{"list":"other","total":88,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"2010.03768","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","created":"2020-10-08","cited_by_count":1205},{"id":"1711.07280","title":"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments","created":"2017-11-20","cited_by_count":1027},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"1912.01734","title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","created":"2019-12-03","cited_by_count":783},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"2204.03162","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","created":"2022-04-07","cited_by_count":529},{"id":"1811.00491","title":"A Corpus for Reasoning About Natural Language Grounded in Photographs","created":"2018-11-01","cited_by_count":459},{"id":"2010.07954","title":"Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding","created":"2020-10-15","cited_by_count":414},{"id":"1611.08669","title":"Visual Dialog","created":"2016-11-26","cited_by_count":377},{"id":"1806.02724","title":"Speaker-Follower Models for Vision-and-Language Navigation","created":"2018-06-07","cited_by_count":340},{"id":"1606.03137","title":"Cooperative Inverse Reinforcement Learning","created":"2016-06-09","cited_by_count":300},{"id":"1907.04957","title":"Vision-and-Dialog Navigation","created":"2019-07-10","cited_by_count":250},{"id":"1711.02827","title":"Inverse Reward Design","created":"2017-11-08","cited_by_count":249},{"id":"2004.10151","title":"Experience Grounds Language","created":"2020-04-21","cited_by_count":242},{"id":"1811.12354","title":"Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments","created":"2018-11-29","cited_by_count":239},{"id":"1301.3836","title":"The Complexity of Decentralized Control of Markov Decision Processes","created":"2013-01-16","cited_by_count":231},{"id":"1912.03098","title":"Connecting Vision and Language with Localized Narratives","created":"2019-12-06","cited_by_count":226},{"id":"2210.13312","title":"Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs","created":"2022-10-24","cited_by_count":220},{"id":"1706.05125","title":"Deal or No Deal? End-to-End Learning for Negotiation Dialogues","created":"2017-06-16","cited_by_count":209},{"id":"1906.06725","title":"Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good","created":"2019-06-16","cited_by_count":209},{"id":"2208.03188","title":"BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage","created":"2022-08-05","cited_by_count":198},{"id":"2006.02419","title":"Emergent Multi-Agent Communication in the Deep Learning Era","created":"2020-06-03","cited_by_count":170},{"id":"1909.05398","title":"Interactive Fiction Games: A Colossal Adventure","created":"2019-09-11","cited_by_count":168},{"id":"2202.06935","title":"Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text","created":"2022-02-14","cited_by_count":155},{"id":"1906.03926","title":"A Survey of Reinforcement Learning Informed by Natural Language","created":"2019-06-10","cited_by_count":154},{"id":"2110.08176","title":"Collaborating with Humans without Human Data","created":"2021-10-15","cited_by_count":142},{"id":"2209.15162","title":"Linearly Mapping from Image to Text Space","created":"2022-09-30","cited_by_count":142},{"id":"1903.03094","title":"Learning to Speak and Act in a Fantasy Text Adventure Game","created":"2019-03-07","cited_by_count":122},{"id":"2002.04833","title":"Reward-rational (implicit) choice: A unifying formalism for reward learning","created":"2020-02-12","cited_by_count":120},{"id":"1611.08481","title":"GuessWhat?! Visual object discovery through multi-modal dialogue","created":"2016-11-23","cited_by_count":113},{"id":"2102.05169","title":"Decontextualization: Making Sentences Stand-Alone","created":"2021-02-09","cited_by_count":102},{"id":"2112.05253","title":"MAGMA -- Multimodal Augmentation of Generative Models through Adapter-based Finetuning","created":"2021-12-09","cited_by_count":85},{"id":"2004.03066","title":"Are Natural Language Inference Models IMPPRESsive? Learning IMPlicature and PRESupposition","created":"2020-04-07","cited_by_count":77},{"id":"1910.03655","title":"Executing Instructions in Situated Collaborative Interactions","created":"2019-10-08","cited_by_count":69},{"id":"1604.00562","title":"Reasoning About Pragmatics with Neural Listeners and Speakers","created":"2016-04-02","cited_by_count":68},{"id":"1811.01458","title":"Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning","created":"2018-11-04","cited_by_count":68},{"id":"1704.05579","title":"A Large Self-Annotated Corpus for Sarcasm","created":"2017-04-19","cited_by_count":64},{"id":"2210.14986","title":"The Goldilocks of Pragmatic Understanding: Fine-Tuning Strategy Matters for Implicature Resolution by LLMs","created":"2022-10-26","cited_by_count":58},{"id":"1703.10186","title":"Colors in Context: A Pragmatic Neural Model for Grounded Language Understanding","created":"2017-03-29","cited_by_count":57},{"id":"1711.04987","title":"Unified Pragmatic Models for Generating and Following Instructions","created":"2017-11-14","cited_by_count":55},{"id":"2210.10606","title":"DALLE-2 is Seeing Double: Flaws in Word-to-Concept Mapping in Text2Image Models","created":"2022-10-19","cited_by_count":51},{"id":"2204.02515","title":"Inferring Rewards from Language in Context","created":"2022-04-05","cited_by_count":50},{"id":"1906.01530","title":"The PhotoBook Dataset: Building Common Ground through Visually-Grounded Dialogue","created":"2019-06-04","cited_by_count":46},{"id":"2101.10504","title":"On the Evaluation of Vision-and-Language Navigation Instructions","created":"2021-01-26","cited_by_count":45},{"id":"1606.02447","title":"Learning Language Games through Interaction","created":"2016-06-08","cited_by_count":43},{"id":"1701.02870","title":"Context-aware Captions from Context-agnostic Supervision","created":"2017-01-11","cited_by_count":43},{"id":"2109.08828","title":"Perspective-taking and Pragmatics for Generating Empathetic Responses Focused on Emotion Causes","created":"2021-09-18","cited_by_count":43},{"id":"1804.05417","title":"Pragmatically Informative Image Captioning with Character-Level Inference","created":"2018-04-15","cited_by_count":42},{"id":"2007.14435","title":"Towards Ecologically Valid Research on Language User Interfaces","created":"2020-07-28","cited_by_count":42},{"id":"1907.03399","title":"A Natural Language Corpus of Common Grounding under Continuous and Partially-Observable Context","created":"2019-07-08","cited_by_count":35},{"id":"1912.07199","title":"Characterizing the dynamics of learning in repeated reference games","created":"2019-12-16","cited_by_count":34},{"id":"1904.01301","title":"Pragmatically Informative Text Generation","created":"2019-04-02","cited_by_count":32},{"id":"1809.04640","title":"Jump to better conclusions: SCAN both left and right","created":"2018-09-12","cited_by_count":29},{"id":"2104.05857","title":"From partners to populations: A hierarchical Bayesian account of coordination and convention","created":"2021-04-12","cited_by_count":27},{"id":"2005.00908","title":"Clue: Cross-modal Coherence Modeling for Caption Generation","created":"2020-05-02","cited_by_count":24},{"id":"1910.02822","title":"A mathematical theory of cooperative communication","created":"2019-10-07","cited_by_count":23},{"id":"2109.06987","title":"NOPE: A Corpus of Naturally-Occurring Presuppositions in English","created":"2021-09-14","cited_by_count":23},{"id":"1704.06956","title":"Naturalizing a Programming Language via Interactive Learning","created":"2017-04-23","cited_by_count":20},{"id":"1907.05084","title":"MeetUp! A Corpus of Joint Activity Dialogues in a Visual Environment","created":"2019-07-11","cited_by_count":19},{"id":"2005.06641","title":"A Rate-Distortion view of human pragmatic reasoning","created":"2020-05-13","cited_by_count":19},{"id":"2108.04812","title":"Continual Learning for Grounded Instruction Generation by Observing Human Following Behavior","created":"2021-08-10","cited_by_count":19},{"id":"1910.14254","title":"Harnessing the linguistic signal to predict scalar inferences","created":"2019-10-31","cited_by_count":17},{"id":"2004.14451","title":"Pragmatic Issue-Sensitive Image Captioning","created":"2020-04-29","cited_by_count":15},{"id":"2007.05060","title":"Program Synthesis with Pragmatic Communication","created":"2020-07-09","cited_by_count":15},{"id":"2109.05042","title":"Reference-Centric Models for Grounded Collaborative Dialogue","created":"2021-09-10","cited_by_count":15},{"id":"2106.14321","title":"Draw Me a Flower: Processing and Grounding Abstraction in Natural Language","created":"2021-06-27","cited_by_count":14},{"id":"2107.04313","title":"Memes in the Wild: Assessing the Generalizability of the Hateful Memes Challenge Dataset","created":"2021-07-09","cited_by_count":13},{"id":"1805.11774","title":"Planning, Inference and Pragmatics in Sequential Language Games","created":"2018-05-30","cited_by_count":12},{"id":"1301.3883","title":"Conversation as Action Under Uncertainty","created":"2013-01-16","cited_by_count":11},{"id":"1902.09514","title":"Lost in Machine Translation: A Method to Reduce Meaning Loss","created":"2019-02-25","cited_by_count":11},{"id":"2109.04452","title":"Analysis of Language Change in Collaborative Instruction Following","created":"2021-09-09","cited_by_count":9},{"id":"1808.08470","title":"Representing Social Media Users for Sarcasm Detection","created":"2018-08-25","cited_by_count":8},{"id":"2010.03127","title":"A Linguistic Analysis of Visually Grounded Dialogues Based on Spatial Expressions","created":"2020-10-07","cited_by_count":6},{"id":"1909.07290","title":"Communication-based Evaluation for Natural Language Generation","created":"2019-09-16","cited_by_count":5},{"id":"1402.4802","title":"Ambiguity in language networks","created":"2014-02-18","cited_by_count":2},{"id":"2103.09977","title":"Situated Language Learning via Interactive Narratives","created":"2021-03-18","cited_by_count":2}],"next_cursor":null}