{"list":"other","total":51,"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":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1606.09282","title":"Learning without Forgetting","created":"2016-06-29","cited_by_count":2496},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1606.04671","title":"Progressive Neural Networks","created":"2016-06-15","cited_by_count":1361},{"id":"1705.07115","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","created":"2017-05-19","cited_by_count":1358},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"id":"1807.11626","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","created":"2018-07-31","cited_by_count":943},{"id":"1802.01548","title":"Regularized Evolution for Image Classifier Architecture Search","created":"2018-02-05","cited_by_count":909},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"1802.03268","title":"Efficient Neural Architecture Search via Parameter Sharing","created":"2018-02-09","cited_by_count":837},{"id":"1711.02257","title":"GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks","created":"2017-11-07","cited_by_count":834},{"id":"1810.04650","title":"Multi-Task Learning as Multi-Objective Optimization","created":"2018-10-10","cited_by_count":821},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"1708.01547","title":"Lifelong Learning with Dynamically Expandable Networks","created":"2017-08-04","cited_by_count":694},{"id":"1705.08045","title":"Learning multiple visual domains with residual adapters","created":"2017-05-22","cited_by_count":557},{"id":"1711.09846","title":"Population Based Training of Neural Networks","created":"2017-11-27","cited_by_count":367},{"id":"1701.08734","title":"PathNet: Evolution Channels Gradient Descent in Super Neural Networks","created":"2017-01-30","cited_by_count":364},{"id":"1904.00310","title":"Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting","created":"2019-03-31","cited_by_count":302},{"id":"1511.05641","title":"Net2Net: Accelerating Learning via Knowledge Transfer","created":"2015-11-18","cited_by_count":250},{"id":"1907.12412","title":"ERNIE 2.0: A Continual Pre-training Framework for Language Understanding","created":"2019-07-29","cited_by_count":231},{"id":"1811.09751","title":"Characterizing and Avoiding Negative Transfer","created":"2018-11-24","cited_by_count":229},{"id":"1802.10592","title":"Model-Ensemble Trust-Region Policy Optimization","created":"2018-02-28","cited_by_count":219},{"id":"2112.10684","title":"Efficient Large Scale Language Modeling with Mixtures of Experts","created":"2021-12-20","cited_by_count":175},{"id":"1911.12423","title":"AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning","created":"2019-11-27","cited_by_count":160},{"id":"2209.01667","title":"A Review of Sparse Expert Models in Deep Learning","created":"2022-09-04","cited_by_count":148},{"id":"2209.15162","title":"Linearly Mapping from Image to Text Space","created":"2022-09-30","cited_by_count":142},{"id":"2009.00909","title":"A Survey on Negative Transfer","created":"2020-09-02","cited_by_count":122},{"id":"1705.04228","title":"Incremental Learning Through Deep Adaptation","created":"2017-05-11","cited_by_count":108},{"id":"2012.12631","title":"Efficient Continual Learning with Modular Networks and Task-Driven Priors","created":"2020-12-23","cited_by_count":88},{"id":"2203.12533","title":"Pathways: Asynchronous Distributed Dataflow for ML","created":"2022-03-23","cited_by_count":82},{"id":"1902.07816","title":"Mixture Models for Diverse Machine Translation: Tricks of the Trade","created":"2019-02-20","cited_by_count":77},{"id":"2103.13318","title":"Factors of Influence for Transfer Learning across Diverse Appearance Domains and Task Types","created":"2021-03-24","cited_by_count":54},{"id":"2106.03027","title":"Model Zoo: A Growing \"Brain\" That Learns Continually","created":"2021-06-06","cited_by_count":54},{"id":"2010.11545","title":"Online Structured Meta-learning","created":"2020-10-22","cited_by_count":27},{"id":"2205.12755","title":"An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems","created":"2022-05-25","cited_by_count":16},{"id":"2205.10937","title":"muNet: Evolving Pretrained Deep Neural Networks into Scalable Auto-tuning Multitask Systems","created":"2022-05-22","cited_by_count":12},{"id":"1811.09828","title":"Evolutionary-Neural Hybrid Agents for Architecture Search","created":"2018-11-24","cited_by_count":11},{"id":"2209.07326","title":"A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems","created":"2022-09-15","cited_by_count":9},{"id":"1902.05781","title":"Fast Task-Aware Architecture Inference","created":"2019-02-15","cited_by_count":7},{"id":"2209.14745","title":"A Multiagent Framework for the Asynchronous and Collaborative Extension of Multitask ML Systems","created":"2022-09-29","cited_by_count":2}],"next_cursor":null}