{"list":"other","total":53,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1510.03055","title":"A Diversity-Promoting Objective Function for Neural Conversation Models","created":"2015-10-11","cited_by_count":1077},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"1506.03099","title":"Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks","created":"2015-06-09","cited_by_count":803},{"id":"1511.06732","title":"Sequence Level Training with Recurrent Neural Networks","created":"2015-11-20","cited_by_count":576},{"id":"1612.00563","title":"Self-critical Sequence Training for Image Captioning","created":"2016-12-02","cited_by_count":547},{"id":"1611.08669","title":"Visual Dialog","created":"2016-11-26","cited_by_count":377},{"id":"1606.01541","title":"Deep Reinforcement Learning for Dialogue Generation","created":"2016-06-05","cited_by_count":288},{"id":"1907.00456","title":"Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog","created":"2019-06-30","cited_by_count":284},{"id":"1912.02315","title":"12-in-1: Multi-Task Vision and Language Representation Learning","created":"2019-12-05","cited_by_count":278},{"id":"1910.06764","title":"Stabilizing Transformers for Reinforcement Learning","created":"2019-10-13","cited_by_count":270},{"id":"1706.05125","title":"Deal or No Deal? End-to-End Learning for Negotiation Dialogues","created":"2017-06-16","cited_by_count":209},{"id":"2004.12651","title":"Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting","created":"2020-04-27","cited_by_count":170},{"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":"1512.07679","title":"Deep Reinforcement Learning in Large Discrete Action Spaces","created":"2015-12-24","cited_by_count":161},{"id":"1607.07086","title":"An Actor-Critic Algorithm for Sequence Prediction","created":"2016-07-24","cited_by_count":159},{"id":"1611.08481","title":"GuessWhat?! Visual object discovery through multi-modal dialogue","created":"2016-11-23","cited_by_count":113},{"id":"2010.02903","title":"Keep CALM and Explore: Language Models for Action Generation in Text-based Games","created":"2020-10-06","cited_by_count":108},{"id":"1611.02796","title":"Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control","created":"2016-11-09","cited_by_count":101},{"id":"2004.10450","title":"Trading Off Diversity and Quality in Natural Language Generation","created":"2020-04-22","cited_by_count":96},{"id":"2010.05848","title":"Human-centric Dialog Training via Offline Reinforcement Learning","created":"2020-10-12","cited_by_count":93},{"id":"1511.04636","title":"Deep Reinforcement Learning with a Natural Language Action Space","created":"2015-11-14","cited_by_count":88},{"id":"1907.01752","title":"On the Weaknesses of Reinforcement Learning for Neural Machine Translation","created":"2019-07-03","cited_by_count":82},{"id":"1809.02121","title":"Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning","created":"2018-09-06","cited_by_count":77},{"id":"1902.00183","title":"Learning Action Representations for Reinforcement Learning","created":"2019-02-01","cited_by_count":75},{"id":"1506.08941","title":"Language Understanding for Text-based Games Using Deep Reinforcement Learning","created":"2015-06-30","cited_by_count":71},{"id":"2005.07064","title":"Multi-agent Communication meets Natural Language: Synergies between Functional and Structural Language Learning","created":"2020-05-14","cited_by_count":66},{"id":"1912.05783","title":"CLOSURE: Assessing Systematic Generalization of CLEVR Models","created":"2019-12-12","cited_by_count":63},{"id":"1706.03850","title":"Adversarial Feature Matching for Text Generation","created":"2017-06-12","cited_by_count":58},{"id":"2003.12694","title":"Countering Language Drift with Seeded Iterated Learning","created":"2020-03-28","cited_by_count":57},{"id":"1603.06059","title":"Generating Natural Questions About an Image","created":"2016-03-19","cited_by_count":56},{"id":"1812.01628","title":"Playing Text-Adventure Games with Graph-Based Deep Reinforcement Learning","created":"2018-12-04","cited_by_count":53},{"id":"1903.03166","title":"CLEVR-Dialog: A Diagnostic Dataset for Multi-Round Reasoning in Visual Dialog","created":"2019-03-07","cited_by_count":44},{"id":"1902.01119","title":"The Natural Language of Actions","created":"2019-02-04","cited_by_count":28},{"id":"1909.07547","title":"Hierarchical Reinforcement Learning for Open-Domain Dialog","created":"2019-09-17","cited_by_count":27},{"id":"2012.13575","title":"Contextual Temperature for Language Modeling","created":"2020-12-25","cited_by_count":27},{"id":"1703.05423","title":"End-to-end optimization of goal-driven and visually grounded dialogue systems","created":"2017-03-15","cited_by_count":17},{"id":"1809.04157","title":"Heated-Up Softmax Embedding","created":"2018-09-11","cited_by_count":15},{"id":"1810.00912","title":"Visual Curiosity: Learning to Ask Questions to Learn Visual Recognition","created":"2018-10-01","cited_by_count":11},{"id":"2103.12777","title":"Unsupervised Contextual Paraphrase Generation using Lexical Control and Reinforcement Learning","created":"2021-03-23","cited_by_count":10},{"id":"1910.02078","title":"I'm sorry Dave, I'm afraid I can't do that, Deep Q-learning from forbidden action","created":"2019-10-04","cited_by_count":4}],"next_cursor":null}