{"list":"other","total":60,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"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":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766},{"id":"2003.11080","title":"XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization","created":"2020-03-24","cited_by_count":742},{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537},{"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":"2007.00644","title":"Measuring Robustness to Natural Distribution Shifts in Image Classification","created":"2020-07-01","cited_by_count":454},{"id":"2303.11897","title":"TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering","created":"2023-03-21","cited_by_count":428},{"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":"1711.10160","title":"Snorkel: Rapid Training Data Creation with Weak Supervision","created":"2017-11-28","cited_by_count":372},{"id":"2006.14799","title":"Evaluation of Text Generation: A Survey","created":"2020-06-26","cited_by_count":277},{"id":"1912.06992","title":"Action Genome: Actions as Composition of Spatio-temporal Scene Graphs","created":"2019-12-15","cited_by_count":250},{"id":"2109.13238","title":"Visually Grounded Reasoning across Languages and Cultures","created":"2021-09-28","cited_by_count":189},{"id":"1911.01464","title":"Emerging Cross-lingual Structure in Pretrained Language Models","created":"2019-11-04","cited_by_count":181},{"id":"2301.08745","title":"Is ChatGPT A Good Translator? Yes With GPT-4 As The Engine","created":"2023-01-20","cited_by_count":176},{"id":"2304.04675","title":"Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis","created":"2023-04-10","cited_by_count":160},{"id":"2101.05853","title":"Algorithmic Monoculture and Social Welfare","created":"2021-01-14","cited_by_count":100},{"id":"2205.12522","title":"Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Dataset","created":"2022-05-25","cited_by_count":100},{"id":"2204.01694","title":"\"This is my unicorn, Fluffy\": Personalizing frozen vision-language representations","created":"2022-04-04","cited_by_count":95},{"id":"2306.01943","title":"NLPositionality: Characterizing Design Biases of Datasets and Models","created":"2023-06-02","cited_by_count":94},{"id":"2307.10350","title":"Improving Multimodal Datasets with Image Captioning","created":"2023-07-19","cited_by_count":93},{"id":"2004.05160","title":"On the Language Neutrality of Pre-trained Multilingual Representations","created":"2020-04-09","cited_by_count":85},{"id":"2211.06679","title":"AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities","created":"2022-11-12","cited_by_count":85},{"id":"1805.08661","title":"COCO-CN for Cross-Lingual Image Tagging, Captioning and Retrieval","created":"2018-05-22","cited_by_count":80},{"id":"2109.06082","title":"xGQA: Cross-Lingual Visual Question Answering","created":"2021-09-13","cited_by_count":72},{"id":"1901.09981","title":"Improving Adversarial Robustness of Ensembles with Diversity Training","created":"2019-01-28","cited_by_count":69},{"id":"2305.14878","title":"Leveraging GPT-4 for Automatic Translation Post-Editing","created":"2023-05-24","cited_by_count":56},{"id":"1705.00823","title":"STAIR Captions: Constructing a Large-Scale Japanese Image Caption Dataset","created":"2017-05-02","cited_by_count":47},{"id":"2307.06930","title":"mBLIP: Efficient Bootstrapping of Multilingual Vision-LLMs","created":"2023-07-13","cited_by_count":41},{"id":"2210.05815","title":"Underspecification in Scene Description-to-Depiction Tasks","created":"2022-10-11","cited_by_count":30},{"id":"2307.12532","title":"On the Connection between Pre-training Data Diversity and Fine-tuning Robustness","created":"2023-07-24","cited_by_count":25},{"id":"2206.03390","title":"Gender Bias in Word Embeddings: A Comprehensive Analysis of Frequency, Syntax, and Semantics","created":"2022-06-07","cited_by_count":24},{"id":"2203.00758","title":"There is a Time and Place for Reasoning Beyond the Image","created":"2022-03-01","cited_by_count":22},{"id":"1601.03916","title":"Multimodal Pivots for Image Caption Translation","created":"2016-01-15","cited_by_count":18},{"id":"2211.10780","title":"ArtELingo: A Million Emotion Annotations of WikiArt with Emphasis on Diversity over Language and Culture","created":"2022-11-19","cited_by_count":17},{"id":"2005.09099","title":"(Re)construing Meaning in NLP","created":"2020-05-18","cited_by_count":16},{"id":"2210.13134","title":"Multilingual Multimodal Learning with Machine Translated Text","created":"2022-10-24","cited_by_count":16},{"id":"1704.07434","title":"Paying Attention to Descriptions Generated by Image Captioning Models","created":"2017-04-24","cited_by_count":12},{"id":"2301.12073","title":"Towards Equitable Representation in Text-to-Image Synthesis Models with the Cross-Cultural Understanding Benchmark (CCUB) Dataset","created":"2023-01-28","cited_by_count":12},{"id":"2305.02151","title":"Identifying the Correlation Between Language Distance and Cross-Lingual Transfer in a Multilingual Representation Space","created":"2023-05-03","cited_by_count":12},{"id":"2301.01893","title":"GIVL: Improving Geographical Inclusivity of Vision-Language Models with Pre-Training Methods","created":"2023-01-05","cited_by_count":11},{"id":"2306.08658","title":"Babel-ImageNet: Massively Multilingual Evaluation of Vision-and-Language Representations","created":"2023-06-14","cited_by_count":11},{"id":"2209.05401","title":"MaXM: Towards Multilingual Visual Question Answering","created":"2022-09-12","cited_by_count":9},{"id":"1809.02094","title":"Uncovering divergent linguistic information in word embeddings with lessons for intrinsic and extrinsic evaluation","created":"2018-09-06","cited_by_count":8},{"id":"2010.01288","title":"UNISON: Unpaired Cross-lingual Image Captioning","created":"2020-10-03","cited_by_count":8},{"id":"2302.12948","title":"Agile Modeling: From Concept to Classifier in Minutes","created":"2023-02-25","cited_by_count":8},{"id":"1301.3226","title":"The Expressive Power of Word Embeddings","created":"2013-01-15","cited_by_count":7},{"id":"2005.00246","title":"Cross-modal Language Generation using Pivot Stabilization for Web-scale Language Coverage","created":"2020-05-01","cited_by_count":5},{"id":"2305.07839","title":"The Geometry of Multilingual Language Models: An Equality Lens","created":"2023-05-13","cited_by_count":2}],"next_cursor":null}