{"list":"other","total":58,"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":"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":"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":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"1812.06127","title":"Federated Optimization in Heterogeneous Networks","created":"2018-12-14","cited_by_count":2987},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"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":"1906.08935","title":"Deep Leakage from Gradients","created":"2019-06-21","cited_by_count":1021},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"2005.00247","title":"AdapterFusion: Non-Destructive Task Composition for Transfer Learning","created":"2020-05-01","cited_by_count":788},{"id":"2110.07602","title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks","created":"2021-10-14","cited_by_count":689},{"id":"2004.02984","title":"MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices","created":"2020-04-06","cited_by_count":482},{"id":"2007.07779","title":"AdapterHub: A Framework for Adapting Transformers","created":"2020-07-15","cited_by_count":444},{"id":"1804.05271","title":"Adaptive Federated Learning in Resource Constrained Edge Computing Systems","created":"2018-04-14","cited_by_count":409},{"id":"1804.08333","title":"Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge","created":"2018-04-23","cited_by_count":352},{"id":"2305.17333","title":"Fine-Tuning Language Models with Just Forward Passes","created":"2023-05-27","cited_by_count":345},{"id":"1705.08741","title":"Train longer, generalize better: closing the generalization gap in large batch training of neural networks","created":"2017-05-24","cited_by_count":279},{"id":"2212.13345","title":"The Forward-Forward Algorithm: Some Preliminary Investigations","created":"2022-12-27","cited_by_count":266},{"id":"2004.04037","title":"DynaBERT: Dynamic BERT with Adaptive Width and Depth","created":"2020-04-08","cited_by_count":251},{"id":"2004.02178","title":"FastBERT: a Self-distilling BERT with Adaptive Inference Time","created":"2020-04-05","cited_by_count":226},{"id":"2102.13451","title":"FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout","created":"2021-02-26","cited_by_count":192},{"id":"2305.07027","title":"EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention","created":"2023-05-11","cited_by_count":172},{"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":"2106.13353","title":"Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models","created":"2021-06-24","cited_by_count":139},{"id":"2105.11367","title":"FedScale: Benchmarking Model and System Performance of Federated Learning at Scale","created":"2021-05-24","cited_by_count":136},{"id":"2004.04314","title":"Client Selection and Bandwidth Allocation in Wireless Federated Learning Networks: A Long-Term Perspective","created":"2020-04-09","cited_by_count":103},{"id":"2208.12268","title":"FedPrompt: Communication-Efficient and Privacy Preserving Prompt Tuning in Federated Learning","created":"2022-08-25","cited_by_count":91},{"id":"2104.08815","title":"FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Tasks","created":"2021-04-18","cited_by_count":85},{"id":"2306.15546","title":"When Foundation Model Meets Federated Learning: Motivations, Challenges, and Future Directions","created":"2023-06-27","cited_by_count":84},{"id":"1908.01580","title":"The HSIC Bottleneck: Deep Learning without Back-Propagation","created":"2019-08-05","cited_by_count":77},{"id":"1806.08054","title":"Error Compensated Quantized SGD and its Applications to Large-scale Distributed Optimization","created":"2018-06-21","cited_by_count":76},{"id":"2202.08587","title":"Gradients without Backpropagation","created":"2022-02-17","cited_by_count":73},{"id":"2210.03310","title":"Scaling Forward Gradient With Local Losses","created":"2022-10-07","cited_by_count":65},{"id":"2103.06819","title":"TAG: Gradient Attack on Transformer-based Language Models","created":"2021-03-11","cited_by_count":63},{"id":"1904.10631","title":"Low-Memory Neural Network Training: A Technical Report","created":"2019-04-24","cited_by_count":57},{"id":"2202.08827","title":"LAMP: Extracting Text from Gradients with Language Model Priors","created":"2022-02-17","cited_by_count":54},{"id":"2205.11200","title":"BBTv2: Towards a Gradient-Free Future with Large Language Models","created":"2022-05-23","cited_by_count":53},{"id":"2201.01601","title":"FedBalancer: Data and Pace Control for Efficient Federated Learning on Heterogeneous Clients","created":"2022-01-05","cited_by_count":46},{"id":"2101.00787","title":"Device Sampling for Heterogeneous Federated Learning: Theory, Algorithms, and Implementation","created":"2021-01-04","cited_by_count":40},{"id":"2007.11622","title":"TinyTL: Reduce Activations, Not Trainable Parameters for Efficient On-Device Learning","created":"2020-07-22","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":"2305.12132","title":"Can Public Large Language Models Help Private Cross-device Federated Learning?","created":"2023-05-20","cited_by_count":30},{"id":"2106.13973","title":"Benchmarking Differential Privacy and Federated Learning for BERT Models","created":"2021-06-26","cited_by_count":28},{"id":"2302.14307","title":"GradMA: A Gradient-Memory-based Accelerated Federated Learning with Alleviated Catastrophic Forgetting","created":"2023-02-28","cited_by_count":27},{"id":"2205.10162","title":"FedAdapter: Efficient Federated Learning for Modern NLP","created":"2022-05-20","cited_by_count":25},{"id":"2102.06329","title":"Stragglers Are Not Disaster: A Hybrid Federated Learning Algorithm with Delayed Gradients","created":"2021-02-12","cited_by_count":13},{"id":"2301.12195","title":"BAFFLE: A Baseline of Backpropagation-Free Federated Learning","created":"2023-01-28","cited_by_count":12},{"id":"2006.08517","title":"The Limit of the Batch Size","created":"2020-06-15","cited_by_count":6},{"id":"2212.00192","title":"Towards Practical Few-shot Federated NLP","created":"2022-12-01","cited_by_count":5},{"id":"2302.06405","title":"An Optical XNOR-Bitcount Based Accelerator for Efficient Inference of Binary Neural Networks","created":"2023-02-03","cited_by_count":3}],"next_cursor":null}