{"list":"other","total":66,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"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":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"1812.06127","title":"Federated Optimization in Heterogeneous Networks","created":"2018-12-14","cited_by_count":2987},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"2106.10199","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","created":"2021-06-18","cited_by_count":1245},{"id":"2007.07481","title":"Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization","created":"2020-07-15","cited_by_count":906},{"id":"1903.00161","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","created":"2019-03-01","cited_by_count":903},{"id":"2205.05638","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","created":"2022-05-11","cited_by_count":896},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"2402.01680","title":"Large Language Model based Multi-Agents: A Survey of Progress and Challenges","created":"2024-01-21","cited_by_count":769},{"id":"2402.09353","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","created":"2024-02-14","cited_by_count":758},{"id":"2403.14608","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","created":"2024-03-21","cited_by_count":656},{"id":"2003.10422","title":"A Unified Theory of Decentralized SGD with Changing Topology and Local Updates","created":"2020-03-23","cited_by_count":367},{"id":"2305.17333","title":"Fine-Tuning Language Models with Just Forward Passes","created":"2023-05-27","cited_by_count":345},{"id":"2002.07948","title":"Personalized Federated Learning: A Meta-Learning Approach","created":"2020-02-19","cited_by_count":312},{"id":"1910.00189","title":"The Non-IID Data Quagmire of Decentralized Machine Learning","created":"2019-10-01","cited_by_count":305},{"id":"2403.12313","title":"Improving LoRA in Privacy-preserving Federated Learning","created":"2024-03-18","cited_by_count":161},{"id":"1310.7063","title":"On the Convergence of Decentralized Gradient Descent","created":"2013-10-26","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":"2409.05976","title":"FLoRA: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptations","created":"2024-09-09","cited_by_count":146},{"id":"2401.06432","title":"Heterogeneous LoRA for Federated Fine-tuning of On-Device Foundation Models","created":"2024-01-12","cited_by_count":116},{"id":"2309.15943","title":"Scalable Multi-Robot Collaboration with Large Language Models: Centralized or Decentralized Systems?","created":"2023-09-27","cited_by_count":106},{"id":"2308.06522","title":"SLoRA: Federated Parameter Efficient Fine-Tuning of Language Models","created":"2023-08-12","cited_by_count":93},{"id":"2208.12268","title":"FedPrompt: Communication-Efficient and Privacy Preserving Prompt Tuning in Federated Learning","created":"2022-08-25","cited_by_count":91},{"id":"2306.01603","title":"Decentralized Federated Learning: A Survey and Perspective","created":"2023-06-02","cited_by_count":86},{"id":"2402.16842","title":"Asymmetry in Low-Rank Adapters of Foundation Models","created":"2024-02-26","cited_by_count":86},{"id":"2410.01463","title":"Selective Aggregation for Low-Rank Adaptation in Federated Learning","created":"2024-10-02","cited_by_count":80},{"id":"2212.10025","title":"When Federated Learning Meets Pre-trained Language Models' Parameter-Efficient Tuning Methods","created":"2022-12-20","cited_by_count":75},{"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":"2305.16742","title":"Parameter-Efficient Fine-Tuning without Introducing New Latency","created":"2023-05-26","cited_by_count":59},{"id":"2402.11867","title":"LoRA Training in the NTK Regime has No Spurious Local Minima","created":"2024-02-19","cited_by_count":48},{"id":"2308.10407","title":"Federated Learning for Connected and Automated Vehicles: A Survey of Existing Approaches and Challenges","created":"2023-08-21","cited_by_count":40},{"id":"1806.11536","title":"An Exact Quantized Decentralized Gradient Descent Algorithm","created":"2018-06-29","cited_by_count":36},{"id":"2301.01313","title":"Decentralized Gradient Tracking with Local Steps","created":"2023-01-03","cited_by_count":32},{"id":"2404.18848","title":"FeDeRA:Efficient Fine-tuning of Language Models in Federated Learning Leveraging Weight Decomposition","created":"2024-04-29","cited_by_count":26},{"id":"2406.05233","title":"Federated LoRA with Sparse Communication","created":"2024-06-07","cited_by_count":26},{"id":"2105.09080","title":"Accelerating Gossip SGD with Periodic Global Averaging","created":"2021-05-19","cited_by_count":25},{"id":"2410.22815","title":"Towards Robust and Efficient Federated Low-Rank Adaptation with Heterogeneous Clients","created":"2024-10-30","cited_by_count":22},{"id":"2410.18965","title":"On the Crucial Role of Initialization for Matrix Factorization","created":"2024-10-24","cited_by_count":15},{"id":"2410.08305","title":"Randomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptation","created":"2024-10-10","cited_by_count":13},{"id":"2402.11417","title":"LoRETTA: Low-Rank Economic Tensor-Train Adaptation for Ultra-Low-Parameter Fine-Tuning of Large Language Models","created":"2024-02-18","cited_by_count":12},{"id":"2410.13097","title":"Communication-Efficient and Tensorized Federated Fine-Tuning of Large Language Models","created":"2024-10-16","cited_by_count":12},{"id":"2211.09722","title":"Federated Multilingual Models for Medical Transcript Analysis","created":"2022-11-04","cited_by_count":11},{"id":"2305.13052","title":"Federated Learning of Medical Concepts Embedding using BEHRT","created":"2023-05-22","cited_by_count":11},{"id":"2409.02346","title":"Robust Federated Finetuning of Foundation Models via Alternating Minimization of LoRA","created":"2024-09-04","cited_by_count":11},{"id":"2405.00965","title":"Robust Decentralized Learning with Local Updates and Gradient Tracking","created":"2024-05-02","cited_by_count":8},{"id":"2411.15385","title":"Gradient dynamics for low-rank fine-tuning beyond kernels","created":"2024-11-23","cited_by_count":5},{"id":"2501.09822","title":"pFedWN: A Personalized Federated Learning Framework for D2D Wireless Networks with Heterogeneous Data","created":"2025-01-16","cited_by_count":3},{"id":"2310.09356","title":"Distributed Gradient Tracking Methods with Guarantees for Computing a Solution to Stochastic MPECs","created":"2023-10-13","cited_by_count":2},{"id":"2411.17876","title":"Leveraging Large Language Models and Topic Modeling for Toxicity Classification","created":"2024-11-26","cited_by_count":2}],"next_cursor":null}