{"list":"other","total":64,"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":"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":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1708.07747","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","created":"2017-08-25","cited_by_count":4349},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1912.04977","title":"Advances and Open Problems in Federated Learning","created":"2019-12-10","cited_by_count":3046},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"1908.07873","title":"Federated Learning: Challenges, Methods, and Future Directions","created":"2019-08-21","cited_by_count":1538},{"id":"1610.05492","title":"Federated Learning: Strategies for Improving Communication Efficiency","created":"2016-10-18","cited_by_count":1475},{"id":"1911.02685","title":"A Comprehensive Survey on Transfer Learning","created":"2019-11-07","cited_by_count":1160},{"id":"2406.12793","title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","created":"2024-06-18","cited_by_count":1121},{"id":"1904.05068","title":"Relational Knowledge Distillation","created":"2019-04-10","cited_by_count":889},{"id":"1902.01046","title":"Towards Federated Learning at Scale: System Design","created":"2019-02-04","cited_by_count":832},{"id":"1910.10699","title":"Contrastive Representation Distillation","created":"2019-10-23","cited_by_count":748},{"id":"1705.10467","title":"Federated Multi-Task Learning","created":"2017-05-30","cited_by_count":672},{"id":"1912.00818","title":"Federated Learning with Personalization Layers","created":"2019-12-02","cited_by_count":541},{"id":"2103.00710","title":"Towards Personalized Federated Learning","created":"2021-03-01","cited_by_count":464},{"id":"2110.06500","title":"Differentially Private Fine-tuning of Language Models","created":"2021-10-13","cited_by_count":400},{"id":"2203.08679","title":"Decoupled Knowledge Distillation","created":"2022-03-16","cited_by_count":388},{"id":"1707.08819","title":"A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets","created":"2017-07-27","cited_by_count":377},{"id":"2105.00243","title":"FedProto: Federated Prototype Learning across Heterogeneous Clients","created":"2021-05-01","cited_by_count":352},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319},{"id":"1909.12488","title":"Improving Federated Learning Personalization via Model Agnostic Meta Learning","created":"2019-09-27","cited_by_count":269},{"id":"2104.07914","title":"Federated Learning for Internet of Things: A Comprehensive Survey","created":"2021-04-16","cited_by_count":252},{"id":"1811.11479","title":"Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Data","created":"2018-11-28","cited_by_count":243},{"id":"2407.00079","title":"Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving","created":"2024-06-24","cited_by_count":196},{"id":"1802.07876","title":"Federated Meta-Learning with Fast Convergence and Efficient Communication","created":"2018-02-22","cited_by_count":155},{"id":"2005.11418","title":"FedPD: A Federated Learning Framework with Optimal Rates and Adaptivity to Non-IID Data","created":"2020-05-22","cited_by_count":144},{"id":"2209.10083","title":"Federated Learning from Pre-Trained Models: A Contrastive Learning Approach","created":"2022-09-21","cited_by_count":142},{"id":"1908.10400","title":"On the Convergence Theory of Gradient-Based Model-Agnostic Meta-Learning Algorithms","created":"2019-08-27","cited_by_count":132},{"id":"1511.06324","title":"Global Convergence of ADMM in Nonconvex Nonsmooth Optimization","created":"2015-11-18","cited_by_count":98},{"id":"1910.13067","title":"Federated Learning over Wireless Networks: Convergence Analysis and Resource Allocation","created":"2019-10-29","cited_by_count":94},{"id":"2102.02973","title":"Show, Attend and Distill:Knowledge Distillation via Attention-based Feature Matching","created":"2021-02-05","cited_by_count":79},{"id":"2302.04870","title":"Offsite-Tuning: Transfer Learning without Full Model","created":"2023-02-09","cited_by_count":78},{"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":"1410.1390","title":"Convergence Analysis of Alternating Direction Method of Multipliers for a Family of Nonconvex Problems","created":"2014-10-06","cited_by_count":64},{"id":"2310.10049","title":"FATE-LLM: A Industrial Grade Federated Learning Framework for Large Language Models","created":"2023-10-16","cited_by_count":63},{"id":"2111.07494","title":"Federated Learning for Internet of Things: Applications, Challenges, and Opportunities","created":"2021-11-15","cited_by_count":50},{"id":"1904.05514","title":"Mitigating Information Leakage in Image Representations: A Maximum Entropy Approach","created":"2019-04-11","cited_by_count":48},{"id":"2109.13236","title":"FedIPR: Ownership Verification for Federated Deep Neural Network Models","created":"2021-09-27","cited_by_count":36},{"id":"2307.01217","title":"FedCP: Separating Feature Information for Personalized Federated Learning via Conditional Policy","created":"2023-07-01","cited_by_count":36},{"id":"2204.07667","title":"Just Fine-tune Twice: Selective Differential Privacy for Large Language Models","created":"2022-04-15","cited_by_count":32},{"id":"2305.12132","title":"Can Public Large Language Models Help Private Cross-device Federated Learning?","created":"2023-05-20","cited_by_count":30},{"id":"2308.14363","title":"Mobile Foundation Model as Firmware","created":"2023-08-28","cited_by_count":25},{"id":"2311.17431","title":"Grounding Foundation Models through Federated Transfer Learning: A General Framework","created":"2023-11-29","cited_by_count":24},{"id":"2305.13865","title":"Selective Pre-training for Private Fine-tuning","created":"2023-05-23","cited_by_count":23},{"id":"2012.08677","title":"Inexact-ADMM Based Federated Meta-Learning for Fast and Continual Edge Learning","created":"2020-12-16","cited_by_count":22},{"id":"2403.15760","title":"An Upload-Efficient Scheme for Transferring Knowledge From a Server-Side Pre-trained Generator to Clients in Heterogeneous Federated Learning","created":"2024-03-23","cited_by_count":17},{"id":"1811.01484","title":"Quantifying the Reality Gap in Robotic Manipulation Tasks","created":"2018-11-05","cited_by_count":15},{"id":"1605.02408","title":"Structured Nonconvex and Nonsmooth Optimization: Algorithms and Iteration Complexity Analysis","created":"2016-05-09","cited_by_count":13},{"id":"2206.01838","title":"Differentially Private Model Compression","created":"2022-06-03","cited_by_count":13},{"id":"1904.03537","title":"Convex-Concave Backtracking for Inertial Bregman Proximal Gradient Algorithms in Non-Convex Optimization","created":"2019-04-06","cited_by_count":12},{"id":"2302.09042","title":"Privately Customizing Prefinetuning to Better Match User Data in Federated Learning","created":"2023-02-17","cited_by_count":12},{"id":"2111.05956","title":"Feature Generation for Long-tail Classification","created":"2021-11-10","cited_by_count":9},{"id":"1409.8033","title":"On the Convergence of Alternating Direction Lagrangian Methods for Nonconvex Structured Optimization Problems","created":"2014-09-29","cited_by_count":8},{"id":"1505.03063","title":"Convergence of multi-block Bregman ADMM for nonconvex composite problems","created":"2015-05-12","cited_by_count":8},{"id":"2006.07278","title":"Convergence for nonconvex ADMM, with applications to CT imaging","created":"2020-06-12","cited_by_count":8},{"id":"2311.00144","title":"Backdoor Threats from Compromised Foundation Models to Federated Learning","created":"2023-10-31","cited_by_count":8},{"id":"1410.8625","title":"Convergence of Bregman alternating direction method with multipliers for nonconvex composite problems","created":"2014-10-31","cited_by_count":7},{"id":"2008.02219","title":"Meta Continual Learning via Dynamic Programming","created":"2020-08-05","cited_by_count":4},{"id":"2208.02482","title":"Privacy Safe Representation Learning via Frequency Filtering Encoder","created":"2022-08-04","cited_by_count":1}],"next_cursor":null}