{"list":"other","total":61,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"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":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"1912.04977","title":"Advances and Open Problems in Federated Learning","created":"2019-12-10","cited_by_count":3046},{"id":"1812.06127","title":"Federated Optimization in Heterogeneous Networks","created":"2018-12-14","cited_by_count":2987},{"id":"1908.07873","title":"Federated Learning: Challenges, Methods, and Future Directions","created":"2019-08-21","cited_by_count":1538},{"id":"1907.02189","title":"On the Convergence of FedAvg on Non-IID Data","created":"2019-07-04","cited_by_count":1229},{"id":"1806.00582","title":"Federated Learning with Non-IID Data","created":"2018-06-02","cited_by_count":1108},{"id":"1609.04747","title":"An overview of gradient descent optimization algorithms","created":"2016-09-15","cited_by_count":1033},{"id":"2007.07481","title":"Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization","created":"2020-07-15","cited_by_count":906},{"id":"2402.09353","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","created":"2024-02-14","cited_by_count":758},{"id":"2012.13255","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","created":"2020-12-22","cited_by_count":671},{"id":"1909.09436","title":"CodeSearchNet Challenge: Evaluating the State of Semantic Code Search","created":"2019-09-20","cited_by_count":654},{"id":"2006.08848","title":"Personalized Federated Learning with Moreau Envelopes","created":"2020-06-16","cited_by_count":618},{"id":"2102.02079","title":"Federated Learning on Non-IID Data Silos: An Experimental Study","created":"2021-02-03","cited_by_count":568},{"id":"2102.07078","title":"Exploiting Shared Representations for Personalized Federated Learning","created":"2021-02-14","cited_by_count":541},{"id":"2402.12354","title":"LoRA+: Efficient Low Rank Adaptation of Large Models","created":"2024-02-19","cited_by_count":377},{"id":"1804.08838","title":"Measuring the Intrinsic Dimension of Objective Landscapes","created":"2018-04-24","cited_by_count":370},{"id":"2106.06843","title":"Federated Learning on Non-IID Data: A Survey","created":"2021-06-12","cited_by_count":346},{"id":"1807.06629","title":"Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learning","created":"2018-07-17","cited_by_count":278},{"id":"2312.03732","title":"A Rank Stabilization Scaling Factor for Fine-Tuning with LoRA","created":"2023-11-28","cited_by_count":243},{"id":"1906.02367","title":"Qsparse-local-SGD: Distributed SGD with Quantization, Sparsification, and Local Computations","created":"2019-06-06","cited_by_count":181},{"id":"2007.07682","title":"FetchSGD: Communication-Efficient Federated Learning with Sketching","created":"2020-07-15","cited_by_count":179},{"id":"2403.12313","title":"Improving LoRA in Privacy-preserving Federated Learning","created":"2024-03-18","cited_by_count":161},{"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":"2409.05976","title":"FLoRA: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptations","created":"2024-09-09","cited_by_count":146},{"id":"2308.03303","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","created":"2023-08-07","cited_by_count":137},{"id":"2105.11367","title":"FedScale: Benchmarking Model and System Performance of Federated Learning at Scale","created":"2021-05-24","cited_by_count":136},{"id":"2208.11625","title":"PromptFL: Let Federated Participants Cooperatively Learn Prompts Instead of Models -- Federated Learning in Age of Foundation Model","created":"2022-08-24","cited_by_count":134},{"id":"2404.19245","title":"HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning","created":"2024-04-30","cited_by_count":123},{"id":"2401.06432","title":"Heterogeneous LoRA for Federated Fine-tuning of On-Device Foundation Models","created":"2024-01-12","cited_by_count":116},{"id":"2106.06047","title":"Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning","created":"2021-06-10","cited_by_count":111},{"id":"2306.11867","title":"Personalized Federated Learning with Feature Alignment and Classifier Collaboration","created":"2023-06-20","cited_by_count":97},{"id":"2402.16842","title":"Asymmetry in Low-Rank Adapters of Foundation Models","created":"2024-02-26","cited_by_count":86},{"id":"2406.17706","title":"FedBiOT: LLM Local Fine-tuning in Federated Learning without Full Model","created":"2024-06-25","cited_by_count":74},{"id":"2206.11488","title":"On the Importance and Applicability of Pre-Training for Federated Learning","created":"2022-06-23","cited_by_count":71},{"id":"2210.08090","title":"Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learning","created":"2022-10-14","cited_by_count":71},{"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":"2407.00952","title":"SplitLoRA: A Split Parameter-Efficient Fine-Tuning Framework for Large Language Models","created":"2024-07-01","cited_by_count":62},{"id":"2406.07925","title":"FDLoRA: Personalized Federated Learning of Large Language Model via Dual LoRA Tuning","created":"2024-06-12","cited_by_count":59},{"id":"2403.19211","title":"Dual-Personalizing Adapter for Federated Foundation Models","created":"2024-03-28","cited_by_count":55},{"id":"2403.00041","title":"Global and Local Prompts Cooperation via Optimal Transport for Federated Learning","created":"2024-02-29","cited_by_count":46},{"id":"2312.17493","title":"Differentially Private Low-Rank Adaptation of Large Language Model Using Federated Learning","created":"2023-12-29","cited_by_count":41},{"id":"2205.08576","title":"Label-Efficient Self-Supervised Federated Learning for Tackling Data Heterogeneity in Medical Imaging","created":"2022-05-17","cited_by_count":39},{"id":"2206.02291","title":"Pretrained Models for Multilingual Federated Learning","created":"2022-06-06","cited_by_count":30},{"id":"2405.09771","title":"Harmonizing Generalization and Personalization in Federated Prompt Learning","created":"2024-05-16","cited_by_count":27},{"id":"2310.01467","title":"FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models","created":"2023-10-02","cited_by_count":26},{"id":"2310.18285","title":"Unlocking the Potential of Prompt-Tuning in Bridging Generalized and Personalized Federated Learning","created":"2023-10-27","cited_by_count":20},{"id":"2408.12300","title":"Tackling Data Heterogeneity in Federated Learning via Loss Decomposition","created":"2024-08-22","cited_by_count":9},{"id":"2408.08699","title":"RBLA: Rank-Based-LoRA-Aggregation for Fine-tuning Heterogeneous Models in FLaaS","created":"2024-08-16","cited_by_count":8},{"id":"2403.10971","title":"Task-Aware Low-Rank Adaptation of Segment Anything Model","created":"2024-03-16","cited_by_count":6},{"id":"2308.11464","title":"Internal Cross-layer Gradients for Extending Homogeneity to Heterogeneity in Federated Learning","created":"2023-08-22","cited_by_count":5},{"id":"2407.17533","title":"SFPrompt: Communication-Efficient Split Federated Fine-Tuning for Large Pre-Trained Models over Resource-Limited Devices","created":"2024-07-24","cited_by_count":5},{"id":"2310.04412","title":"FedConv: Enhancing Convolutional Neural Networks for Handling Data Heterogeneity in Federated Learning","created":"2023-10-06","cited_by_count":2}],"next_cursor":null}