{"list":"other","total":71,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"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":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"1904.08920","title":"Towards VQA Models That Can Read","created":"2019-04-18","cited_by_count":1718},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"2103.10360","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","created":"2021-03-18","cited_by_count":1031},{"id":"2302.04023","title":"A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity","created":"2023-02-08","cited_by_count":894},{"id":"1802.08218","title":"VizWiz Grand Challenge: Answering Visual Questions from Blind People","created":"2018-02-22","cited_by_count":858},{"id":"2210.02414","title":"GLM-130B: An Open Bilingual Pre-trained Model","created":"2022-10-05","cited_by_count":843},{"id":"1910.14599","title":"Adversarial NLI: A New Benchmark for Natural Language Understanding","created":"2019-10-31","cited_by_count":807},{"id":"2202.03052","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","created":"2022-02-07","cited_by_count":745},{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537},{"id":"1909.11059","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","created":"2019-09-24","cited_by_count":494},{"id":"1712.00377","title":"Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering","created":"2017-12-01","cited_by_count":339},{"id":"1907.13528","title":"What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language models","created":"2019-07-31","cited_by_count":320},{"id":"1511.03416","title":"Visual7W: Grounded Question Answering in Images","created":"2015-11-11","cited_by_count":318},{"id":"1810.02338","title":"Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding","created":"2018-10-04","cited_by_count":304},{"id":"2006.04315","title":"Counterfactual VQA: A Cause-Effect Look at Language Bias","created":"2020-06-08","cited_by_count":266},{"id":"1911.03343","title":"Negated and Misprimed Probes for Pretrained Language Models: Birds Can Talk, But Cannot Fly","created":"2019-11-08","cited_by_count":243},{"id":"2212.12017","title":"OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization","created":"2022-12-22","cited_by_count":236},{"id":"1706.05125","title":"Deal or No Deal? End-to-End Learning for Negotiation Dialogues","created":"2017-06-16","cited_by_count":209},{"id":"2103.15025","title":"On Hallucination and Predictive Uncertainty in Conditional Language Generation","created":"2021-03-28","cited_by_count":176},{"id":"1505.02074","title":"Exploring Models and Data for Image Question Answering","created":"2015-05-08","cited_by_count":139},{"id":"2004.02990","title":"Evaluating the Evaluation of Diversity in Natural Language Generation","created":"2020-04-06","cited_by_count":129},{"id":"1606.07356","title":"Analyzing the Behavior of Visual Question Answering Models","created":"2016-06-23","cited_by_count":119},{"id":"1912.07538","title":"Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing","created":"2019-12-16","cited_by_count":108},{"id":"1902.05660","title":"Cycle-Consistency for Robust Visual Question Answering","created":"2019-02-15","cited_by_count":105},{"id":"2103.09382","title":"SPICE: Semantic Pseudo-labeling for Image Clustering","created":"2021-03-17","cited_by_count":104},{"id":"2211.09699","title":"PromptCap: Prompt-Guided Task-Aware Image Captioning","created":"2022-11-15","cited_by_count":104},{"id":"2012.04638","title":"TAP: Text-Aware Pre-training for Text-VQA and Text-Caption","created":"2020-12-08","cited_by_count":95},{"id":"1703.09684","title":"An Analysis of Visual Question Answering Algorithms","created":"2017-03-28","cited_by_count":90},{"id":"2110.01705","title":"Let there be a clock on the beach: Reducing Object Hallucination in Image Captioning","created":"2021-10-04","cited_by_count":76},{"id":"2106.00245","title":"Adversarial VQA: A New Benchmark for Evaluating the Robustness of VQA Models","created":"2021-06-01","cited_by_count":75},{"id":"2105.03519","title":"Understanding by Understanding Not: Modeling Negation in Language Models","created":"2021-05-07","cited_by_count":73},{"id":"2203.06386","title":"Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation","created":"2022-03-12","cited_by_count":70},{"id":"2006.05121","title":"Roses Are Red, Violets Are Blue... but Should Vqa Expect Them To?","created":"2020-06-09","cited_by_count":69},{"id":"2205.01883","title":"All You May Need for VQA are Image Captions","created":"2022-05-04","cited_by_count":65},{"id":"2009.08566","title":"MUTANT: A Training Paradigm for Out-of-Distribution Generalization in Visual Question Answering","created":"2020-09-18","cited_by_count":63},{"id":"2209.12711","title":"Can Large Language Models Truly Understand Prompts? A Case Study with Negated Prompts","created":"2022-09-26","cited_by_count":59},{"id":"2104.08200","title":"IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generation","created":"2021-04-16","cited_by_count":57},{"id":"2106.02280","title":"Human-Adversarial Visual Question Answering","created":"2021-06-04","cited_by_count":57},{"id":"2103.09666","title":"Multimodal End-to-End Sparse Model for Emotion Recognition","created":"2021-03-17","cited_by_count":40},{"id":"1905.07870","title":"PaperRobot: Incremental Draft Generation of Scientific Ideas","created":"2019-05-20","cited_by_count":37},{"id":"1909.04696","title":"Sunny and Dark Outside?! Improving Answer Consistency in VQA through Entailed Question Generation","created":"2019-09-10","cited_by_count":36},{"id":"2007.06198","title":"Reducing Language Biases in Visual Question Answering with Visually-Grounded Question Encoder","created":"2020-07-13","cited_by_count":34},{"id":"2112.00974","title":"Consensus Graph Representation Learning for Better Grounded Image Captioning","created":"2021-12-02","cited_by_count":28},{"id":"1805.09701","title":"R-VQA: Learning Visual Relation Facts with Semantic Attention for Visual Question Answering","created":"2018-05-24","cited_by_count":23},{"id":"2106.02523","title":"Hallucination In Object Detection -- A Study In Visual Part Verification","created":"2021-06-04","cited_by_count":16},{"id":"2209.08529","title":"Overcoming Language Priors in Visual Question Answering via Distinguishing Superficially Similar Instances","created":"2022-09-18","cited_by_count":16},{"id":"2106.02325","title":"ERICA: An Empathetic Android Companion for Covid-19 Quarantine","created":"2021-06-04","cited_by_count":8},{"id":"2011.13406","title":"Learning from Lexical Perturbations for Consistent Visual Question Answering","created":"2020-11-26","cited_by_count":7},{"id":"2209.01638","title":"Every picture tells a story: Image-grounded controllable stylistic story generation","created":"2022-09-04","cited_by_count":5},{"id":"2302.14680","title":"Which One Are You Referring To? Multimodal Object Identification in Situated Dialogue","created":"2023-02-28","cited_by_count":1}],"next_cursor":null}