided Masked Autoencoders for Ultra-High Resolution Scientific Image Understanding","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.32814","title":"Change the Product, Keep the Parameters: Associative Algebra Layers for Transformers","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":"100"}