{"list":"other","total":55,"rows":[{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"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":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"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":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1812.01754","title":"Moment Matching for Multi-Source Domain Adaptation","created":"2018-12-04","cited_by_count":1331},{"id":"1802.10026","title":"Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs","created":"2018-02-27","cited_by_count":588},{"id":"2002.06440","title":"Federated Learning with Matched Averaging","created":"2020-02-15","cited_by_count":564},{"id":"2111.04263","title":"Federated Learning Based on Dynamic Regularization","created":"2021-11-08","cited_by_count":562},{"id":"2209.04836","title":"Git Re-Basin: Merging Models modulo Permutation Symmetries","created":"2022-09-11","cited_by_count":471},{"id":"2403.03507","title":"GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection","created":"2024-03-06","cited_by_count":463},{"id":"1905.12022","title":"Bayesian Nonparametric Federated Learning of Neural Networks","created":"2019-05-28","cited_by_count":387},{"id":"1803.00885","title":"Essentially No Barriers in Neural Network Energy Landscape","created":"2018-03-02","cited_by_count":330},{"id":"2107.06917","title":"A Field Guide to Federated Optimization","created":"2021-07-14","cited_by_count":315},{"id":"2408.07666","title":"Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities","created":"2024-08-14","cited_by_count":254},{"id":"1702.03849","title":"Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysis","created":"2017-02-13","cited_by_count":243},{"id":"2003.00307","title":"Loss landscapes and optimization in over-parameterized non-linear systems and neural networks","created":"2020-02-29","cited_by_count":233},{"id":"2307.05695","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","created":"2023-07-11","cited_by_count":204},{"id":"2305.05644","title":"Towards Building the Federated GPT: Federated Instruction Tuning","created":"2023-05-09","cited_by_count":185},{"id":"2403.12313","title":"Improving LoRA in Privacy-preserving Federated Learning","created":"2024-03-18","cited_by_count":161},{"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":"2402.06954","title":"OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning","created":"2024-02-10","cited_by_count":128},{"id":"2311.08105","title":"DiLoCo: Distributed Low-Communication Training of Language Models","created":"2023-11-14","cited_by_count":121},{"id":"2402.03293","title":"Flora: Low-Rank Adapters Are Secretly Gradient Compressors","created":"2024-02-05","cited_by_count":108},{"id":"2106.14343","title":"High-probability Bounds for Non-Convex Stochastic Optimization with Heavy Tails","created":"2021-06-28","cited_by_count":80},{"id":"2010.01017","title":"Practical One-Shot Federated Learning for Cross-Silo Setting","created":"2020-10-02","cited_by_count":77},{"id":"1906.06247","title":"Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets","created":"2019-06-14","cited_by_count":63},{"id":"2205.02719","title":"Communication-Efficient Adaptive Federated Learning","created":"2022-05-05","cited_by_count":55},{"id":"2306.16504","title":"Momentum Benefits Non-IID Federated Learning Simply and Provably","created":"2023-06-28","cited_by_count":38},{"id":"2411.14961","title":"LoRA-FAIR: Federated LoRA Fine-Tuning with Aggregation and Initialization Refinement","created":"2024-11-22","cited_by_count":38},{"id":"2212.00974","title":"Faster Adaptive Federated Learning","created":"2022-12-02","cited_by_count":35},{"id":"2410.11289","title":"Subspace Optimization for Large Language Models with Convergence Guarantees","created":"2024-10-15","cited_by_count":34},{"id":"1704.02060","title":"Angle-Based Joint and Individual Variation Explained","created":"2017-04-07","cited_by_count":30},{"id":"2310.19103","title":"Proving Linear Mode Connectivity of Neural Networks via Optimal Transport","created":"2023-10-29","cited_by_count":25},{"id":"2503.12016","title":"A Survey on Federated Fine-tuning of Large Language Models","created":"2025-03-15","cited_by_count":24},{"id":"2308.00522","title":"Efficient Federated Learning via Local Adaptive Amended Optimizer with Linear Speedup","created":"2023-07-30","cited_by_count":23},{"id":"2207.08041","title":"Personalized PCA: Decoupling Shared and Unique Features","created":"2022-07-17","cited_by_count":17},{"id":"2510.27486","title":"FedAdamW: A Communication-Efficient Optimizer with Convergence and Generalization Guarantees for Federated Large Models","created":"2025-10-31","cited_by_count":15},{"id":"2012.14409","title":"Latent space models for multiplex networks with shared structure","created":"2020-12-28","cited_by_count":14},{"id":"2504.20437","title":"GaLore 2: Large-Scale LLM Pre-Training by Gradient Low-Rank Projection","created":"2025-04-29","cited_by_count":14},{"id":"2409.13155","title":"Convergence of Distributed Adaptive Optimization with Local Updates","created":"2024-09-20","cited_by_count":10},{"id":"2005.11890","title":"mvlearn: Multiview Machine Learning in Python","created":"2020-05-25","cited_by_count":7},{"id":"2501.09336","title":"Estimating shared subspace with AJIVE: the power and limitation of multiple data matrices","created":"2025-01-16","cited_by_count":7},{"id":"2510.17802","title":"Unbiased Gradient Low-Rank Projection","created":"2025-10-20","cited_by_count":7},{"id":"2402.09941","title":"FedLion: Faster Adaptive Federated Optimization with Fewer Communication","created":"2024-02-15","cited_by_count":6},{"id":"2501.14406","title":"Adaptive Rank Allocation for Federated Parameter-Efficient Fine-Tuning of Language Models","created":"2025-01-24","cited_by_count":4},{"id":"2302.06103","title":"FedDA: Faster Framework of Local Adaptive Gradient Methods via Restarted Dual Averaging","created":"2023-02-13","cited_by_count":2}],"next_cursor":null}