{"total":102,"rows":[{"id":"2306.14048","title":"H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models","created":"2023-06-24","cited_by_count":832,"area":"inference"},{"id":"2310.17157","title":"Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time","created":"2023-10-26","cited_by_count":252,"area":null},{"id":"2402.04347","title":"The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry","created":"2024-02-06","cited_by_count":120,"area":null},{"id":"2410.16179","title":"MagicPIG: LSH Sampling for Efficient LLM Generation","created":"2024-10-21","cited_by_count":111,"area":null},{"id":"2310.05869","title":"HyperAttention: Long-context Attention in Near-Linear Time","created":"2023-10-09","cited_by_count":85,"area":null},{"id":"2502.01951","title":"On the Emergence of Position Bias in Transformers","created":"2025-02-04","cited_by_count":59,"area":null},{"id":"2304.10411","title":"Attention Scheme Inspired Softmax Regression","created":"2023-04-20","cited_by_count":49,"area":null},{"id":"2405.18781","title":"On the Role of Attention Masks and LayerNorm in Transformers","created":"2024-05-29","cited_by_count":48,"area":null},{"id":"2303.16504","title":"An Over-parameterized Exponential Regression","created":"2023-03-29","cited_by_count":45,"area":null},{"id":"2303.15725","title":"Solving Regularized Exp, Cosh and Sinh Regression Problems","created":"2023-03-28","cited_by_count":44,"area":null},{"id":"2310.04064","title":"How to Capture Higher-order Correlations? Generalizing Matrix Softmax Attention to Kronecker Computation","created":"2023-10-06","cited_by_count":44,"area":null},{"id":"2304.13276","title":"The Closeness of In-Context Learning and Weight Shifting for Softmax Regression","created":"2023-04-26","cited_by_count":41,"area":null},{"id":"2404.03827","title":"Uniform Memory Retrieval with Larger Capacity for Modern Hopfield Models","created":"2024-04-04","cited_by_count":38,"area":null},{"id":"2404.03828","title":"Outlier-Efficient Hopfield Layers for Large Transformer-Based Models","created":"2024-04-04","cited_by_count":38,"area":null},{"id":"2304.04397","title":"Randomized and Deterministic Attention Sparsification Algorithms for Over-parameterized Feature Dimension","created":"2023-04-10","cited_by_count":37,"area":null},{"id":"2310.01655","title":"PolySketchFormer: Fast Transformers via Sketching Polynomial Kernels","created":"2023-10-02","cited_by_count":36,"area":null},{"id":"2305.00660","title":"An Iterative Algorithm for Rescaled Hyperbolic Functions Regression","created":"2023-05-01","cited_by_count":35,"area":null},{"id":"2307.02419","title":"In-Context Learning for Attention Scheme: from Single Softmax Regression to Multiple Softmax Regression via a Tensor Trick","created":"2023-07-05","cited_by_count":32,"area":null},{"id":"2406.03136","title":"Computational Limits of Low-Rank Adaptation (LoRA) Fine-Tuning for Transformer Models","created":"2024-06-05","cited_by_count":31,"area":null},{"id":"2306.04933","title":"InfoPrompt: Information-Theoretic Soft Prompt Tuning for Natural Language Understanding","created":"2023-06-08","cited_by_count":30,"area":null},{"id":"2309.07418","title":"A Fast Optimization View: Reformulating Single Layer Attention in LLM Based on Tensor and SVM Trick, and Solving It in Matrix Multiplication Time","created":"2023-09-14","cited_by_count":30,"area":null},{"id":"2402.04497","title":"The Fine-Grained Complexity of Gradient Computation for Training Large Language Models","created":"2024-02-07","cited_by_count":30,"area":null},{"id":"2405.16411","title":"Training Tensor Attention Efficiently: From Cubic to Almost Linear Time","created":"2024-05-26","cited_by_count":30,"area":null},{"id":"2306.02295","title":"A Mathematical Abstraction for Balancing the Trade-off Between Creativity and Reality in Large Language Models","created":"2023-06-04","cited_by_count":29,"area":null},{"id":"2308.12247","title":"How to Protect Copyright Data in Optimization of Large Language Models?","created":"2023-08-23","cited_by_count":26,"area":null},{"id":"2411.07602","title":"Circuit Complexity Bounds for RoPE-based Transformer Architecture","created":"2024-11-12","cited_by_count":26,"area":null},{"id":"2305.04701","title":"Differentially Private Attention Computation","created":"2023-05-08","cited_by_count":25,"area":null},{"id":"2308.10502","title":"GradientCoin: A Peer-to-Peer Decentralized Large Language Models","created":"2023-08-21","cited_by_count":23,"area":null},{"id":"2408.13233","title":"Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time","created":"2024-08-23","cited_by_count":22,"area":null},{"id":"2402.06082","title":"SubGen: Token Generation in Sublinear Time and Memory","created":"2024-02-08","cited_by_count":21,"area":"inference"},{"id":"2412.06148","title":"The Computational Limits of State-Space Models and Mamba via the Lens of Circuit Complexity","created":"2024-12-09","cited_by_count":21,"area":"ssm"},{"id":"2308.14304","title":"Solving Attention Kernel Regression Problem via Pre-conditioner","created":"2023-08-28","cited_by_count":20,"area":null},{"id":"2402.13934","title":"Do Efficient Transformers Really Save Computation?","created":"2024-02-21","cited_by_count":20,"area":null},{"id":"2408.12151","title":"A Tighter Complexity Analysis of SparseGPT","created":"2024-08-22","cited_by_count":19,"area":null},{"id":"2410.09375","title":"Looped ReLU MLPs May Be All You Need as Practical Programmable Computers","created":"2024-10-12","cited_by_count":19,"area":null},{"id":"2410.10165","title":"HSR-Enhanced Sparse Attention Acceleration","created":"2024-10-14","cited_by_count":19,"area":null},{"id":"2307.08045","title":"Beyond Classical Attention: Quantum Attention for Scalable Computation","created":"2023-07-16","cited_by_count":18,"area":null},{"id":"2510.04401","title":"Your Vision-Language Model Can't Even Count to 20: Exposing the Failures of VLMs in Compositional Counting","created":"2025-10-06","cited_by_count":18,"area":"mllm"},{"id":"2307.08352","title":"Zero-th Order Algorithm for Softmax Attention Optimization","created":"2023-07-17","cited_by_count":16,"area":null},{"id":"2310.11685","title":"Why Softmax Attention Outperforms Linear Attention","created":"2023-10-18","cited_by_count":15,"area":null},{"id":"2407.14717","title":"Provable Differentially Private Computation of the Cross-Attention Mechanism","created":"2024-07-20","cited_by_count":14,"area":"diffusion"},{"id":"2412.17316","title":"RoPE Attention Can Be Trained in Almost Linear Time","created":"2024-12-23","cited_by_count":13,"area":null},{"id":"2309.13482","title":"A Unified Scheme of ResNet and Softmax","created":"2023-09-23","cited_by_count":12,"area":null},{"id":"2310.12462","title":"Unmasking Transformers: A Theoretical Approach to Data Recovery via Attention Weights","created":"2023-10-19","cited_by_count":12,"area":null},{"id":"2307.06565","title":"Efficient SGD Neural Network Training via Sublinear Activated Neuron Identification","created":"2023-07-13","cited_by_count":11,"area":null},{"id":"2502.00500","title":"Video Latent Flow Matching: Optimal Polynomial Projections for Video Interpolation and Extrapolation","created":"2025-02-01","cited_by_count":11,"area":"diffusion"},{"id":"2502.16490","title":"On Computational Limits of FlowAR Models: Expressivity and Efficiency","created":"2025-02-23","cited_by_count":10,"area":null},{"id":"2305.17482","title":"Federated Empirical Risk Minimization via Second-Order Method","created":"2023-05-27","cited_by_count":9,"area":null},{"id":"2311.15390","title":"Local Convergence of Approximate Newton Method for Two Layer Nonlinear Regression","created":"2023-11-26","cited_by_count":9,"area":null},{"id":"2410.04271","title":"Fundamental Limitations on Subquadratic Alternatives to Transformers","created":"2024-10-05","cited_by_count":9,"area":"ssm"},{"id":"2412.05562","title":"Modern Hopfield Networks Require Chain-of-Thought to Solve $\\mathsf{NC}^1$-Hard Problems","created":"2024-12-07","cited_by_count":9,"area":null},{"id":"2505.11892","title":"Fast RoPE Attention: Combining the Polynomial Method and Fast Fourier Transform","created":"2025-05-17","cited_by_count":9,"area":null},{"id":"2304.06594","title":"Solving Tensor Low Cycle Rank Approximation","created":"2023-04-13","cited_by_count":8,"area":null},{"id":"2309.07452","title":"Is Solving Graph Neural Tangent Kernel Equivalent to Training Graph Neural Network?","created":"2023-09-14","cited_by_count":8,"area":null},{"id":"2310.20051","title":"The Expressibility of Polynomial based Attention Scheme","created":"2023-10-30","cited_by_count":7,"area":null},{"id":"2502.12063","title":"Low-Rank Thinning","created":"2025-02-17","cited_by_count":7,"area":null},{"id":"2505.16284","title":"Only Large Weights (And Not Skip Connections) Can Prevent the Perils of Rank Collapse","created":"2025-05-22","cited_by_count":7,"area":null},{"id":"2308.08358","title":"Convergence of Two-Layer Regression with Nonlinear Units","created":"2023-08-16","cited_by_count":6,"area":null},{"id":"2311.13624","title":"A Theoretical Insight into Attack and Defense of Gradient Leakage in Transformer","created":"2023-11-22","cited_by_count":6,"area":null},{"id":"2311.14652","title":"One Pass Streaming Algorithm for Super Long Token Attention Approximation in Sublinear Space","created":"2023-11-24","cited_by_count":6,"area":null},{"id":"2402.07443","title":"The I/O Complexity of Attention, or How Optimal is Flash Attention?","created":"2024-02-12","cited_by_count":6,"area":null},{"id":"2410.14944","title":"Part-Whole Relational Fusion Towards Multi-Modal Scene Understanding","created":"2024-10-19","cited_by_count":6,"area":null},{"id":"2602.10056","title":"WildCat: Near-Linear Attention in Theory and Practice","created":"2026-02-10","cited_by_count":6,"area":null},{"id":"2303.04555","title":"Streaming Kernel PCA Algorithm With Small Space","created":"2023-03-08","cited_by_count":5,"area":null},{"id":"2305.08001","title":"Structured and Fast Optimization: The Kronecker SGD Algorithm","created":"2023-05-13","cited_by_count":5,"area":null},{"id":"2502.15955","title":"Compression Barriers for Autoregressive Transformers","created":"2025-02-21","cited_by_count":5,"area":"inference"},{"id":"2505.14840","title":"Subquadratic Algorithms and Hardness for Attention with Any Temperature","created":"2025-05-20","cited_by_count":5,"area":null},{"id":"2508.07102","title":"Towards High-Order Mean Flow Generative Models: Feasibility, Expressivity, and Provably Efficient Criteria","created":"2025-08-09","cited_by_count":5,"area":"diffusion"},{"id":"2410.11279","title":"Advancing the Understanding of Fixed Point Iterations in Deep Neural Networks: A Detailed Analytical Study","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2503.01314","title":"Scaling Law Phenomena Across Regression Paradigms: Multiple and Kernel Approaches","created":"2025-03-03","cited_by_count":4,"area":null},{"id":"2505.19531","title":"Minimalist Softmax Attention Provably Learns Constrained Boolean Functions","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2507.23539","title":"Improved Algorithms for Kernel Matrix-Vector Multiplication Under Sparsity Assumptions","created":"2025-07-31","cited_by_count":4,"area":null},{"id":"2508.13214","title":"Too Easily Fooled? Prompt Injection Breaks LLMs on Frustratingly Simple Multiple-Choice Questions","created":"2025-08-16","cited_by_count":4,"area":"safety"},{"id":"2605.05602","title":"Nearly Optimal Attention Coresets","created":"2026-05-07","cited_by_count":4,"area":null},{"id":"2607.01520","title":"The risk of KV cache compression","created":"2026-07-01","cited_by_count":4,"area":"inference"},{"id":"2311.01960","title":"Hardness of Low Rank Approximation of Entrywise Transformed Matrix Products","created":"2023-11-03","cited_by_count":3,"area":null},{"id":"2407.03250","title":"When big data actually are low-rank, or entrywise approximation of certain function-generated matrices","created":"2024-07-03","cited_by_count":3,"area":null},{"id":"2409.01688","title":"Differentially Private Kernel Density Estimation","created":"2024-09-03","cited_by_count":3,"area":null},{"id":"2410.05462","title":"LevAttention: Time, Space, and Streaming Efficient Algorithm for Heavy Attentions","created":"2024-10-07","cited_by_count":3,"area":null},{"id":"2502.16912","title":"When Can We Solve the Weighted Low Rank Approximation Problem in Truly Subquadratic Time?","created":"2025-02-24","cited_by_count":3,"area":null},{"id":"2509.09001","title":"Fast attention mechanisms: a tale of parallelism","created":"2025-09-10","cited_by_count":3,"area":null},{"id":"2503.11108","title":"Time and Memory Trade-off of KV-Cache Compression in Tensor Transformer Decoding","created":"2025-03-14","cited_by_count":2,"area":"inference"},{"id":"2503.14076","title":"Theoretical Foundation of Flow-Based Time Series Generation: Provable Approximation, Generalization, and Efficiency","created":"2025-03-18","cited_by_count":2,"area":"diffusion"},{"id":"2506.12220","title":"Two Heads Are Better than One: Simulating Large Transformers with Small Ones","created":"2025-06-13","cited_by_count":2,"area":null},{"id":"2512.07011","title":"Block Sparse Flash Attention","created":"2025-12-07","cited_by_count":2,"area":null},{"id":"2512.22088","title":"Unifying Learning Dynamics and Generalization in Transformers Scaling Law","created":"2025-12-26","cited_by_count":2,"area":null},{"id":"2405.06003","title":"Binary Hypothesis Testing for Softmax Models and Leverage Score Models","created":"2024-05-09","cited_by_count":1,"area":null},{"id":"2411.04013","title":"$k$NN Attention Demystified: A Theoretical Exploration for Scalable Transformers","created":"2024-11-06","cited_by_count":1,"area":null},{"id":"2510.02540","title":"Even Faster Kernel Matrix Linear Algebra via Density Estimation","created":"2025-10-02","cited_by_count":1,"area":null},{"id":"2510.03678","title":"Towards Sampling Data Structures for Tensor Products in Turnstile Streams","created":"2025-10-04","cited_by_count":1,"area":null},{"id":"2602.00874","title":"Sublinear Time Quantum Algorithm for Attention Approximation","created":"2026-01-31","cited_by_count":1,"area":null},{"id":"2602.02707","title":"Every Bit Counts: A Theoretical Study of Precision-Expressivity Tradeoffs in Quantized Transformers","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2309.01030","title":"Online Adaptive Mahalanobis Distance Estimation","created":"2023-09-02","cited_by_count":0,"area":null},{"id":"2311.11429","title":"Fast Heavy Inner Product Identification Between Weights and Inputs in Neural Network Training","created":"2023-11-19","cited_by_count":0,"area":null},{"id":"2407.03392","title":"M5: A Whole Genome Bacterial Encoder at Single Nucleotide Resolution","created":"2024-07-03","cited_by_count":0,"area":null},{"id":"2503.01564","title":"Attention Condensation via Sparsity Induced Regularized Training","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2510.05494","title":"Fundamental Limits of Crystalline Equivariant Graph Neural Networks: A Circuit Complexity Perspective","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2603.11332","title":"On the Computational Hardness of Transformers","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2604.10980","title":"Tracking High-order Evolutions via Cascading Low-rank Fitting","created":"2026-04-13","cited_by_count":0,"area":"diffusion"},{"id":"2605.23751","title":"Approaching I/O-optimality for Approximate Attention","created":"2026-05-22","cited_by_count":0,"area":null}],"next_cursor":"100"}