{"list":"other","total":56,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"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":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"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":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"1809.08887","title":"Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task","created":"2018-09-24","cited_by_count":1139},{"id":"1704.00051","title":"Reading Wikipedia to Answer Open-Domain Questions","created":"2017-03-31","cited_by_count":777},{"id":"1709.00103","title":"Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning","created":"2017-08-31","cited_by_count":687},{"id":"1905.03197","title":"Unified Language Model Pre-training for Natural Language Understanding and Generation","created":"2019-05-08","cited_by_count":670},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649},{"id":"2009.02252","title":"KILT: a Benchmark for Knowledge Intensive Language Tasks","created":"2020-09-04","cited_by_count":573},{"id":"2202.11094","title":"GroupViT: Semantic Segmentation Emerges from Text Supervision","created":"2022-02-22","cited_by_count":531},{"id":"1508.00305","title":"Compositional Semantic Parsing on Semi-Structured Tables","created":"2015-08-03","cited_by_count":515},{"id":"2208.10442","title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","created":"2022-08-22","cited_by_count":511},{"id":"1911.04942","title":"RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers","created":"2019-11-10","cited_by_count":424},{"id":"2102.02779","title":"Unifying Vision-and-Language Tasks via Text Generation","created":"2021-02-04","cited_by_count":412},{"id":"2012.14740","title":"LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding","created":"2020-12-29","cited_by_count":408},{"id":"2010.00904","title":"Autoregressive Entity Retrieval","created":"2020-10-02","cited_by_count":334},{"id":"2208.02816","title":"Expanding Language-Image Pretrained Models for General Video Recognition","created":"2022-08-04","cited_by_count":321},{"id":"2204.07141","title":"Masked Siamese Networks for Label-Efficient Learning","created":"2022-04-14","cited_by_count":302},{"id":"2109.10282","title":"TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models","created":"2021-09-21","cited_by_count":279},{"id":"2106.11539","title":"DocFormer: End-to-End Transformer for Document Understanding","created":"2021-06-22","cited_by_count":256},{"id":"2107.07653","title":"TAPEX: Table Pre-training via Learning a Neural SQL Executor","created":"2021-07-16","cited_by_count":235},{"id":"2202.10401","title":"Vision-Language Pre-Training with Triple Contrastive Learning","created":"2022-02-21","cited_by_count":212},{"id":"1905.08205","title":"Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation","created":"2019-05-20","cited_by_count":210},{"id":"2202.09741","title":"Visual Attention Network","created":"2022-02-20","cited_by_count":210},{"id":"1907.12461","title":"Leveraging Pre-trained Checkpoints for Sequence Generation Tasks","created":"2019-07-29","cited_by_count":182},{"id":"1806.09029","title":"Improving Text-to-SQL Evaluation Methodology","created":"2018-06-23","cited_by_count":135},{"id":"2106.01065","title":"Towards Robustness of Text-to-SQL Models against Synonym Substitution","created":"2021-06-02","cited_by_count":110},{"id":"2109.05157","title":"Exploring Underexplored Limitations of Cross-Domain Text-to-SQL Generalization","created":"2021-09-11","cited_by_count":92},{"id":"2112.12494","title":"LaTr: Layout-Aware Transformer for Scene-Text VQA","created":"2021-12-23","cited_by_count":72},{"id":"2010.11246","title":"On the Potential of Lexico-logical Alignments for Semantic Parsing to SQL Queries","created":"2020-10-21","cited_by_count":60},{"id":"1804.10637","title":"Improving Entity Linking by Modeling Latent Relations between Mentions","created":"2018-04-27","cited_by_count":53},{"id":"2003.05473","title":"Investigating Entity Knowledge in BERT with Simple Neural End-To-End Entity Linking","created":"2020-03-11","cited_by_count":49},{"id":"2104.06678","title":"Large-Scale Self- and Semi-Supervised Learning for Speech Translation","created":"2021-04-14","cited_by_count":36},{"id":"2110.02369","title":"EntQA: Entity Linking as Question Answering","created":"2021-10-05","cited_by_count":34},{"id":"2204.06347","title":"WikiDiverse: A Multimodal Entity Linking Dataset with Diversified Contextual Topics and Entity Types","created":"2022-04-13","cited_by_count":34},{"id":"2206.14017","title":"Proton: Probing Schema Linking Information from Pre-trained Language Models for Text-to-SQL Parsing","created":"2022-06-28","cited_by_count":30},{"id":"2104.03236","title":"Multimodal Entity Linking for Tweets","created":"2021-04-07","cited_by_count":28},{"id":"2109.10540","title":"Awakening Latent Grounding from Pretrained Language Models for Semantic Parsing","created":"2021-09-22","cited_by_count":28},{"id":"1907.08243","title":"Joint Learning of Named Entity Recognition and Entity Linking","created":"2019-07-18","cited_by_count":26},{"id":"2109.03792","title":"Highly Parallel Autoregressive Entity Linking with Discriminative Correction","created":"2021-09-08","cited_by_count":21},{"id":"2212.07086","title":"NLIP: Noise-robust Language-Image Pre-training","created":"2022-12-14","cited_by_count":20},{"id":"2211.07912","title":"YORO -- Lightweight End to End Visual Grounding","created":"2022-11-15","cited_by_count":17},{"id":"1802.10229","title":"Collective Entity Disambiguation with Structured Gradient Tree Boosting","created":"2018-02-28","cited_by_count":16},{"id":"2108.07253","title":"Who's Waldo? Linking People Across Text and Images","created":"2021-08-16","cited_by_count":16},{"id":"2204.05990","title":"Detection, Disambiguation, Re-ranking: Autoregressive Entity Linking as a Multi-Task Problem","created":"2022-04-12","cited_by_count":11},{"id":"2102.01847","title":"An Investigation Between Schema Linking and Text-to-SQL Performance","created":"2021-02-03","cited_by_count":5},{"id":"2009.14809","title":"A Tale of Two Linkings: Dynamically Gating between Schema Linking and Structural Linking for Text-to-SQL Parsing","created":"2020-09-30","cited_by_count":4},{"id":"2207.01937","title":"Entity Linking in Tabular Data Needs the Right Attention","created":"2022-07-05","cited_by_count":2}],"next_cursor":null}