{"list":"other","total":55,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"1803.01271","title":"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling","created":"2018-03-04","cited_by_count":1476},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"2209.11895","title":"In-context Learning and Induction Heads","created":"2022-09-24","cited_by_count":964},{"id":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","created":"2024-03-13","cited_by_count":916},{"id":"2312.11805","title":"Gemini: A Family of Highly Capable Multimodal Models","created":"2023-12-19","cited_by_count":872},{"id":"2307.08621","title":"Retentive Network: A Successor to Transformer for Large Language Models","created":"2023-07-17","cited_by_count":613},{"id":"2306.09927","title":"Trained Transformers Learn Linear Models In-Context","created":"2023-06-16","cited_by_count":337},{"id":"2402.13753","title":"LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens","created":"2024-02-21","cited_by_count":313},{"id":"2309.12307","title":"LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models","created":"2023-09-21","cited_by_count":244},{"id":"1908.11775","title":"Transformer Dissection: A Unified Understanding of Transformer's Attention via the Lens of Kernel","created":"2019-08-30","cited_by_count":213},{"id":"2403.07183","title":"Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews","created":"2024-03-11","cited_by_count":164},{"id":"2401.01325","title":"LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning","created":"2024-01-02","cited_by_count":136},{"id":"2402.14735","title":"How Transformers Learn Causal Structure with Gradient Descent","created":"2024-02-22","cited_by_count":118},{"id":"1312.5851","title":"Fast Training of Convolutional Networks through FFTs","created":"2013-12-20","cited_by_count":89},{"id":"2402.17463","title":"Training-Free Long-Context Scaling of Large Language Models","created":"2024-02-27","cited_by_count":62},{"id":"2303.09136","title":"A Short Survey of Viewing Large Language Models in Legal Aspect","created":"2023-03-16","cited_by_count":52},{"id":"2304.10411","title":"Attention Scheme Inspired Softmax Regression","created":"2023-04-20","cited_by_count":49},{"id":"2404.08801","title":"Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length","created":"2024-04-12","cited_by_count":46},{"id":"2303.15725","title":"Solving Regularized Exp, Cosh and Sinh Regression Problems","created":"2023-03-28","cited_by_count":44},{"id":"2305.04749","title":"Toeplitz Neural Network for Sequence Modeling","created":"2023-05-08","cited_by_count":43},{"id":"2304.13276","title":"The Closeness of In-Context Learning and Weight Shifting for Softmax Regression","created":"2023-04-26","cited_by_count":41},{"id":"2304.04397","title":"Randomized and Deterministic Attention Sparsification Algorithms for Over-parameterized Feature Dimension","created":"2023-04-10","cited_by_count":37},{"id":"2310.01655","title":"PolySketchFormer: Fast Transformers via Sketching Polynomial Kernels","created":"2023-10-02","cited_by_count":36},{"id":"2305.00660","title":"An Iterative Algorithm for Rescaled Hyperbolic Functions Regression","created":"2023-05-01","cited_by_count":35},{"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},{"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},{"id":"2402.04497","title":"The Fine-Grained Complexity of Gradient Computation for Training Large Language Models","created":"2024-02-07","cited_by_count":30},{"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},{"id":"2305.04701","title":"Differentially Private Attention Computation","created":"2023-05-08","cited_by_count":25},{"id":"2308.10502","title":"GradientCoin: A Peer-to-Peer Decentralized Large Language Models","created":"2023-08-21","cited_by_count":23},{"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":"2308.14304","title":"Solving Attention Kernel Regression Problem via Pre-conditioner","created":"2023-08-28","cited_by_count":20},{"id":"2307.08045","title":"Beyond Classical Attention: Quantum Attention for Scalable Computation","created":"2023-07-16","cited_by_count":18},{"id":"2310.04861","title":"Uncovering hidden geometry in Transformers via disentangling position and context","created":"2023-10-07","cited_by_count":18},{"id":"2307.08352","title":"Zero-th Order Algorithm for Softmax Attention Optimization","created":"2023-07-17","cited_by_count":16},{"id":"2310.11685","title":"Why Softmax Attention Outperforms Linear Attention","created":"2023-10-18","cited_by_count":15},{"id":"2309.13482","title":"A Unified Scheme of ResNet and Softmax","created":"2023-09-23","cited_by_count":12},{"id":"2310.12462","title":"Unmasking Transformers: A Theoretical Approach to Data Recovery via Attention Weights","created":"2023-10-19","cited_by_count":12},{"id":"2311.15390","title":"Local Convergence of Approximate Newton Method for Two Layer Nonlinear Regression","created":"2023-11-26","cited_by_count":9},{"id":"2310.20051","title":"The Expressibility of Polynomial based Attention Scheme","created":"2023-10-30","cited_by_count":7},{"id":"2404.13785","title":"How to Inverting the Leverage Score Distribution?","created":"2024-04-21","cited_by_count":5},{"id":"2306.03356","title":"Query Complexity of Active Learning for Function Family With Nearly Orthogonal Basis","created":"2023-06-06","cited_by_count":4},{"id":"2208.09634","title":"An $O(k\\log n)$ Time Fourier Set Query Algorithm","created":"2022-08-20","cited_by_count":2},{"id":"2205.00658","title":"Improved Reconstruction for Fourier-Sparse Signals","created":"2022-05-02","cited_by_count":1}],"next_cursor":null}