{"list":"other","total":52,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"2305.11206","title":"LIMA: Less Is More for Alignment","created":"2023-05-18","cited_by_count":1100},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"1903.00161","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","created":"2019-03-01","cited_by_count":903},{"id":"1912.11370","title":"Big Transfer (BiT): General Visual Representation Learning","created":"2019-12-24","cited_by_count":769},{"id":"1812.05159","title":"An Empirical Study of Example Forgetting during Deep Neural Network Learning","created":"2018-12-12","cited_by_count":678},{"id":"2107.07075","title":"Deep Learning on a Data Diet: Finding Important Examples Early in Training","created":"2021-07-15","cited_by_count":533},{"id":"2006.05929","title":"Dataset Condensation with Gradient Matching","created":"2020-06-10","cited_by_count":516},{"id":"2208.10442","title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","created":"2022-08-22","cited_by_count":511},{"id":"2203.11932","title":"Dataset Distillation by Matching Training Trajectories","created":"2022-03-22","cited_by_count":442},{"id":"2110.04181","title":"Dataset Condensation with Distribution Matching","created":"2021-10-08","cited_by_count":365},{"id":"2201.10005","title":"Text and Code Embeddings by Contrastive Pre-Training","created":"2022-01-24","cited_by_count":361},{"id":"1906.11829","title":"Selection via Proxy: Efficient Data Selection for Deep Learning","created":"2019-06-26","cited_by_count":339},{"id":"2102.08259","title":"Dataset Condensation with Differentiable Siamese Augmentation","created":"2021-02-16","cited_by_count":291},{"id":"2103.11886","title":"DeepViT: Towards Deeper Vision Transformer","created":"2021-03-22","cited_by_count":289},{"id":"2103.00123","title":"GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Training","created":"2021-02-27","cited_by_count":274},{"id":"2012.10630","title":"GLISTER: Generalization based Data Subset Selection for Efficient and Robust Learning","created":"2020-12-19","cited_by_count":226},{"id":"2205.14959","title":"Dataset Condensation via Efficient Synthetic-Data Parameterization","created":"2022-05-30","cited_by_count":188},{"id":"1802.09841","title":"Adversarial Active Learning for Deep Networks: a Margin Based Approach","created":"2018-02-27","cited_by_count":158},{"id":"2109.03764","title":"Active Learning by Acquiring Contrastive Examples","created":"2021-09-08","cited_by_count":156},{"id":"2204.08499","title":"DeepCore: A Comprehensive Library for Coreset Selection in Deep Learning","created":"2022-04-18","cited_by_count":147},{"id":"2204.12451","title":"Understanding The Robustness in Vision Transformers","created":"2022-04-26","cited_by_count":144},{"id":"2211.11004","title":"Minimizing the Accumulated Trajectory Error to Improve Dataset Distillation","created":"2022-11-20","cited_by_count":142},{"id":"2008.05723","title":"Contextual Diversity for Active Learning","created":"2020-08-13","cited_by_count":139},{"id":"2302.14416","title":"DREAM: Efficient Dataset Distillation by Representative Matching","created":"2023-02-28","cited_by_count":94},{"id":"2303.04947","title":"InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning","created":"2023-03-08","cited_by_count":90},{"id":"2006.15412","title":"Submodular Combinatorial Information Measures with Applications in Machine Learning","created":"2020-06-27","cited_by_count":88},{"id":"2211.13976","title":"Expanding Small-Scale Datasets with Guided Imagination","created":"2022-11-25","cited_by_count":62},{"id":"2306.04757","title":"INSTRUCTEVAL: Towards Holistic Evaluation of Instruction-Tuned Large Language Models","created":"2023-06-07","cited_by_count":62},{"id":"2303.04707","title":"DiM: Distilling Dataset into Generative Model","created":"2023-03-08","cited_by_count":46},{"id":"1311.2106","title":"Submodular Optimization with Submodular Cover and Submodular Knapsack Constraints","created":"2013-11-08","cited_by_count":41},{"id":"1910.13540","title":"Small-GAN: Speeding Up GAN Training Using Core-sets","created":"2019-10-29","cited_by_count":41},{"id":"2107.06869","title":"Core-set Sampling for Efficient Neural Architecture Search","created":"2021-07-08","cited_by_count":23},{"id":"2011.00981","title":"Coresets for Regressions with Panel Data","created":"2020-11-02","cited_by_count":8}],"next_cursor":null}