{"list":"other","total":57,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2305.15408","title":"Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective","created":"2023-05-24","cited_by_count":294},{"id":"2210.10749","title":"Transformers Learn Shortcuts to Automata","created":"2022-10-19","cited_by_count":268},{"id":"2207.00729","title":"The Parallelism Tradeoff: Limitations of Log-Precision Transformers","created":"2022-07-02","cited_by_count":193},{"id":"2106.16213","title":"Saturated Transformers are Constant-Depth Threshold Circuits","created":"2021-06-30","cited_by_count":139},{"id":"2306.02896","title":"Representational Strengths and Limitations of Transformers","created":"2023-06-05","cited_by_count":133},{"id":"1706.03175","title":"Recovery Guarantees for One-hidden-layer Neural Networks","created":"2017-06-10","cited_by_count":94},{"id":"2210.02671","title":"A Logic for Expressing Log-Precision Transformers","created":"2022-10-06","cited_by_count":67},{"id":"1406.3824","title":"Spectral Methods meet EM: A Provably Optimal Algorithm for Crowdsourcing","created":"2014-06-15","cited_by_count":63},{"id":"2112.07628","title":"Training Multi-Layer Over-Parametrized Neural Network in Subquadratic Time","created":"2021-12-14","cited_by_count":62},{"id":"2303.16504","title":"An Over-parameterized Exponential Regression","created":"2023-03-29","cited_by_count":45},{"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},{"id":"2402.04520","title":"On Computational Limits of Modern Hopfield Models: A Fine-Grained Complexity Analysis","created":"2024-02-07","cited_by_count":41},{"id":"2407.01079","title":"On Statistical Rates and Provably Efficient Criteria of Latent Diffusion Transformers (DiTs)","created":"2024-07-01","cited_by_count":40},{"id":"2407.15720","title":"Do Large Language Models Have Compositional Ability? An Investigation into Limitations and Scalability","created":"2024-07-22","cited_by_count":40},{"id":"2409.17422","title":"Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token Reduction","created":"2024-09-25","cited_by_count":39},{"id":"1307.6887","title":"Sequential Transfer in Multi-armed Bandit with Finite Set of Models","created":"2013-07-25","cited_by_count":38},{"id":"2404.03827","title":"Uniform Memory Retrieval with Larger Capacity for Modern Hopfield Models","created":"2024-04-04","cited_by_count":38},{"id":"1708.04181","title":"Tensor Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Tensors via Convex Optimization","created":"2017-08-14","cited_by_count":35},{"id":"2312.17346","title":"STanHop: Sparse Tandem Hopfield Model for Memory-Enhanced Time Series Prediction","created":"2023-12-28","cited_by_count":35},{"id":"2405.05219","title":"Conv-Basis: A New Paradigm for Efficient Attention Inference and Gradient Computation in Transformers","created":"2024-05-08","cited_by_count":32},{"id":"2406.03136","title":"Computational Limits of Low-Rank Adaptation (LoRA) Fine-Tuning for Transformer Models","created":"2024-06-05","cited_by_count":31},{"id":"2405.16411","title":"Training Tensor Attention Efficiently: From Cubic to Almost Linear Time","created":"2024-05-26","cited_by_count":30},{"id":"1608.05749","title":"Solving a Mixture of Many Random Linear Equations by Tensor Decomposition and Alternating Minimization","created":"2016-08-19","cited_by_count":26},{"id":"2411.07602","title":"Circuit Complexity Bounds for RoPE-based Transformer Architecture","created":"2024-11-12","cited_by_count":26},{"id":"2409.13629","title":"Transformers in Uniform TC$^0$","created":"2024-09-20","cited_by_count":25},{"id":"2402.09469","title":"Fourier Circuits in Neural Networks and Transformers: A Case Study of Modular Arithmetic with Multiple Inputs","created":"2024-02-12","cited_by_count":22},{"id":"2408.13233","title":"Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time","created":"2024-08-23","cited_by_count":22},{"id":"2410.11268","title":"Bypassing the Exponential Dependency: Looped Transformers Efficiently Learn In-context by Multi-step Gradient Descent","created":"2024-10-15","cited_by_count":22},{"id":"2411.16525","title":"Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency","created":"2024-11-25","cited_by_count":22},{"id":"2404.03830","title":"BiSHop: Bi-Directional Cellular Learning for Tabular Data with Generalized Sparse Modern Hopfield Model","created":"2024-04-04","cited_by_count":21},{"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},{"id":"1908.01341","title":"SF-Net: Structured Feature Network for Continuous Sign Language Recognition","created":"2019-08-04","cited_by_count":20},{"id":"2410.11261","title":"Beyond Linear Approximations: A Novel Pruning Approach for Attention Matrix","created":"2024-10-15","cited_by_count":20},{"id":"2211.00170","title":"What is my math transformer doing? -- Three results on interpretability and generalization","created":"2022-10-31","cited_by_count":19},{"id":"2408.12151","title":"A Tighter Complexity Analysis of SparseGPT","created":"2024-08-22","cited_by_count":19},{"id":"2410.09375","title":"Looped ReLU MLPs May Be All You Need as Practical Programmable Computers","created":"2024-10-12","cited_by_count":19},{"id":"2410.10165","title":"HSR-Enhanced Sparse Attention Acceleration","created":"2024-10-14","cited_by_count":19},{"id":"2410.23126","title":"Provably Optimal Memory Capacity for Modern Hopfield Models: Transformer-Compatible Dense Associative Memories as Spherical Codes","created":"2024-10-30","cited_by_count":19},{"id":"2407.14717","title":"Provable Differentially Private Computation of the Cross-Attention Mechanism","created":"2024-07-20","cited_by_count":14},{"id":"2210.08361","title":"A Nearly Optimal Size Coreset Algorithm with Nearly Linear Time","created":"2022-10-15","cited_by_count":13},{"id":"2102.01279","title":"Deep Online Fused Video Stabilization","created":"2021-02-02","cited_by_count":11},{"id":"2410.09397","title":"On Fine-Grained I/O Complexity of Attention Backward Passes","created":"2024-10-12","cited_by_count":11},{"id":"2110.02667","title":"Attentive Walk-Aggregating Graph Neural Networks","created":"2021-10-06","cited_by_count":10},{"id":"2303.06210","title":"A Theoretical Analysis Of Nearest Neighbor Search On Approximate Near Neighbor Graph","created":"2023-03-10","cited_by_count":10},{"id":"2310.11291","title":"An Automatic Learning Rate Schedule Algorithm for Achieving Faster Convergence and Steeper Descent","created":"2023-10-17","cited_by_count":9},{"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},{"id":"2412.06061","title":"Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond","created":"2024-12-08","cited_by_count":8},{"id":"2408.06395","title":"Fast John Ellipsoid Computation with Differential Privacy Optimization","created":"2024-08-12","cited_by_count":7},{"id":"2411.16549","title":"In-Context Deep Learning via Transformer Models","created":"2024-11-25","cited_by_count":6},{"id":"1507.01784","title":"Rethinking LDA: moment matching for discrete ICA","created":"2015-07-07","cited_by_count":5},{"id":"1701.04043","title":"Iterative Block Tensor Singular Value Thresholding for Extraction of Low Rank Component of Image Data","created":"2017-01-15","cited_by_count":4},{"id":"1610.00843","title":"The Search Problem in Mixture Models","created":"2016-10-04","cited_by_count":3},{"id":"2005.00404","title":"Complexity of the Infinitary Lambek Calculus with Kleene Star","created":"2020-05-01","cited_by_count":2}],"next_cursor":null}