{"list":"other","total":66,"rows":[{"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":"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":"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":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"1908.07873","title":"Federated Learning: Challenges, Methods, and Future Directions","created":"2019-08-21","cited_by_count":1538},{"id":"1709.00029","title":"EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification","created":"2017-08-31","cited_by_count":1496},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"2304.12244","title":"WizardLM: Empowering large pre-trained language models to follow complex instructions","created":"2023-04-24","cited_by_count":1125},{"id":"2211.01910","title":"Large Language Models Are Human-Level Prompt Engineers","created":"2022-11-03","cited_by_count":1045},{"id":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"id":"2007.07481","title":"Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization","created":"2020-07-15","cited_by_count":906},{"id":"1909.06335","title":"Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification","created":"2019-09-13","cited_by_count":851},{"id":"1703.00121","title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","created":"2017-03-01","cited_by_count":797},{"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":"1708.03999","title":"ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models","created":"2017-08-14","cited_by_count":666},{"id":"2308.10792","title":"Instruction Tuning for Large Language Models: A Survey","created":"2023-08-21","cited_by_count":623},{"id":"2111.04263","title":"Federated Learning Based on Dynamic Regularization","created":"2021-11-08","cited_by_count":562},{"id":"2104.06599","title":"Learning How to Ask: Querying LMs with Mixtures of Soft Prompts","created":"2021-04-14","cited_by_count":377},{"id":"2205.12548","title":"RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning","created":"2022-05-25","cited_by_count":366},{"id":"2104.05240","title":"Factual Probing Is [MASK]: Learning vs. Learning to Recall","created":"2021-04-12","cited_by_count":291},{"id":"2203.17274","title":"Exploring Visual Prompts for Adapting Large-Scale Models","created":"2022-03-31","cited_by_count":274},{"id":"2201.03514","title":"Black-Box Tuning for Language-Model-as-a-Service","created":"2022-01-10","cited_by_count":256},{"id":"2105.11259","title":"PTR: Prompt Tuning with Rules for Text Classification","created":"2021-05-24","cited_by_count":238},{"id":"2109.04332","title":"PPT: Pre-trained Prompt Tuning for Few-shot Learning","created":"2021-09-09","cited_by_count":232},{"id":"2305.05644","title":"Towards Building the Federated GPT: Federated Instruction Tuning","created":"2023-05-09","cited_by_count":185},{"id":"2109.11797","title":"CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models","created":"2021-09-24","cited_by_count":183},{"id":"1301.1942","title":"Bayesian Optimization in a Billion Dimensions via Random Embeddings","created":"2013-01-09","cited_by_count":182},{"id":"1903.05987","title":"To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks","created":"2019-03-14","cited_by_count":167},{"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":"2205.10782","title":"Instruction Induction: From Few Examples to Natural Language Task Descriptions","created":"2022-05-22","cited_by_count":152},{"id":"2104.10201","title":"Bayesian Optimization is Superior to Random Search for Machine Learning Hyperparameter Tuning: Analysis of the Black-Box Optimization Challenge 2020","created":"2021-04-20","cited_by_count":148},{"id":"1805.11770","title":"AutoZOOM: Autoencoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networks","created":"2018-05-30","cited_by_count":137},{"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":"2109.10964","title":"Multi-Objective Bayesian Optimization over High-Dimensional Search Spaces","created":"2021-09-22","cited_by_count":87},{"id":"2204.12703","title":"Heterogeneous Ensemble Knowledge Transfer for Training Large Models in Federated Learning","created":"2022-04-27","cited_by_count":81},{"id":"2004.01442","title":"From Local SGD to Local Fixed-Point Methods for Federated Learning","created":"2020-04-03","cited_by_count":74},{"id":"2201.08531","title":"Black-box Prompt Learning for Pre-trained Language Models","created":"2022-01-21","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":"2303.14773","title":"BlackVIP: Black-Box Visual Prompting for Robust Transfer Learning","created":"2023-03-26","cited_by_count":70},{"id":"2306.03082","title":"InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models","created":"2023-06-05","cited_by_count":68},{"id":"1710.10551","title":"Stochastic Zeroth-order Optimization in High Dimensions","created":"2017-10-29","cited_by_count":63},{"id":"2102.12206","title":"PADA: Example-based Prompt Learning for on-the-fly Adaptation to Unseen Domains","created":"2021-02-24","cited_by_count":61},{"id":"2205.11200","title":"BBTv2: Towards a Gradient-Free Future with Large Language Models","created":"2022-05-23","cited_by_count":53},{"id":"2103.05032","title":"Convergence and Accuracy Trade-Offs in Federated Learning and Meta-Learning","created":"2021-03-08","cited_by_count":52},{"id":"2302.10429","title":"FedSpeed: Larger Local Interval, Less Communication Round, and Higher Generalization Accuracy","created":"2023-02-21","cited_by_count":49},{"id":"2210.10199","title":"Bayesian Optimization over Discrete and Mixed Spaces via Probabilistic Reparameterization","created":"2022-10-18","cited_by_count":37},{"id":"2309.05950","title":"Language Models as Black-Box Optimizers for Vision-Language Models","created":"2023-09-12","cited_by_count":36},{"id":"2102.07325","title":"Cross-modal Adversarial Reprogramming","created":"2021-02-15","cited_by_count":34},{"id":"2211.08025","title":"FedTune: A Deep Dive into Efficient Federated Fine-Tuning with Pre-trained Transformers","created":"2022-11-15","cited_by_count":33},{"id":"2206.02291","title":"Pretrained Models for Multilingual Federated Learning","created":"2022-06-06","cited_by_count":30},{"id":"2005.04828","title":"Pretraining Federated Text Models for Next Word Prediction","created":"2020-05-11","cited_by_count":22},{"id":"2303.08678","title":"Visual Prompt Based Personalized Federated Learning","created":"2023-03-15","cited_by_count":16},{"id":"2303.15234","title":"Prompt Tuning based Adapter for Vision-Language Model Adaption","created":"2023-03-24","cited_by_count":10},{"id":"2305.03518","title":"Black-box Prompt Tuning with Subspace Learning","created":"2023-05-04","cited_by_count":5},{"id":"2305.08088","title":"Make Prompt-based Black-Box Tuning Colorful: Boosting Model Generalization from Three Orthogonal Perspectives","created":"2023-05-14","cited_by_count":5}],"next_cursor":null}