{"list":"other","total":56,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"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":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"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":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"1812.01097","title":"LEAF: A Benchmark for Federated Settings","created":"2018-12-03","cited_by_count":792},{"id":"1705.10467","title":"Federated Multi-Task Learning","created":"2017-05-30","cited_by_count":672},{"id":"2012.04221","title":"Ditto: Fair and Robust Federated Learning Through Personalization","created":"2020-12-08","cited_by_count":672},{"id":"2006.08848","title":"Personalized Federated Learning with Moreau Envelopes","created":"2020-06-16","cited_by_count":618},{"id":"1706.06978","title":"Deep Interest Network for Click-Through Rate Prediction","created":"2017-06-21","cited_by_count":544},{"id":"2106.04647","title":"Compacter: Efficient Low-Rank Hypercomplex Adapter Layers","created":"2021-06-08","cited_by_count":460},{"id":"2105.10056","title":"Data-Free Knowledge Distillation for Heterogeneous Federated Learning","created":"2021-05-20","cited_by_count":383},{"id":"1809.03672","title":"Deep Interest Evolution Network for Click-Through Rate Prediction","created":"2018-09-11","cited_by_count":338},{"id":"2001.01523","title":"Think Locally, Act Globally: Federated Learning with Local and Global Representations","created":"2020-01-06","cited_by_count":325},{"id":"2002.10619","title":"Three Approaches for Personalization with Applications to Federated Learning","created":"2020-02-25","cited_by_count":325},{"id":"2112.06825","title":"VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks","created":"2021-12-13","cited_by_count":320},{"id":"2203.14940","title":"Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Model","created":"2022-03-28","cited_by_count":317},{"id":"2210.08823","title":"Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning","created":"2022-10-17","cited_by_count":294},{"id":"2106.04489","title":"Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks","created":"2021-06-08","cited_by_count":284},{"id":"1909.12488","title":"Improving Federated Learning Personalization via Model Agnostic Meta Learning","created":"2019-09-27","cited_by_count":269},{"id":"2106.05001","title":"No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data","created":"2021-06-09","cited_by_count":241},{"id":"2205.03340","title":"Prompt Distribution Learning","created":"2022-05-06","cited_by_count":235},{"id":"1802.01483","title":"Explicit Inductive Bias for Transfer Learning with Convolutional Networks","created":"2018-02-05","cited_by_count":227},{"id":"1702.05373","title":"EMNIST: an extension of MNIST to handwritten letters","created":"2017-02-17","cited_by_count":213},{"id":"2102.10407","title":"VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioning","created":"2021-02-20","cited_by_count":191},{"id":"2203.09249","title":"Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning","created":"2022-03-17","cited_by_count":172},{"id":"1811.08737","title":"SpotTune: Transfer Learning through Adaptive Fine-tuning","created":"2018-11-21","cited_by_count":168},{"id":"1802.07876","title":"Federated Meta-Learning with Fast Convergence and Efficient Communication","created":"2018-02-22","cited_by_count":155},{"id":"2105.11367","title":"FedScale: Benchmarking Model and System Performance of Federated Learning at Scale","created":"2021-05-24","cited_by_count":136},{"id":"2205.03993","title":"Layer-wised Model Aggregation for Personalized Federated Learning","created":"2022-05-09","cited_by_count":96},{"id":"2107.00358","title":"Cross-domain Few-shot Learning with Task-specific Adapters","created":"2021-07-01","cited_by_count":80},{"id":"2008.03371","title":"LotteryFL: Personalized and Communication-Efficient Federated Learning with Lottery Ticket Hypothesis on Non-IID Datasets","created":"2020-08-07","cited_by_count":60},{"id":"2203.10541","title":"Unsupervised Domain Adaptation for Nighttime Aerial Tracking","created":"2022-03-20","cited_by_count":56},{"id":"2204.03880","title":"CD$^2$-pFed: Cyclic Distillation-guided Channel Decoupling for Model Personalization in Federated Learning","created":"2022-04-08","cited_by_count":34},{"id":"2012.11842","title":"Personalized Adaptive Meta Learning for Cold-start User Preference Prediction","created":"2020-12-22","cited_by_count":15},{"id":"2211.01163","title":"On-Device Model Fine-Tuning with Label Correction in Recommender Systems","created":"2022-10-21","cited_by_count":2}],"next_cursor":null}