{"list":"other","total":57,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"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":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1306.0895","title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances","created":"2013-06-04","cited_by_count":2316},{"id":"1704.00028","title":"Improved Training of Wasserstein GANs","created":"2017-03-31","cited_by_count":2235},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2002.10957","title":"MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers","created":"2020-02-25","cited_by_count":1463},{"id":"1707.01083","title":"ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices","created":"2017-07-04","cited_by_count":1200},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"id":"1612.03928","title":"Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer","created":"2016-12-12","cited_by_count":1077},{"id":"1708.00055","title":"SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation","created":"2017-07-31","cited_by_count":1001},{"id":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"id":"1904.05068","title":"Relational Knowledge Distillation","created":"2019-04-10","cited_by_count":889},{"id":"1606.07947","title":"Sequence-Level Knowledge Distillation","created":"2016-06-25","cited_by_count":801},{"id":"1910.10699","title":"Contrastive Representation Distillation","created":"2019-10-23","cited_by_count":748},{"id":"1706.00384","title":"Deep Mutual Learning","created":"2017-06-01","cited_by_count":628},{"id":"1902.03393","title":"Improved Knowledge Distillation via Teacher Assistant","created":"2019-02-09","cited_by_count":573},{"id":"1907.09682","title":"Similarity-Preserving Knowledge Distillation","created":"2019-07-23","cited_by_count":516},{"id":"1908.09355","title":"Patient Knowledge Distillation for BERT Model Compression","created":"2019-08-25","cited_by_count":508},{"id":"1606.00709","title":"f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization","created":"2016-06-02","cited_by_count":506},{"id":"2004.02984","title":"MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices","created":"2020-04-06","cited_by_count":482},{"id":"1701.04862","title":"Towards Principled Methods for Training Generative Adversarial Networks","created":"2017-01-17","cited_by_count":464},{"id":"1912.08795","title":"Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion","created":"2019-12-18","cited_by_count":423},{"id":"1904.05835","title":"Variational Information Distillation for Knowledge Transfer","created":"2019-04-11","cited_by_count":324},{"id":"1706.00292","title":"Learning Generative Models with Sinkhorn Divergences","created":"2017-06-01","cited_by_count":314},{"id":"2202.01279","title":"PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts","created":"2022-02-02","cited_by_count":289},{"id":"1904.01802","title":"Correlation Congruence for Knowledge Distillation","created":"2019-04-03","cited_by_count":285},{"id":"1705.08848","title":"Joint Distribution Optimal Transportation for Domain Adaptation","created":"2017-05-24","cited_by_count":282},{"id":"1802.04977","title":"Paraphrasing Complex Network: Network Compression via Factor Transfer","created":"2018-02-14","cited_by_count":260},{"id":"1811.03233","title":"Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons","created":"2018-11-08","cited_by_count":238},{"id":"1803.10837","title":"Learning Deep Representations with Probabilistic Knowledge Transfer","created":"2018-03-28","cited_by_count":213},{"id":"1506.05439","title":"Learning with a Wasserstein Loss","created":"2015-06-17","cited_by_count":196},{"id":"2105.08919","title":"Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation","created":"2021-05-19","cited_by_count":134},{"id":"1904.09149","title":"Knowledge Distillation via Route Constrained Optimization","created":"2019-04-19","cited_by_count":75},{"id":"2106.04570","title":"BERT Learns to Teach: Knowledge Distillation with Meta Learning","created":"2021-06-08","cited_by_count":61},{"id":"2102.07650","title":"Learning Student-Friendly Teacher Networks for Knowledge Distillation","created":"2021-02-12","cited_by_count":60},{"id":"2207.11518","title":"Online Knowledge Distillation via Mutual Contrastive Learning for Visual Recognition","created":"2022-07-23","cited_by_count":36},{"id":"2005.00850","title":"ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation","created":"2020-05-02","cited_by_count":34},{"id":"2110.15094","title":"Mosaicking to Distill: Knowledge Distillation from Out-of-Domain Data","created":"2021-10-27","cited_by_count":32},{"id":"2003.03463","title":"Training Deep Energy-Based Models with f-Divergence Minimization","created":"2020-03-06","cited_by_count":29},{"id":"2302.13344","title":"Tailoring Language Generation Models under Total Variation Distance","created":"2023-02-26","cited_by_count":27},{"id":"2103.14473","title":"Distilling a Powerful Student Model via Online Knowledge Distillation","created":"2021-03-26","cited_by_count":22},{"id":"2110.07940","title":"Wasserstein Unsupervised Reinforcement Learning","created":"2021-10-15","cited_by_count":22},{"id":"2305.16958","title":"MixCE: Training Autoregressive Language Models by Mixing Forward and Reverse Cross-Entropies","created":"2023-05-26","cited_by_count":16},{"id":"2109.03075","title":"Knowledge Distillation Using Hierarchical Self-Supervision Augmented Distribution","created":"2021-09-07","cited_by_count":13},{"id":"2106.02835","title":"On the Role of Entropy-based Loss for Learning Causal Structures with Continuous Optimization","created":"2021-06-05","cited_by_count":5},{"id":"2204.11526","title":"Selective Cross-Task Distillation","created":"2022-04-25","cited_by_count":1}],"next_cursor":null}