{"list":"other","total":58,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1708.07747","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","created":"2017-08-25","cited_by_count":4349},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"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":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"1907.02189","title":"On the Convergence of FedAvg on Non-IID Data","created":"2019-07-04","cited_by_count":1229},{"id":"1606.04838","title":"Optimization Methods for Large-Scale Machine Learning","created":"2016-06-15","cited_by_count":1150},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120},{"id":"1807.05520","title":"Deep Clustering for Unsupervised Learning of Visual Features","created":"2018-07-15","cited_by_count":1028},{"id":"2007.07481","title":"Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization","created":"2020-07-15","cited_by_count":906},{"id":"1902.01046","title":"Towards Federated Learning at Scale: System Design","created":"2019-02-04","cited_by_count":832},{"id":"2306.01708","title":"TIES-Merging: Resolving Interference When Merging Models","created":"2023-06-02","cited_by_count":818},{"id":"1812.01097","title":"LEAF: A Benchmark for Federated Settings","created":"2018-12-03","cited_by_count":792},{"id":"2103.16257","title":"Model-Contrastive Federated Learning","created":"2021-03-30","cited_by_count":766},{"id":"2311.03099","title":"Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch","created":"2023-11-06","cited_by_count":694},{"id":"2006.07242","title":"Ensemble Distillation for Robust Model Fusion in Federated Learning","created":"2020-06-12","cited_by_count":682},{"id":"2006.08848","title":"Personalized Federated Learning with Moreau Envelopes","created":"2020-06-16","cited_by_count":618},{"id":"2006.04088","title":"An Efficient Framework for Clustered Federated Learning","created":"2020-06-07","cited_by_count":511},{"id":"1910.03581","title":"FedMD: Heterogenous Federated Learning via Model Distillation","created":"2019-10-08","cited_by_count":459},{"id":"1905.12022","title":"Bayesian Nonparametric Federated Learning of Neural Networks","created":"2019-05-28","cited_by_count":387},{"id":"2212.09849","title":"Dataless Knowledge Fusion by Merging Weights of Language Models","created":"2022-12-19","cited_by_count":387},{"id":"1903.03934","title":"Asynchronous Federated Optimization","created":"2019-03-10","cited_by_count":267},{"id":"2403.13187","title":"Evolutionary Optimization of Model Merging Recipes","created":"2024-03-19","cited_by_count":208},{"id":"2106.06639","title":"Federated Learning with Buffered Asynchronous Aggregation","created":"2021-06-11","cited_by_count":190},{"id":"2108.13323","title":"FedKD: Communication Efficient Federated Learning via Knowledge Distillation","created":"2021-08-30","cited_by_count":187},{"id":"2203.11751","title":"FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correction","created":"2022-03-22","cited_by_count":181},{"id":"2009.01974","title":"FedBE: Making Bayesian Model Ensemble Applicable to Federated Learning","created":"2020-09-04","cited_by_count":176},{"id":"2402.14800","title":"Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models","created":"2024-02-22","cited_by_count":146},{"id":"2010.13723","title":"Optimal Client Sampling for Federated Learning","created":"2020-10-26","cited_by_count":124},{"id":"2111.02862","title":"Parameterized Knowledge Transfer for Personalized Federated Learning","created":"2021-11-04","cited_by_count":109},{"id":"2001.09249","title":"TiFL: A Tier-based Federated Learning System","created":"2020-01-25","cited_by_count":96},{"id":"2206.07977","title":"Personalized Federated Learning via Variational Bayesian Inference","created":"2022-06-16","cited_by_count":68},{"id":"2010.05958","title":"FedAT: A High-Performance and Communication-Efficient Federated Learning System with Asynchronous Tiers","created":"2020-10-12","cited_by_count":64},{"id":"2310.05077","title":"FedFed: Feature Distillation against Data Heterogeneity in Federated Learning","created":"2023-10-08","cited_by_count":54},{"id":"2407.00945","title":"Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs","created":"2024-07-01","cited_by_count":53},{"id":"2312.05770","title":"FedASMU: Efficient Asynchronous Federated Learning with Dynamic Staleness-aware Model Update","created":"2023-12-10","cited_by_count":32},{"id":"2304.06947","title":"TimelyFL: Heterogeneity-aware Asynchronous Federated Learning with Adaptive Partial Training","created":"2023-04-14","cited_by_count":27},{"id":"2305.12557","title":"Confidence-aware Personalized Federated Learning via Variational Expectation Maximization","created":"2023-05-21","cited_by_count":17},{"id":"2407.18365","title":"FADAS: Towards Federated Adaptive Asynchronous Optimization","created":"2024-07-25","cited_by_count":10},{"id":"2306.14245","title":"FedSampling: A Better Sampling Strategy for Federated Learning","created":"2023-06-25","cited_by_count":8},{"id":"2303.05048","title":"Semi-Federated Learning for Collaborative Intelligence in Massive IoT Networks","created":"2023-03-09","cited_by_count":7},{"id":"2205.11044","title":"Personalized Federated Learning with Server-Side Information","created":"2022-05-23","cited_by_count":6},{"id":"2404.02241","title":"Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better","created":"2024-04-02","cited_by_count":6},{"id":"2405.00017","title":"Queuing dynamics of asynchronous Federated Learning","created":"2024-02-12","cited_by_count":6},{"id":"2011.06892","title":"Hybrid Federated and Centralized Learning","created":"2020-11-13","cited_by_count":5},{"id":"2202.09848","title":"Personalized Federated Learning with Exact Stochastic Gradient Descent","created":"2022-02-20","cited_by_count":4}],"next_cursor":null}