{"list":"other","total":53,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216},{"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":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649},{"id":"1811.10830","title":"From Recognition to Cognition: Visual Commonsense Reasoning","created":"2018-11-27","cited_by_count":556},{"id":"2102.02779","title":"Unifying Vision-and-Language Tasks via Text Generation","created":"2021-02-04","cited_by_count":412},{"id":"1711.10160","title":"Snorkel: Rapid Training Data Creation with Weak Supervision","created":"2017-11-28","cited_by_count":372},{"id":"1906.02361","title":"Explain Yourself! Leveraging Language Models for Commonsense Reasoning","created":"2019-06-06","cited_by_count":367},{"id":"2010.05953","title":"COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs","created":"2020-10-12","cited_by_count":254},{"id":"2201.04676","title":"UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning","created":"2022-01-12","cited_by_count":184},{"id":"2002.04108","title":"Adversarial Filters of Dataset Biases","created":"2020-02-10","cited_by_count":160},{"id":"2004.14546","title":"WT5?! Training Text-to-Text Models to Explain their Predictions","created":"2020-04-30","cited_by_count":148},{"id":"2112.07566","title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","created":"2021-12-14","cited_by_count":135},{"id":"2002.08565","title":"Captioning Images Taken by People Who Are Blind","created":"2020-02-20","cited_by_count":110},{"id":"2005.12116","title":"NILE : Natural Language Inference with Faithful Natural Language Explanations","created":"2020-05-25","cited_by_count":96},{"id":"2205.02655","title":"Language Models Can See: Plugging Visual Controls in Text Generation","created":"2022-05-05","cited_by_count":90},{"id":"1807.04905","title":"Ultra-Fine Entity Typing","created":"2018-07-13","cited_by_count":87},{"id":"2111.08284","title":"Few-Shot Self-Rationalization with Natural Language Prompts","created":"2021-11-16","cited_by_count":83},{"id":"1702.00820","title":"HoloClean: Holistic Data Repairs with Probabilistic Inference","created":"2017-02-02","cited_by_count":79},{"id":"1704.08803","title":"Neural Ranking Models with Weak Supervision","created":"2017-04-28","cited_by_count":61},{"id":"2211.01562","title":"PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales","created":"2022-11-03","cited_by_count":56},{"id":"2005.04304","title":"Temporal Common Sense Acquisition with Minimal Supervision","created":"2020-05-08","cited_by_count":39},{"id":"2106.04098","title":"Ultra-Fine Entity Typing with Weak Supervision from a Masked Language Model","created":"2021-06-08","cited_by_count":39},{"id":"1811.10582","title":"Visual Entailment Task for Visually-Grounded Language Learning","created":"2018-11-26","cited_by_count":36},{"id":"2106.05438","title":"Cross-Modal Discrete Representation Learning","created":"2021-06-10","cited_by_count":35},{"id":"2103.11320","title":"Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resources","created":"2021-03-21","cited_by_count":30},{"id":"2205.03784","title":"Should We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual Analysis","created":"2022-05-08","cited_by_count":30},{"id":"2012.08012","title":"Learning to Rationalize for Nonmonotonic Reasoning with Distant Supervision","created":"2020-12-14","cited_by_count":27},{"id":"2104.06511","title":"\"I'm Not Mad\": Commonsense Implications of Negation and Contradiction","created":"2021-04-13","cited_by_count":26},{"id":"2011.00905","title":"Advanced Semantics for Commonsense Knowledge Extraction","created":"2020-11-02","cited_by_count":24},{"id":"2010.12852","title":"Beyond VQA: Generating Multi-word Answer and Rationale to Visual Questions","created":"2020-10-24","cited_by_count":19},{"id":"2205.12640","title":"Does Your Model Classify Entities Reasonably? Diagnosing and Mitigating Spurious Correlations in Entity Typing","created":"2022-05-25","cited_by_count":16},{"id":"2210.04992","title":"Extracting or Guessing? Improving Faithfulness of Event Temporal Relation Extraction","created":"2022-10-10","cited_by_count":15},{"id":"2110.13606","title":"AUTO-DISCERN: Autonomous Driving Using Common Sense Reasoning","created":"2021-10-17","cited_by_count":14},{"id":"1806.05645","title":"Grounded Textual Entailment","created":"2018-06-14","cited_by_count":10},{"id":"2104.08712","title":"PaCo: Preconditions Attributed to Commonsense Knowledge","created":"2021-04-18","cited_by_count":9},{"id":"2004.02032","title":"Generating Rationales in Visual Question Answering","created":"2020-04-04","cited_by_count":6},{"id":"1611.08583","title":"Learning from Maps: Visual Common Sense for Autonomous Driving","created":"2016-11-25","cited_by_count":4},{"id":"2203.09052","title":"DU-VLG: Unifying Vision-and-Language Generation via Dual Sequence-to-Sequence Pre-training","created":"2022-03-17","cited_by_count":4},{"id":"2206.07920","title":"PInKS: Preconditioned Commonsense Inference with Minimal Supervision","created":"2022-06-16","cited_by_count":4},{"id":"2209.07000","title":"VIPHY: Probing \"Visible\" Physical Commonsense Knowledge","created":"2022-09-15","cited_by_count":4},{"id":"2207.01823","title":"Scene-Aware Prompt for Multi-modal Dialogue Understanding and Generation","created":"2022-07-05","cited_by_count":1}],"next_cursor":null}