{"list":"other","total":61,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"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":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120},{"id":"1604.06174","title":"Training Deep Nets with Sublinear Memory Cost","created":"2016-04-21","cited_by_count":848},{"id":"2012.13255","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","created":"2020-12-22","cited_by_count":671},{"id":"1705.09056","title":"Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent","created":"2017-05-25","cited_by_count":502},{"id":"2403.03507","title":"GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection","created":"2024-03-06","cited_by_count":463},{"id":"1804.08838","title":"Measuring the Intrinsic Dimension of Objective Landscapes","created":"2018-04-24","cited_by_count":370},{"id":"2305.17333","title":"Fine-Tuning Language Models with Just Forward Passes","created":"2023-05-27","cited_by_count":345},{"id":"2101.06840","title":"ZeRO-Offload: Democratizing Billion-Scale Model Training","created":"2021-01-18","cited_by_count":341},{"id":"1502.04759","title":"Coordinate Descent Algorithms","created":"2015-02-17","cited_by_count":219},{"id":"2307.05695","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","created":"2023-07-11","cited_by_count":204},{"id":"2402.17193","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","created":"2024-02-27","cited_by_count":204},{"id":"1905.03817","title":"On the Linear Speedup Analysis of Communication Efficient Momentum SGD for Distributed Non-Convex Optimization","created":"2019-05-09","cited_by_count":180},{"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":"2406.16793","title":"Adam-mini: Use Fewer Learning Rates To Gain More","created":"2024-06-24","cited_by_count":137},{"id":"2306.09782","title":"Full Parameter Fine-tuning for Large Language Models with Limited Resources","created":"2023-06-16","cited_by_count":134},{"id":"2401.06432","title":"Heterogeneous LoRA for Federated Fine-tuning of On-Device Foundation Models","created":"2024-01-12","cited_by_count":116},{"id":"1812.11446","title":"Greedy Layerwise Learning Can Scale to ImageNet","created":"2018-12-29","cited_by_count":115},{"id":"2106.06047","title":"Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning","created":"2021-06-10","cited_by_count":111},{"id":"1805.11454","title":"Distributed Stochastic Gradient Tracking Methods","created":"2018-05-25","cited_by_count":106},{"id":"2208.12268","title":"FedPrompt: Communication-Efficient and Privacy Preserving Prompt Tuning in Federated Learning","created":"2022-08-25","cited_by_count":91},{"id":"1702.08704","title":"Optimal algorithms for smooth and strongly convex distributed optimization in networks","created":"2017-02-28","cited_by_count":83},{"id":"2401.04151","title":"Chain of LoRA: Efficient Fine-tuning of Language Models via Residual Learning","created":"2024-01-08","cited_by_count":82},{"id":"2410.01463","title":"Selective Aggregation for Low-Rank Adaptation in Federated Learning","created":"2024-10-02","cited_by_count":80},{"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":"2102.04761","title":"Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data","created":"2021-02-09","cited_by_count":69},{"id":"2106.13673","title":"Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy","created":"2021-06-25","cited_by_count":69},{"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":"2312.06353","title":"Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytes","created":"2023-12-11","cited_by_count":55},{"id":"2302.04083","title":"Improving the Model Consistency of Decentralized Federated Learning","created":"2023-02-08","cited_by_count":45},{"id":"2012.13063","title":"Decentralized Federated Learning via Mutual Knowledge Transfer","created":"2020-12-24","cited_by_count":43},{"id":"1806.00291","title":"Optimal Algorithms for Non-Smooth Distributed Optimization in Networks","created":"2018-06-01","cited_by_count":41},{"id":"2304.14999","title":"Empirical Analysis of the Strengths and Weaknesses of PEFT Techniques for LLMs","created":"2023-04-28","cited_by_count":38},{"id":"2103.02051","title":"Cross-Gradient Aggregation for Decentralized Learning from Non-IID data","created":"2021-03-02","cited_by_count":33},{"id":"2206.02291","title":"Pretrained Models for Multilingual Federated Learning","created":"2022-06-06","cited_by_count":30},{"id":"1305.4723","title":"On the Complexity Analysis of Randomized Block-Coordinate Descent Methods","created":"2013-05-21","cited_by_count":21},{"id":"2310.01972","title":"Epidemic Learning: Boosting Decentralized Learning with Randomized Communication","created":"2023-10-03","cited_by_count":21},{"id":"2209.15505","title":"Momentum Tracking: Momentum Acceleration for Decentralized Deep Learning on Heterogeneous Data","created":"2022-09-30","cited_by_count":20},{"id":"2501.15361","title":"Decentralized Low-Rank Fine-Tuning of Large Language Models","created":"2025-01-26","cited_by_count":14},{"id":"2408.10774","title":"Flexora: Flexible Low Rank Adaptation for Large Language Models","created":"2024-08-20","cited_by_count":13},{"id":"2208.08490","title":"NET-FLEET: Achieving Linear Convergence Speedup for Fully Decentralized Federated Learning with Heterogeneous Data","created":"2022-08-17","cited_by_count":12},{"id":"2305.04792","title":"Global Update Tracking: A Decentralized Learning Algorithm for Heterogeneous Data","created":"2023-05-08","cited_by_count":12},{"id":"2401.15207","title":"HiFT: A Hierarchical Full Parameter Fine-Tuning Strategy","created":"2024-01-26","cited_by_count":12},{"id":"2405.00965","title":"Robust Decentralized Learning with Local Updates and Gradient Tracking","created":"2024-05-02","cited_by_count":8},{"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":"2409.06277","title":"Ferret: Federated Full-Parameter Tuning at Scale for Large Language Models","created":"2024-09-10","cited_by_count":6},{"id":"2503.23726","title":"PDSL: Privacy-Preserved Decentralized Stochastic Learning with Heterogeneous Data Distribution","created":"2025-03-31","cited_by_count":2},{"id":"2505.21382","title":"DeCAF: Decentralized Consensus-And-Factorization for Low-Rank Adaptation of Foundation Models","created":"2025-05-27","cited_by_count":2},{"id":"2411.00365","title":"ROSS: RObust decentralized Stochastic learning based on Shapley values","created":"2024-11-01","cited_by_count":1}],"next_cursor":null}