{"list":"other","total":97,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"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":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"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":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"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":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1919},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"1812.01754","title":"Moment Matching for Multi-Source Domain Adaptation","created":"2018-12-04","cited_by_count":1331},{"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":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"id":"2304.12244","title":"WizardLM: Empowering large pre-trained language models to follow complex instructions","created":"2023-04-24","cited_by_count":1125},{"id":"1710.03077","title":"Deeper, Broader and Artier Domain Generalization","created":"2017-10-09","cited_by_count":986},{"id":"1809.05053","title":"XNLI: Evaluating Cross-lingual Sentence Representations","created":"2018-09-13","cited_by_count":915},{"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":"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":"2401.02385","title":"TinyLlama: An Open-Source Small Language Model","created":"2024-01-04","cited_by_count":618},{"id":"2104.05938","title":"QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization","created":"2021-04-13","cited_by_count":365},{"id":"2303.10512","title":"AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning","created":"2023-03-18","cited_by_count":357},{"id":"2012.07463","title":"Parameter-Efficient Transfer Learning with Diff Pruning","created":"2020-12-14","cited_by_count":352},{"id":"2010.01264","title":"HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients","created":"2020-10-03","cited_by_count":337},{"id":"2310.11454","title":"VeRA: Vector-based Random Matrix Adaptation","created":"2023-10-17","cited_by_count":300},{"id":"2210.08823","title":"Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning","created":"2022-10-17","cited_by_count":294},{"id":"1903.00089","title":"Massively Multilingual Neural Machine Translation","created":"2019-02-28","cited_by_count":246},{"id":"2210.07558","title":"DyLoRA: Parameter Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation","created":"2022-10-14","cited_by_count":233},{"id":"2004.01401","title":"XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation","created":"2020-04-03","cited_by_count":222},{"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":"2209.10083","title":"Federated Learning from Pre-Trained Models: A Contrastive Learning Approach","created":"2022-09-21","cited_by_count":142},{"id":"2208.11625","title":"PromptFL: Let Federated Participants Cooperatively Learn Prompts Instead of Models -- Federated Learning in Age of Foundation Model","created":"2022-08-24","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":"2106.08087","title":"CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark","created":"2021-06-15","cited_by_count":101},{"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":"2306.15546","title":"When Foundation Model Meets Federated Learning: Motivations, Challenges, and Future Directions","created":"2023-06-27","cited_by_count":84},{"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":"2406.17706","title":"FedBiOT: LLM Local Fine-tuning in Federated Learning without Full Model","created":"2024-06-25","cited_by_count":74},{"id":"2308.12305","title":"FedDAT: An Approach for Foundation Model Finetuning in Multi-Modal Heterogeneous Federated Learning","created":"2023-08-21","cited_by_count":60},{"id":"2403.19211","title":"Dual-Personalizing Adapter for Federated Foundation Models","created":"2024-03-28","cited_by_count":55},{"id":"2308.15367","title":"Efficient Model Personalization in Federated Learning via Client-Specific Prompt Generation","created":"2023-08-29","cited_by_count":54},{"id":"2305.11414","title":"Federated Foundation Models: Privacy-Preserving and Collaborative Learning for Large Models","created":"2023-05-19","cited_by_count":50},{"id":"2403.00041","title":"Global and Local Prompts Cooperation via Optimal Transport for Federated Learning","created":"2024-02-29","cited_by_count":46},{"id":"2304.03271","title":"Making AI Less \"Thirsty\": Uncovering and Addressing the Secret Water Footprint of AI Models","created":"2023-04-06","cited_by_count":44},{"id":"2310.13283","title":"pFedLoRA: Model-Heterogeneous Personalized Federated Learning with LoRA Tuning","created":"2023-10-20","cited_by_count":40},{"id":"2411.14961","title":"LoRA-FAIR: Federated LoRA Fine-Tuning with Aggregation and Initialization Refinement","created":"2024-11-22","cited_by_count":38},{"id":"2403.08506","title":"DiPrompT: Disentangled Prompt Tuning for Multiple Latent Domain Generalization in Federated Learning","created":"2024-03-11","cited_by_count":32},{"id":"2307.08925","title":"Integration of Large Language Models and Federated Learning","created":"2023-07-18","cited_by_count":31},{"id":"2211.07864","title":"Federated Adaptive Prompt Tuning for Multi-Domain Collaborative Learning","created":"2022-11-15","cited_by_count":29},{"id":"2409.15723","title":"Federated Large Language Models: Current Progress and Future Directions","created":"2024-09-24","cited_by_count":27},{"id":"2205.10162","title":"FedAdapter: Efficient Federated Learning for Modern NLP","created":"2022-05-20","cited_by_count":25},{"id":"2409.19610","title":"Federated Learning from Vision-Language Foundation Models: Theoretical Analysis and Method","created":"2024-09-29","cited_by_count":22},{"id":"2410.22815","title":"Towards Robust and Efficient Federated Low-Rank Adaptation with Heterogeneous Clients","created":"2024-10-30","cited_by_count":22},{"id":"2310.18285","title":"Unlocking the Potential of Prompt-Tuning in Bridging Generalized and Personalized Federated Learning","created":"2023-10-27","cited_by_count":20},{"id":"2311.11227","title":"FedRA: A Random Allocation Strategy for Federated Tuning to Unleash the Power of Heterogeneous Clients","created":"2023-11-19","cited_by_count":19},{"id":"2410.09432","title":"FedEx-LoRA: Exact Aggregation for Federated and Efficient Fine-Tuning of Foundation Models","created":"2024-10-12","cited_by_count":18},{"id":"2410.10114","title":"Mixture of Experts Made Personalized: Federated Prompt Learning for Vision-Language Models","created":"2024-10-14","cited_by_count":17},{"id":"2502.01755","title":"Robust Federated Finetuning of LLMs via Alternating Optimization of LoRA","created":"2025-02-03","cited_by_count":17},{"id":"2406.12844","title":"Synergizing Foundation Models and Federated Learning: A Survey","created":"2024-06-18","cited_by_count":14},{"id":"2503.11880","title":"FedALT: Federated Fine-Tuning through Adaptive Local Training with Rest-of-World LoRA","created":"2025-03-14","cited_by_count":13},{"id":"2210.01708","title":"Exploring Parameter-Efficient Fine-Tuning to Enable Foundation Models in Federated Learning","created":"2022-10-04","cited_by_count":11},{"id":"2104.12501","title":"Communication-Efficient and Personalized Federated Lottery Ticket Learning","created":"2021-04-26","cited_by_count":10},{"id":"2305.12449","title":"Communication Efficient Federated Learning for Multilingual Neural Machine Translation with Adapter","created":"2023-05-21","cited_by_count":8},{"id":"2411.00311","title":"C2A: Client-Customized Adaptation for Parameter-Efficient Federated Learning","created":"2024-11-01","cited_by_count":8},{"id":"2401.14678","title":"Prompt-enhanced Federated Content Representation Learning for Cross-domain Recommendation","created":"2024-01-26","cited_by_count":7},{"id":"2409.18222","title":"Trustworthy AI: Securing Sensitive Data in Large Language Models","created":"2024-09-26","cited_by_count":7},{"id":"2308.03275","title":"Adapter-based Selective Knowledge Distillation for Federated Multi-domain Meeting Summarization","created":"2023-08-07","cited_by_count":6},{"id":"2311.03615","title":"CAFE: Carbon-Aware Federated Learning in Geographically Distributed Data Centers","created":"2023-11-06","cited_by_count":6},{"id":"2410.07738","title":"Enhancing Federated Domain Adaptation with Multi-Domain Prototype-Based Federated Fine-Tuning","created":"2024-10-10","cited_by_count":6},{"id":"2503.03920","title":"Personalized Federated Fine-tuning for Heterogeneous Data: An Automatic Rank Learning Approach via Two-Level LoRA","created":"2025-03-05","cited_by_count":6},{"id":"2412.20004","title":"Adaptive Parameter-Efficient Federated Fine-Tuning on Heterogeneous Devices","created":"2024-12-28","cited_by_count":5},{"id":"2501.13985","title":"Pilot: Building the Federated Multimodal Instruction Tuning Framework","created":"2025-01-23","cited_by_count":5},{"id":"2405.17267","title":"FedHPL: Efficient Heterogeneous Federated Learning with Prompt Tuning and Logit Distillation","created":"2024-05-27","cited_by_count":3},{"id":"2306.13264","title":"FedSelect: Customized Selection of Parameters for Fine-Tuning during Personalized Federated Learning","created":"2023-06-23","cited_by_count":2},{"id":"2502.04387","title":"FedP$^2$EFT: Federated Learning to Personalize PEFT for Multilingual LLMs","created":"2025-02-05","cited_by_count":2}],"next_cursor":null}