{"list":"other","total":62,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"1609.08144","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","created":"2016-09-26","cited_by_count":1475},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"2201.07207","title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","created":"2022-01-18","cited_by_count":1035},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"id":"1911.05507","title":"Compressive Transformers for Long-Range Sequence Modelling","created":"2019-11-13","cited_by_count":726},{"id":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661},{"id":"2106.02039","title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","created":"2021-06-03","cited_by_count":644},{"id":"1910.11856","title":"On the Cross-lingual Transferability of Monolingual Representations","created":"2019-10-25","cited_by_count":578},{"id":"1805.06370","title":"Progress & Compress: A scalable framework for continual learning","created":"2018-05-16","cited_by_count":520},{"id":"1912.01588","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","created":"2019-12-03","cited_by_count":483},{"id":"2008.02217","title":"Hopfield Networks is All You Need","created":"2020-07-16","cited_by_count":475},{"id":"1507.06527","title":"Deep Recurrent Q-Learning for Partially Observable MDPs","created":"2015-07-23","cited_by_count":465},{"id":"1910.06764","title":"Stabilizing Transformers for Reinforcement Learning","created":"2019-10-13","cited_by_count":270},{"id":"2006.04884","title":"On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines","created":"2020-06-08","cited_by_count":255},{"id":"2006.05987","title":"Revisiting Few-sample BERT Fine-tuning","created":"2020-06-10","cited_by_count":238},{"id":"1606.01164","title":"Dense Associative Memory for Pattern Recognition","created":"2016-06-03","cited_by_count":236},{"id":"2202.01771","title":"Pre-Trained Language Models for Interactive Decision-Making","created":"2022-02-03","cited_by_count":221},{"id":"1909.10893","title":"Recurrent Independent Mechanisms","created":"2019-09-24","cited_by_count":219},{"id":"1708.02182","title":"Regularizing and Optimizing LSTM Language Models","created":"2017-08-07","cited_by_count":205},{"id":"2010.03934","title":"Prioritized Level Replay","created":"2020-10-08","cited_by_count":198},{"id":"2103.05247","title":"Pretrained Transformers as Universal Computation Engines","created":"2021-03-09","cited_by_count":162},{"id":"1912.13283","title":"oLMpics -- On what Language Model Pre-training Captures","created":"2019-12-31","cited_by_count":161},{"id":"1906.07343","title":"Language as an Abstraction for Hierarchical Deep Reinforcement Learning","created":"2019-06-18","cited_by_count":138},{"id":"2002.12292","title":"RIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated Environments","created":"2020-02-27","cited_by_count":135},{"id":"2009.04416","title":"Phasic Policy Gradient","created":"2020-09-09","cited_by_count":123},{"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":"2110.01517","title":"Skill Induction and Planning with Latent Language","created":"2021-10-04","cited_by_count":99},{"id":"2110.11316","title":"CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP","created":"2021-10-21","cited_by_count":89},{"id":"2112.06598","title":"WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models","created":"2021-12-13","cited_by_count":89},{"id":"2201.12122","title":"Can Wikipedia Help Offline Reinforcement Learning?","created":"2022-01-28","cited_by_count":77},{"id":"1711.00482","title":"Learning with Latent Language","created":"2017-11-01","cited_by_count":75},{"id":"2005.09382","title":"Human Instruction-Following with Deep Reinforcement Learning via Transfer-Learning from Text","created":"2020-05-19","cited_by_count":59},{"id":"2009.01719","title":"Grounded Language Learning Fast and Slow","created":"2020-09-03","cited_by_count":54},{"id":"2007.13505","title":"Modern Hopfield Networks and Attention for Immune Repertoire Classification","created":"2020-07-16","cited_by_count":53},{"id":"2204.05080","title":"Semantic Exploration from Language Abstractions and Pretrained Representations","created":"2022-04-08","cited_by_count":51},{"id":"2202.08938","title":"Improving Intrinsic Exploration with Language Abstractions","created":"2022-02-17","cited_by_count":49},{"id":"2009.14108","title":"Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution","created":"2020-09-29","cited_by_count":36},{"id":"2105.08710","title":"Fast and Slow Learning of Recurrent Independent Mechanisms","created":"2021-05-18","cited_by_count":36},{"id":"2104.01655","title":"Efficient Transformers in Reinforcement Learning using Actor-Learner Distillation","created":"2021-04-04","cited_by_count":35},{"id":"2010.06498","title":"Cross-Domain Few-Shot Learning by Representation Fusion","created":"2020-10-13","cited_by_count":32},{"id":"2105.06548","title":"Not All Memories are Created Equal: Learning to Forget by Expiring","created":"2021-05-13","cited_by_count":32},{"id":"2012.01399","title":"Convergence Proof for Actor-Critic Methods Applied to PPO and RUDDER","created":"2020-12-02","cited_by_count":19},{"id":"2110.03501","title":"Pretrained Language Models are Symbolic Mathematics Solvers too!","created":"2021-10-07","cited_by_count":17},{"id":"2104.07219","title":"Multitasking Inhibits Semantic Drift","created":"2021-04-15","cited_by_count":8},{"id":"2107.12460","title":"Don't Sweep your Learning Rate under the Rug: A Closer Look at Cross-modal Transfer of Pretrained Transformers","created":"2021-07-26","cited_by_count":6},{"id":"2109.15101","title":"Compositional generalization in semantic parsing with pretrained transformers","created":"2021-09-30","cited_by_count":5},{"id":"1912.00871","title":"Solving Arithmetic Word Problems Automatically Using Transformer and Unambiguous Representations","created":"2019-12-02","cited_by_count":4}],"next_cursor":null}