{"list":"other","total":141,"rows":[{"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":"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"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":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"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":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"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":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154},{"id":"2003.00295","title":"Adaptive Federated Optimization","created":"2020-02-29","cited_by_count":1046},{"id":"1609.09106","title":"HyperNetworks","created":"2016-09-27","cited_by_count":1027},{"id":"1906.08935","title":"Deep Leakage from Gradients","created":"2019-06-21","cited_by_count":1021},{"id":"1807.00459","title":"How To Backdoor Federated Learning","created":"2018-07-02","cited_by_count":765},{"id":"2003.14053","title":"Inverting Gradients -- How easy is it to break privacy in federated learning?","created":"2020-03-31","cited_by_count":712},{"id":"1803.01498","title":"Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates","created":"2018-03-05","cited_by_count":711},{"id":"2006.07242","title":"Ensemble Distillation for Robust Model Fusion in Federated Learning","created":"2020-06-12","cited_by_count":682},{"id":"2012.13255","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","created":"2020-12-22","cited_by_count":671},{"id":"1906.01502","title":"How multilingual is Multilingual BERT?","created":"2019-06-04","cited_by_count":645},{"id":"2003.08119","title":"The Future of Digital Health with Federated Learning","created":"2020-03-18","cited_by_count":633},{"id":"2102.02079","title":"Federated Learning on Non-IID Data Silos: An Experimental Study","created":"2021-02-03","cited_by_count":568},{"id":"2111.04263","title":"Federated Learning Based on Dynamic Regularization","created":"2021-11-08","cited_by_count":562},{"id":"1911.00222","title":"Federated Learning with Differential Privacy: Algorithms and Performance Analysis","created":"2019-11-01","cited_by_count":536},{"id":"1911.11815","title":"Local Model Poisoning Attacks to Byzantine-Robust Federated Learning","created":"2019-11-26","cited_by_count":493},{"id":"1611.04558","title":"Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation","created":"2016-11-14","cited_by_count":469},{"id":"2305.19860","title":"A Survey on Large Language Models for Recommendation","created":"2023-05-31","cited_by_count":379},{"id":"1802.04633","title":"Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring","created":"2018-02-13","cited_by_count":357},{"id":"1909.13014","title":"FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantization","created":"2019-09-28","cited_by_count":356},{"id":"2012.13995","title":"FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping","created":"2020-12-27","cited_by_count":346},{"id":"2305.17333","title":"Fine-Tuning Language Models with Just Forward Passes","created":"2023-05-27","cited_by_count":345},{"id":"2010.01264","title":"HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients","created":"2020-10-03","cited_by_count":337},{"id":"2006.03677","title":"Visual Transformers: Token-based Image Representation and Processing for Computer Vision","created":"2020-06-05","cited_by_count":334},{"id":"2004.12088","title":"SplitFed: When Federated Learning Meets Split Learning","created":"2020-04-25","cited_by_count":310},{"id":"2007.13518","title":"FedML: A Research Library and Benchmark for Federated Machine Learning","created":"2020-07-27","cited_by_count":300},{"id":"2008.00401","title":"Multilingual Translation with Extensible Multilingual Pretraining and Finetuning","created":"2020-08-02","cited_by_count":287},{"id":"2201.03514","title":"Black-Box Tuning for Language-Model-as-a-Service","created":"2022-01-10","cited_by_count":256},{"id":"1811.11479","title":"Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Data","created":"2018-11-28","cited_by_count":243},{"id":"2303.14524","title":"Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender System","created":"2023-03-25","cited_by_count":242},{"id":"1909.12326","title":"Model Pruning Enables Efficient Federated Learning on Edge Devices","created":"2019-09-26","cited_by_count":222},{"id":"2005.09093","title":"Are All Languages Created Equal in Multilingual BERT?","created":"2020-05-18","cited_by_count":207},{"id":"1312.2139","title":"Optimal rates for zero-order convex optimization: the power of two function evaluations","created":"2013-12-07","cited_by_count":198},{"id":"2305.05644","title":"Towards Building the Federated GPT: Federated Instruction Tuning","created":"2023-05-09","cited_by_count":185},{"id":"2007.07682","title":"FetchSGD: Communication-Efficient Federated Learning with Sketching","created":"2020-07-15","cited_by_count":179},{"id":"2303.15647","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","created":"2023-03-28","cited_by_count":173},{"id":"2305.07001","title":"Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach","created":"2023-05-11","cited_by_count":168},{"id":"2012.06337","title":"Privacy and Robustness in Federated Learning: Attacks and Defenses","created":"2020-12-07","cited_by_count":166},{"id":"2006.06224","title":"A Primer on Zeroth-Order Optimization in Signal Processing and Machine Learning","created":"2020-06-11","cited_by_count":162},{"id":"2303.04360","title":"Does Synthetic Data Generation of LLMs Help Clinical Text Mining?","created":"2023-03-08","cited_by_count":154},{"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":"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":"2402.06954","title":"OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning","created":"2024-02-10","cited_by_count":128},{"id":"2112.02918","title":"When the Curious Abandon Honesty: Federated Learning Is Not Private","created":"2021-12-06","cited_by_count":127},{"id":"1912.10389","title":"Lessons from Archives: Strategies for Collecting Sociocultural Data in Machine Learning","created":"2019-12-22","cited_by_count":116},{"id":"2401.06432","title":"Heterogeneous LoRA for Federated Fine-tuning of On-Device Foundation Models","created":"2024-01-12","cited_by_count":116},{"id":"2212.14882","title":"ChatGPT Makes Medicine Easy to Swallow: An Exploratory Case Study on Simplified Radiology Reports","created":"2022-12-30","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":"2111.00197","title":"Backdoor Pre-trained Models Can Transfer to All","created":"2021-10-30","cited_by_count":86},{"id":"2302.08888","title":"Multimodal Federated Learning via Contrastive Representation Ensemble","created":"2023-02-17","cited_by_count":86},{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86},{"id":"2201.08135","title":"Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challenges","created":"2022-01-20","cited_by_count":84},{"id":"1901.09888","title":"Federated Collaborative Filtering for Privacy-Preserving Personalized Recommendation System","created":"2019-01-29","cited_by_count":79},{"id":"1912.12716","title":"Federated Variance-Reduced Stochastic Gradient Descent with Robustness to Byzantine Attacks","created":"2019-12-29","cited_by_count":79},{"id":"1909.09145","title":"Detailed comparison of communication efficiency of split learning and federated learning","created":"2019-09-18","cited_by_count":77},{"id":"2303.16129","title":"Unleashing the Power of Edge-Cloud Generative AI in Mobile Networks: A Survey of AIGC Services","created":"2023-03-28","cited_by_count":76},{"id":"2205.08514","title":"Recovering Private Text in Federated Learning of Language Models","created":"2022-05-17","cited_by_count":70},{"id":"2302.13485","title":"FedCLIP: Fast Generalization and Personalization for CLIP in Federated Learning","created":"2023-02-27","cited_by_count":70},{"id":"2305.18465","title":"Federated Learning of Gboard Language Models with Differential Privacy","created":"2023-05-29","cited_by_count":66},{"id":"2201.09531","title":"Communication-Efficient Stochastic Zeroth-Order Optimization for Federated Learning","created":"2022-01-24","cited_by_count":59},{"id":"2304.06632","title":"AI-Generated Content (AIGC): A Survey","created":"2023-03-26","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":"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":"2204.05011","title":"FederatedScope: A Flexible Federated Learning Platform for Heterogeneity","created":"2022-04-11","cited_by_count":53},{"id":"2312.16475","title":"Federated Continual Learning via Knowledge Fusion: A Survey","created":"2023-12-27","cited_by_count":53},{"id":"2305.11414","title":"Federated Foundation Models: Privacy-Preserving and Collaborative Learning for Large Models","created":"2023-05-19","cited_by_count":50},{"id":"2108.07792","title":"Federated Multi-Target Domain Adaptation","created":"2021-08-17","cited_by_count":44},{"id":"1911.06317","title":"Gradientless Descent: High-Dimensional Zeroth-Order Optimization","created":"2019-11-14","cited_by_count":43},{"id":"2303.16181","title":"Learning Federated Visual Prompt in Null Space for MRI Reconstruction","created":"2023-03-28","cited_by_count":40},{"id":"2008.07298","title":"WAFFLE: Watermarking in Federated Learning","created":"2020-08-17","cited_by_count":37},{"id":"2302.07173","title":"An Experimental Study of Byzantine-Robust Aggregation Schemes in Federated Learning","created":"2023-02-14","cited_by_count":32},{"id":"2403.08506","title":"DiPrompT: Disentangled Prompt Tuning for Multiple Latent Domain Generalization in Federated Learning","created":"2024-03-11","cited_by_count":32}],"next_cursor":"100"}