{"total":68,"rows":[{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"id":"2407.09450","title":"Human-inspired Episodic Memory for Infinite Context LLMs","created":"2024-07-12","cited_by_count":62,"area":null},{"id":"2406.15486","title":"SampleAttention: Near-Lossless Acceleration of Long Context LLM Inference with Adaptive Structured Sparse Attention","created":"2024-06-17","cited_by_count":39,"area":null},{"id":"2501.06425","title":"Tensor Product Attention Is All You Need","created":"2025-01-11","cited_by_count":31,"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":"2412.14468","title":"HashAttention: Semantic Sparsity for Faster Inference","created":"2024-12-19","cited_by_count":24,"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":"2408.12151","title":"A Tighter Complexity Analysis of SparseGPT","created":"2024-08-22","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":"2311.10609","title":"Scaling TabPFN: Sketching and Feature Selection for Tabular Prior-Data Fitted Networks","created":"2023-11-17","cited_by_count":18,"area":null},{"id":"2310.11685","title":"Why Softmax Attention Outperforms Linear Attention","created":"2023-10-18","cited_by_count":15,"area":null},{"id":"2505.17505","title":"L-MTP: Leap Multi-Token Prediction Beyond Adjacent Context for Large Language Models","created":"2025-05-23","cited_by_count":15,"area":null},{"id":"2406.05815","title":"What Can We Learn from State Space Models for Machine Learning on Graphs?","created":"2024-06-09","cited_by_count":13,"area":null},{"id":"2402.12535","title":"Locality-Sensitive Hashing-Based Efficient Point Transformer with Applications in High-Energy Physics","created":"2024-02-19","cited_by_count":12,"area":null},{"id":"2410.06441","title":"Addax: Utilizing Zeroth-Order Gradients to Improve Memory Efficiency and Performance of SGD for Fine-Tuning Language Models","created":"2024-10-09","cited_by_count":11,"area":null},{"id":"2502.07861","title":"Streaming Attention Approximation via Discrepancy Theory","created":"2025-02-11","cited_by_count":11,"area":null},{"id":"2502.08246","title":"Inference-time sparse attention with asymmetric indexing","created":"2025-02-12","cited_by_count":11,"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":"2403.01915","title":"xT: Nested Tokenization for Larger Context in Large Images","created":"2024-03-04","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":"2504.09621","title":"Tokenize Image Patches: Global Context Fusion for Effective Haze Removal in Large Images","created":"2025-04-13","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":"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":"2510.05688","title":"vAttention: Verified Sparse Attention","created":"2025-10-07","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":"2505.14840","title":"Subquadratic Algorithms and Hardness for Attention with Any Temperature","created":"2025-05-20","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":"2505.22107","title":"Curse of High Dimensionality Issue in Transformer for Long-context Modeling","created":"2025-05-28","cited_by_count":5,"area":null},{"id":"2510.04008","title":"RACE Attention: A Strictly Linear-Time Attention Layer for Training on Outrageously Large Contexts","created":"2025-10-05","cited_by_count":5,"area":null},{"id":"2409.12175","title":"Expanding Expressivity in Transformer Models with M\\\"obiusAttention","created":"2024-09-08","cited_by_count":4,"area":null},{"id":"2410.14092","title":"Efficient Sparse PCA via Block-Diagonalization","created":"2024-10-18","cited_by_count":4,"area":null},{"id":"2507.07694","title":"SAS: Simulated Attention Score","created":"2025-07-10","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":"2605.05602","title":"Nearly Optimal Attention Coresets","created":"2026-05-07","cited_by_count":4,"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":"2410.05462","title":"LevAttention: Time, Space, and Streaming Efficient Algorithm for Heavy Attentions","created":"2024-10-07","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":"2402.17682","title":"NextLevelBERT: Masked Language Modeling with Higher-Level Representations for Long Documents","created":"2024-02-27","cited_by_count":2,"area":null},{"id":"2412.02819","title":"CNNSum: Exploring Long-Context Summarization with Large Language Models in Chinese Novels","created":"2024-12-03","cited_by_count":2,"area":null},{"id":"2503.10571","title":"Radar: Fast Long-Context Decoding for Any Transformer","created":"2025-03-13","cited_by_count":2,"area":null},{"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":"2512.22088","title":"Unifying Learning Dynamics and Generalization in Transformers Scaling Law","created":"2025-12-26","cited_by_count":2,"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":"2508.07185","title":"DySK-Attn: A Framework for Efficient, Real-Time Knowledge Updating in Large Language Models via Dynamic Sparse Knowledge Attention","created":"2025-08-10","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":"2602.04915","title":"SLAY: Geometry-Aware Spherical Linearized Attention with Yat-Kernel","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2602.12128","title":"HLA: Hadamard Linear Attention","created":"2026-02-12","cited_by_count":1,"area":null},{"id":"2605.09472","title":"Positional LSH: Binary Block Matrix Approximation for Attention with Linear Biases","created":"2026-05-10","cited_by_count":1,"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":"2503.01564","title":"Attention Condensation via Sparsity Induced Regularized Training","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2505.11040","title":"Efficient Attention via Pre-Scoring: Prioritizing Informative Keys in Transformers","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2507.17245","title":"DistrAttention: An Efficient and Flexible Self-Attention Mechanism on Modern GPUs","created":"2025-07-23","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":"2605.14935","title":"Multi-scale Coarse-to-fine Modeling for Test-time Human Motion Control","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.23751","title":"Approaching I/O-optimality for Approximate Attention","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2606.10944","title":"Express Language Modeling","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2607.20214","title":"ELSAA: Efficient Low-Rank and Sparse Attention Approximation for Training Transformers","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2608.26965","title":"ClusterAttention: A training-free speedup of bidirectional attention","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.37261","title":"Efficiently Approximating Attention Is Hard","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.01230","title":"HHR: Hierarchical Hash Retrieval for Efficient LLM Generation","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}