{"list":"other","total":60,"rows":[{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"2103.10360","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","created":"2021-03-18","cited_by_count":1031},{"id":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"id":"1503.05671","title":"Optimizing Neural Networks with Kronecker-factored Approximate Curvature","created":"2015-03-19","cited_by_count":796},{"id":"2103.10385","title":"GPT Understands, Too","created":"2021-03-18","cited_by_count":716},{"id":"2401.02385","title":"TinyLlama: An Open-Source Small Language Model","created":"2024-01-04","cited_by_count":618},{"id":"1412.1193","title":"New insights and perspectives on the natural gradient method","created":"2014-12-03","cited_by_count":443},{"id":"2310.06694","title":"Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning","created":"2023-10-10","cited_by_count":415},{"id":"2006.04647","title":"Neural Architecture Search without Training","created":"2020-06-08","cited_by_count":244},{"id":"1906.04284","title":"Analyzing the Structure of Attention in a Transformer Language Model","created":"2019-06-07","cited_by_count":243},{"id":"1905.12558","title":"Limitations of the Empirical Fisher Approximation for Natural Gradient Descent","created":"2019-05-29","cited_by_count":217},{"id":"1910.04732","title":"Structured Pruning of Large Language Models","created":"2019-10-10","cited_by_count":203},{"id":"1903.09848","title":"Competence-based Curriculum Learning for Neural Machine Translation","created":"2019-03-23","cited_by_count":202},{"id":"1301.3584","title":"Revisiting Natural Gradient for Deep Networks","created":"2013-01-16","cited_by_count":159},{"id":"2309.00363","title":"FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learning","created":"2023-09-01","cited_by_count":149},{"id":"2204.03809","title":"Federated Learning with Partial Model Personalization","created":"2022-04-08","cited_by_count":114},{"id":"2308.06522","title":"SLoRA: Federated Parameter Efficient Fine-Tuning of Language Models","created":"2023-08-12","cited_by_count":93},{"id":"1806.01316","title":"Universal Statistics of Fisher Information in Deep Neural Networks: Mean Field Approach","created":"2018-06-04","cited_by_count":91},{"id":"2208.12268","title":"FedPrompt: Communication-Efficient and Privacy Preserving Prompt Tuning in Federated Learning","created":"2022-08-25","cited_by_count":91},{"id":"2205.11961","title":"ATTEMPT: Parameter-Efficient Multi-task Tuning via Attentional Mixtures of Soft Prompts","created":"2022-05-24","cited_by_count":85},{"id":"2012.15832","title":"Shortformer: Better Language Modeling using Shorter Inputs","created":"2020-12-31","cited_by_count":76},{"id":"2206.00187","title":"DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Training","created":"2022-06-01","cited_by_count":74},{"id":"2104.14362","title":"From Distributed Machine Learning to Federated Learning: A Survey","created":"2021-04-29","cited_by_count":66},{"id":"2310.15080","title":"Federated Learning of Large Language Models with Parameter-Efficient Prompt Tuning and Adaptive Optimization","created":"2023-10-23","cited_by_count":65},{"id":"2012.14193","title":"Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization","created":"2020-12-28","cited_by_count":62},{"id":"2112.09824","title":"Federated Dynamic Sparse Training: Computing Less, Communicating Less, Yet Learning Better","created":"2021-12-18","cited_by_count":55},{"id":"2204.04497","title":"IDPG: An Instance-Dependent Prompt Generation Method","created":"2022-04-09","cited_by_count":43},{"id":"2305.02776","title":"Efficient Personalized Federated Learning via Sparse Model-Adaptation","created":"2023-05-04","cited_by_count":38},{"id":"1904.09408","title":"Language Models with Transformers","created":"2019-04-20","cited_by_count":36},{"id":"2108.06084","title":"The Stability-Efficiency Dilemma: Investigating Sequence Length Warmup for Training GPT Models","created":"2021-08-13","cited_by_count":36},{"id":"2312.05770","title":"FedASMU: Efficient Asynchronous Federated Learning with Dynamic Staleness-aware Model Update","created":"2023-12-10","cited_by_count":32},{"id":"1303.0818","title":"Riemannian metrics for neural networks I: feedforward networks","created":"2013-03-04","cited_by_count":30},{"id":"2112.05928","title":"Efficient Device Scheduling with Multi-Job Federated Learning","created":"2021-12-11","cited_by_count":29},{"id":"2204.11536","title":"FedDUAP: Federated Learning with Dynamic Update and Adaptive Pruning Using Shared Data on the Server","created":"2022-04-25","cited_by_count":29},{"id":"2308.13894","title":"FwdLLM: Efficient FedLLM using Forward Gradient","created":"2023-08-26","cited_by_count":26},{"id":"2302.05601","title":"Pruning Deep Neural Networks from a Sparsity Perspective","created":"2023-02-11","cited_by_count":25},{"id":"2211.14133","title":"PipeFisher: Efficient Training of Large Language Models Using Pipelining and Fisher Information Matrices","created":"2022-11-25","cited_by_count":24},{"id":"2207.07223","title":"Accelerated Federated Learning with Decoupled Adaptive Optimization","created":"2022-07-14","cited_by_count":23},{"id":"2210.11292","title":"Late Prompt Tuning: A Late Prompt Could Be Better Than Many Prompts","created":"2022-10-20","cited_by_count":23},{"id":"2206.10546","title":"FedHiSyn: A Hierarchical Synchronous Federated Learning Framework for Resource and Data Heterogeneity","created":"2022-06-21","cited_by_count":20},{"id":"2211.13430","title":"Multi-Job Intelligent Scheduling with Cross-Device Federated Learning","created":"2022-11-24","cited_by_count":20},{"id":"2212.08343","title":"SplitGP: Achieving Both Generalization and Personalization in Federated Learning","created":"2022-12-16","cited_by_count":20},{"id":"2111.10635","title":"HeterPS: Distributed Deep Learning With Reinforcement Learning Based Scheduling in Heterogeneous Environments","created":"2021-11-20","cited_by_count":15},{"id":"2312.10935","title":"AEDFL: Efficient Asynchronous Decentralized Federated Learning with Heterogeneous Devices","created":"2023-12-18","cited_by_count":15},{"id":"2403.12329","title":"FedFisher: Leveraging Fisher Information for One-Shot Federated Learning","created":"2024-03-19","cited_by_count":15},{"id":"2212.03597","title":"DeepSpeed Data Efficiency: Improving Deep Learning Model Quality and Training Efficiency via Efficient Data Sampling and Routing","created":"2022-12-07","cited_by_count":13},{"id":"2303.04574","title":"Distributed and Deep Vertical Federated Learning with Big Data","created":"2023-03-08","cited_by_count":10},{"id":"2212.12712","title":"When Do Curricula Work in Federated Learning?","created":"2022-12-24","cited_by_count":9},{"id":"2312.15186","title":"Efficient Asynchronous Federated Learning with Sparsification and Quantization","created":"2023-12-23","cited_by_count":9},{"id":"2408.05678","title":"Efficient Federated Learning Using Dynamic Update and Adaptive Pruning with Momentum on Shared Server Data","created":"2024-08-11","cited_by_count":6},{"id":"2306.07644","title":"SRATTA : Sample Re-ATTribution Attack of Secure Aggregation in Federated Learning","created":"2023-06-13","cited_by_count":3}],"next_cursor":null}