{"list":"other","total":66,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"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":"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":"2004.09297","title":"MPNet: Masked and Permuted Pre-training for Language Understanding","created":"2020-04-20","cited_by_count":981},{"id":"2005.00928","title":"Quantifying Attention Flow in Transformers","created":"2020-05-02","cited_by_count":775},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649},{"id":"2204.03162","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","created":"2022-04-07","cited_by_count":529},{"id":"1805.01070","title":"What you can cram into a single vector: Probing sentence embeddings for linguistic properties","created":"2018-05-03","cited_by_count":457},{"id":"2112.07899","title":"Large Dual Encoders Are Generalizable Retrievers","created":"2021-12-15","cited_by_count":456},{"id":"1705.02364","title":"Supervised Learning of Universal Sentence Representations from Natural Language Inference Data","created":"2017-05-05","cited_by_count":432},{"id":"2106.02997","title":"Causal Abstractions of Neural Networks","created":"2021-06-06","cited_by_count":422},{"id":"1511.02799","title":"Neural Module Networks","created":"2015-11-09","cited_by_count":376},{"id":"2004.10151","title":"Experience Grounds Language","created":"2020-04-21","cited_by_count":242},{"id":"1906.02715","title":"Visualizing and Measuring the Geometry of BERT","created":"2019-06-06","cited_by_count":216},{"id":"2006.16934","title":"ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graph","created":"2020-06-30","cited_by_count":211},{"id":"2212.07796","title":"CREPE: Can Vision-Language Foundation Models Reason Compositionally?","created":"2022-12-13","cited_by_count":181},{"id":"2103.05247","title":"Pretrained Transformers as Universal Computation Engines","created":"2021-03-09","cited_by_count":162},{"id":"2005.00719","title":"Probing the Probing Paradigm: Does Probing Accuracy Entail Task Relevance?","created":"2020-05-02","cited_by_count":151},{"id":"2103.03493","title":"Causal Attention for Vision-Language Tasks","created":"2021-03-05","cited_by_count":111},{"id":"1601.01705","title":"Learning to Compose Neural Networks for Question Answering","created":"2016-01-07","cited_by_count":85},{"id":"2011.15124","title":"Multimodal Pretraining Unmasked: A Meta-Analysis and a Unified Framework of Vision-and-Language BERTs","created":"2020-11-30","cited_by_count":71},{"id":"2106.13488","title":"Probing Inter-modality: Visual Parsing with Self-Attention for Vision-Language Pre-training","created":"2021-06-25","cited_by_count":67},{"id":"1904.00157","title":"Linguistic generalization and compositionality in modern artificial neural networks","created":"2019-03-30","cited_by_count":58},{"id":"2203.17247","title":"VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers","created":"2022-03-30","cited_by_count":53},{"id":"2103.04350","title":"Syntax-BERT: Improving Pre-trained Transformers with Syntax Trees","created":"2021-03-07","cited_by_count":51},{"id":"2205.01128","title":"Neurocompositional computing: From the Central Paradox of Cognition to a new generation of AI systems","created":"2022-05-02","cited_by_count":44},{"id":"2211.00768","title":"Why is Winoground Hard? Investigating Failures in Visuolinguistic Compositionality","created":"2022-11-01","cited_by_count":44},{"id":"2206.05379","title":"A Benchmark for Compositional Visual Reasoning","created":"2022-06-11","cited_by_count":43},{"id":"2211.01288","title":"Characterizing Intrinsic Compositionality in Transformers with Tree Projections","created":"2022-11-02","cited_by_count":41},{"id":"2105.07109","title":"The Low-Dimensional Linear Geometry of Contextualized Word Representations","created":"2021-05-15","cited_by_count":40},{"id":"2105.14002","title":"What if This Modified That? Syntactic Interventions via Counterfactual Embeddings","created":"2021-05-28","cited_by_count":39},{"id":"1910.09113","title":"Discovering the Compositional Structure of Vector Representations with Role Learning Networks","created":"2019-10-21","cited_by_count":34},{"id":"1905.06401","title":"Correlating neural and symbolic representations of language","created":"2019-05-14","cited_by_count":33},{"id":"2108.07073","title":"ROSITA: Enhancing Vision-and-Language Semantic Alignments via Cross- and Intra-modal Knowledge Integration","created":"2021-08-16","cited_by_count":31},{"id":"2106.02559","title":"Do Syntactic Probes Probe Syntax? Experiments with Jabberwocky Probing","created":"2021-06-04","cited_by_count":28},{"id":"1812.08718","title":"RNNs Implicitly Implement Tensor Product Representations","created":"2018-12-20","cited_by_count":26},{"id":"2012.15150","title":"Improving BERT with Syntax-aware Local Attention","created":"2020-12-30","cited_by_count":26},{"id":"1908.02127","title":"Aligning Linguistic Words and Visual Semantic Units for Image Captioning","created":"2019-08-06","cited_by_count":25},{"id":"1906.01958","title":"From Balustrades to Pierre Vinken: Looking for Syntax in Transformer Self-Attentions","created":"2019-06-05","cited_by_count":22},{"id":"2103.12975","title":"VLGrammar: Grounded Grammar Induction of Vision and Language","created":"2021-03-24","cited_by_count":22},{"id":"2105.13868","title":"Learning Relation Alignment for Calibrated Cross-modal Retrieval","created":"2021-05-28","cited_by_count":21},{"id":"2009.07364","title":"An information theoretic view on selecting linguistic probes","created":"2020-09-15","cited_by_count":19},{"id":"2112.02505","title":"Causal Distillation for Language Models","created":"2021-12-05","cited_by_count":19},{"id":"2112.13884","title":"A Fistful of Words: Learning Transferable Visual Models from Bag-of-Words Supervision","created":"2021-12-27","cited_by_count":19},{"id":"1805.10547","title":"Using Syntax to Ground Referring Expressions in Natural Images","created":"2018-05-26","cited_by_count":16},{"id":"2108.10568","title":"Auto-Parsing Network for Image Captioning and Visual Question Answering","created":"2021-08-24","cited_by_count":16},{"id":"2112.08587","title":"SGEITL: Scene Graph Enhanced Image-Text Learning for Visual Commonsense Reasoning","created":"2021-12-16","cited_by_count":16},{"id":"2203.14395","title":"Single-Stream Multi-Level Alignment for Vision-Language Pretraining","created":"2022-03-27","cited_by_count":16},{"id":"2004.14999","title":"A Matter of Framing: The Impact of Linguistic Formalism on Probing Results","created":"2020-04-30","cited_by_count":12},{"id":"1906.01575","title":"Pitfalls in the Evaluation of Sentence Embeddings","created":"2019-06-04","cited_by_count":9},{"id":"1308.0729","title":"Homotopy Type Theory: Univalent Foundations of Mathematics","created":"2013-08-03","cited_by_count":8},{"id":"2210.12079","title":"Do Vision-and-Language Transformers Learn Grounded Predicate-Noun Dependencies?","created":"2022-10-21","cited_by_count":8},{"id":"2203.09306","title":"Finding Structural Knowledge in Multimodal-BERT","created":"2022-03-17","cited_by_count":7},{"id":"2208.01744","title":"Cross-Modal Alignment Learning of Vision-Language Conceptual Systems","created":"2022-07-31","cited_by_count":4},{"id":"1910.03375","title":"In Search for Linear Relations in Sentence Embedding Spaces","created":"2019-10-08","cited_by_count":3}],"next_cursor":null}