{"total":207,"rows":[{"id":"2112.10003","title":"Image Segmentation Using Text and Image Prompts","created":"2021-12-18","cited_by_count":512,"area":null},{"id":"2106.08962","title":"Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better","created":"2021-06-16","cited_by_count":154,"area":null},{"id":"2201.06642","title":"Towards a Cleaner Document-Oriented Multilingual Crawled Corpus","created":"2022-01-17","cited_by_count":143,"area":null},{"id":"2303.03366","title":"Referring Multi-Object Tracking","created":"2023-03-06","cited_by_count":93,"area":null},{"id":"2104.08027","title":"Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders","created":"2021-04-16","cited_by_count":88,"area":null},{"id":"2204.09634","title":"Clotho-AQA: A Crowdsourced Dataset for Audio Question Answering","created":"2022-04-20","cited_by_count":85,"area":null},{"id":"2402.16785","title":"CARTE: Pretraining and Transfer for Tabular Learning","created":"2024-02-26","cited_by_count":76,"area":null},{"id":"2102.08886","title":"Towards generalisable hate speech detection: a review on obstacles and solutions","created":"2021-02-17","cited_by_count":66,"area":null},{"id":"2103.13309","title":"Are Multilingual Models Effective in Code-Switching?","created":"2021-03-24","cited_by_count":56,"area":null},{"id":"2102.06866","title":"Understanding Negative Samples in Instance Discriminative Self-supervised Representation Learning","created":"2021-02-13","cited_by_count":47,"area":null},{"id":"2303.12080","title":"Natural Language-Assisted Sign Language Recognition","created":"2023-03-21","cited_by_count":46,"area":null},{"id":"2404.02904","title":"ALOHa: A New Measure for Hallucination in Captioning Models","created":"2024-04-03","cited_by_count":45,"area":null},{"id":"2403.01509","title":"Fantastic Semantics and Where to Find Them: Investigating Which Layers of Generative LLMs Reflect Lexical Semantics","created":"2024-03-03","cited_by_count":44,"area":null},{"id":"2102.02967","title":"RpBERT: A Text-image Relation Propagation-based BERT Model for Multimodal NER","created":"2021-02-05","cited_by_count":37,"area":null},{"id":"2204.08398","title":"L3Cube-HingCorpus and HingBERT: A Code Mixed Hindi-English Dataset and BERT Language Models","created":"2022-04-18","cited_by_count":34,"area":null},{"id":"2302.10908","title":"Human-Centric Multimodal Machine Learning: Recent Advances and Testbed on AI-based Recruitment","created":"2023-02-13","cited_by_count":33,"area":null},{"id":"2103.11408","title":"L3CubeMahaSent: A Marathi Tweet-based Sentiment Analysis Dataset","created":"2021-03-21","cited_by_count":31,"area":null},{"id":"2103.11799","title":"DeepHate: Hate Speech Detection via Multi-Faceted Text Representations","created":"2021-03-14","cited_by_count":29,"area":null},{"id":"2107.14586","title":"An Efficient DP-SGD Mechanism for Large Scale NLP Models","created":"2021-07-14","cited_by_count":27,"area":null},{"id":"2104.09791","title":"B-PROP: Bootstrapped Pre-training with Representative Words Prediction for Ad-hoc Retrieval","created":"2021-04-20","cited_by_count":25,"area":"synth"},{"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,"area":null},{"id":"2104.04243","title":"Incorporating External Knowledge to Enhance Tabular Reasoning","created":"2021-04-09","cited_by_count":23,"area":null},{"id":"2106.02596","title":"Understanding and Countering Stereotypes: A Computational Approach to the Stereotype Content Model","created":"2021-06-04","cited_by_count":23,"area":null},{"id":"2109.06987","title":"NOPE: A Corpus of Naturally-Occurring Presuppositions in English","created":"2021-09-14","cited_by_count":23,"area":null},{"id":"2205.05949","title":"Automated Audio Captioning: An Overview of Recent Progress and New Challenges","created":"2022-05-12","cited_by_count":23,"area":null},{"id":"2204.04911","title":"Category-Aware Transformer Network for Better Human-Object Interaction Detection","created":"2022-04-11","cited_by_count":22,"area":null},{"id":"2209.09824","title":"Twitter Topic Classification","created":"2022-09-20","cited_by_count":22,"area":null},{"id":"2212.10440","title":"Perplexed by Quality: A Perplexity-based Method for Adult and Harmful Content Detection in Multilingual Heterogeneous Web Data","created":"2022-12-20","cited_by_count":22,"area":"safety"},{"id":"2106.03819","title":"A Semi-Personalized System for User Cold Start Recommendation on Music Streaming Apps","created":"2021-06-07","cited_by_count":21,"area":null},{"id":"2203.13920","title":"Canary Extraction in Natural Language Understanding Models","created":"2022-03-25","cited_by_count":21,"area":null},{"id":"2201.00103","title":"Robust Region Feature Synthesizer for Zero-Shot Object Detection","created":"2022-01-01","cited_by_count":20,"area":null},{"id":"2307.03360","title":"Evaluating Biased Attitude Associations of Language Models in an Intersectional Context","created":"2023-07-07","cited_by_count":20,"area":null},{"id":"2112.10728","title":"MuMuQA: Multimedia Multi-Hop News Question Answering via Cross-Media Knowledge Extraction and Grounding","created":"2021-12-20","cited_by_count":19,"area":null},{"id":"2505.14415","title":"Table Foundation Models: on knowledge pre-training for tabular learning","created":"2025-05-20","cited_by_count":19,"area":null},{"id":"2203.14266","title":"A Survey on Aspect-Based Sentiment Classification","created":"2022-03-27","cited_by_count":18,"area":null},{"id":"2103.12711","title":"A Pseudo-Metric between Probability Distributions based on Depth-Trimmed Regions","created":"2021-03-23","cited_by_count":17,"area":null},{"id":"2105.12628","title":"Predict then Interpolate: A Simple Algorithm to Learn Stable Classifiers","created":"2021-05-26","cited_by_count":16,"area":null},{"id":"2204.13749","title":"Learning to Split for Automatic Bias Detection","created":"2022-04-28","cited_by_count":16,"area":null},{"id":"2203.06907","title":"Hierarchical Memory Learning for Fine-Grained Scene Graph Generation","created":"2022-03-14","cited_by_count":15,"area":null},{"id":"2107.11584","title":"Extending Challenge Sets to Uncover Gender Bias in Machine Translation: Impact of Stereotypical Verbs and Adjectives","created":"2021-07-24","cited_by_count":14,"area":null},{"id":"2108.13112","title":"NEREL: A Russian Dataset with Nested Named Entities, Relations and Events","created":"2021-08-30","cited_by_count":13,"area":null},{"id":"2211.09172","title":"Deep Emotion Recognition in Textual Conversations: A Survey","created":"2022-11-16","cited_by_count":13,"area":null},{"id":"2212.13899","title":"Attentive Deep Neural Networks for Legal Document Retrieval","created":"2022-12-13","cited_by_count":13,"area":null},{"id":"2305.17993","title":"Multi-Scale Attention for Audio Question Answering","created":"2023-05-29","cited_by_count":13,"area":null},{"id":"2110.06376","title":"ALL Dolphins Are Intelligent and SOME Are Friendly: Probing BERT for Nouns' Semantic Properties and their Prototypicality","created":"2021-10-12","cited_by_count":12,"area":null},{"id":"2211.04591","title":"Learning to Follow Instructions in Text-Based Games","created":"2022-11-08","cited_by_count":12,"area":null},{"id":"2106.15065","title":"Rethinking End-to-End Evaluation of Decomposable Tasks: A Case Study on Spoken Language Understanding","created":"2021-06-29","cited_by_count":11,"area":null},{"id":"2304.06910","title":"HCAM -- Hierarchical Cross Attention Model for Multi-modal Emotion Recognition","created":"2023-04-14","cited_by_count":11,"area":null},{"id":"2310.03477","title":"Tik-to-Tok: Translating Language Models One Token at a Time: An Embedding Initialization Strategy for Efficient Language Adaptation","created":"2023-10-05","cited_by_count":11,"area":null},{"id":"2202.02387","title":"Automatic Identification of Self-Admitted Technical Debt from Four Different Sources","created":"2022-02-04","cited_by_count":10,"area":null},{"id":"2204.09597","title":"Perceiving the World: Question-guided Reinforcement Learning for Text-based Games","created":"2022-03-20","cited_by_count":10,"area":null},{"id":"2104.09792","title":"Identifying Helpful Sentences in Product Reviews","created":"2021-04-20","cited_by_count":9,"area":null},{"id":"2109.07968","title":"Alquist 4.0: Towards Social Intelligence Using Generative Models and Dialogue Personalization","created":"2021-09-16","cited_by_count":9,"area":null},{"id":"2202.01128","title":"Language Models Explain Word Reading Times Better Than Empirical Predictability","created":"2022-02-02","cited_by_count":9,"area":null},{"id":"2209.03465","title":"TAG: Learning Circuit Spatial Embedding From Layouts","created":"2022-09-07","cited_by_count":9,"area":null},{"id":"2205.05435","title":"Building for Tomorrow: Assessing the Temporal Persistence of Text Classifiers","created":"2022-05-11","cited_by_count":8,"area":null},{"id":"2207.09370","title":"Data-Centric Epidemic Forecasting: A Survey","created":"2022-07-19","cited_by_count":8,"area":null},{"id":"2305.12987","title":"GPT-SW3: An Autoregressive Language Model for the Nordic Languages","created":"2023-05-22","cited_by_count":8,"area":null},{"id":"2103.13942","title":"Visual Grounding Strategies for Text-Only Natural Language Processing","created":"2021-03-25","cited_by_count":7,"area":null},{"id":"2104.07777","title":"Proteno: Text Normalization with Limited Data for Fast Deployment in Text to Speech Systems","created":"2021-04-15","cited_by_count":7,"area":null},{"id":"2108.00480","title":"Realised Volatility Forecasting: Machine Learning via Financial Word Embedding","created":"2021-08-01","cited_by_count":7,"area":null},{"id":"2202.09166","title":"Evaluating the Construct Validity of Text Embeddings with Application to Survey Questions","created":"2022-02-18","cited_by_count":7,"area":null},{"id":"2210.05211","title":"A Win-win Deal: Towards Sparse and Robust Pre-trained Language Models","created":"2022-10-11","cited_by_count":7,"area":null},{"id":"2302.07189","title":"Reveal the Unknown: Out-of-Knowledge-Base Mention Discovery with Entity Linking","created":"2023-02-14","cited_by_count":7,"area":null},{"id":"2304.07781","title":"It's All in the Embedding! Fake News Detection Using Document Embeddings","created":"2023-04-16","cited_by_count":7,"area":null},{"id":"2408.03312","title":"MDT-A2G: Exploring Masked Diffusion Transformers for Co-Speech Gesture Generation","created":"2024-08-06","cited_by_count":7,"area":"diffusion"},{"id":"2411.14823","title":"Omni-IML: Towards Unified Image Manipulation Localization","created":"2024-11-22","cited_by_count":7,"area":null},{"id":"2510.12110","title":"Deep Associations, High Creativity: A Simple yet Effective Metric for Evaluating Large Language Models","created":"2025-10-14","cited_by_count":7,"area":null},{"id":"2103.02333","title":"Few-shot Learning for Slot Tagging with Attentive Relational Network","created":"2021-03-03","cited_by_count":6,"area":null},{"id":"2104.04630","title":"WLV-RIT at SemEval-2021 Task 5: A Neural Transformer Framework for Detecting Toxic Spans","created":"2021-04-09","cited_by_count":6,"area":null},{"id":"2105.04117","title":"Wiki-Reliability: A Large Scale Dataset for Content Reliability on Wikipedia","created":"2021-05-10","cited_by_count":6,"area":null},{"id":"2105.04556","title":"TANGO: Commonsense Generalization in Predicting Tool Interactions for Mobile Manipulators","created":"2021-05-05","cited_by_count":6,"area":null},{"id":"2106.07847","title":"Learning Stable Classifiers by Transferring Unstable Features","created":"2021-06-15","cited_by_count":6,"area":null},{"id":"2108.11056","title":"Social Norm Bias: Residual Harms of Fairness-Aware Algorithms","created":"2021-08-25","cited_by_count":6,"area":null},{"id":"2109.05252","title":"XCoref: Cross-document Coreference Resolution in the Wild","created":"2021-09-11","cited_by_count":6,"area":null},{"id":"2202.02180","title":"Identifying Self-Admitted Technical Debt in Issue Tracking Systems using Machine Learning","created":"2022-02-04","cited_by_count":6,"area":null},{"id":"2212.05058","title":"Structured Like a Language Model: Analysing AI as an Automated Subject","created":"2022-12-08","cited_by_count":6,"area":null},{"id":"2301.08731","title":"Can Peanuts Fall in Love with Distributional Semantics?","created":"2023-01-20","cited_by_count":6,"area":null},{"id":"2310.04689","title":"SeeDS: Semantic Separable Diffusion Synthesizer for Zero-shot Food Detection","created":"2023-10-07","cited_by_count":6,"area":"diffusion"},{"id":"2410.02773","title":"Mind the Uncertainty in Human Disagreement: Evaluating Discrepancies between Model Predictions and Human Responses in VQA","created":"2024-09-17","cited_by_count":6,"area":"mllm"},{"id":"2108.10698","title":"Efficacy of BERT embeddings on predicting disaster from Twitter data","created":"2021-08-08","cited_by_count":5,"area":null},{"id":"2110.07410","title":"Evaluating Off-the-Shelf Machine Listening and Natural Language Models for Automated Audio Captioning","created":"2021-10-14","cited_by_count":5,"area":null},{"id":"2204.05459","title":"Easy Adaptation to Mitigate Gender Bias in Multilingual Text Classification","created":"2022-04-12","cited_by_count":5,"area":null},{"id":"2204.05673","title":"What do Toothbrushes do in the Kitchen? How Transformers Think our World is Structured","created":"2022-04-12","cited_by_count":5,"area":"lr"},{"id":"2204.08226","title":"Empirical Evaluation and Theoretical Analysis for Representation Learning: A Survey","created":"2022-04-18","cited_by_count":5,"area":null},{"id":"2206.07593","title":"HICEM: A High-Coverage Emotion Model for Artificial Emotional Intelligence","created":"2022-06-15","cited_by_count":5,"area":null},{"id":"2305.11251","title":"Computational thematics: Comparing algorithms for clustering the genres of literary fiction","created":"2023-05-18","cited_by_count":5,"area":null},{"id":"2306.03443","title":"Alzheimer Disease Classification through ASR-based Transcriptions: Exploring the Impact of Punctuation and Pauses","created":"2023-06-06","cited_by_count":5,"area":null},{"id":"2306.16143","title":"Generative User-Experience Research for Developing Domain-specific Natural Language Processing Applications","created":"2023-06-28","cited_by_count":5,"area":null},{"id":"2102.03596","title":"Does He Wink or Does He Nod? A Challenging Benchmark for Evaluating Word Understanding of Language Models","created":"2021-02-06","cited_by_count":4,"area":null},{"id":"2109.12406","title":"MINIMAL: Mining Models for Data Free Universal Adversarial Triggers","created":"2021-09-25","cited_by_count":4,"area":null},{"id":"2110.13317","title":"Exposure of occupations to technologies of the fourth industrial revolution","created":"2021-10-25","cited_by_count":4,"area":null},{"id":"2206.07359","title":"The Emotion is Not One-hot Encoding: Learning with Grayscale Label for Emotion Recognition in Conversation","created":"2022-06-15","cited_by_count":4,"area":null},{"id":"2305.06923","title":"EAML: Ensemble Self-Attention-based Mutual Learning Network for Document Image Classification","created":"2023-05-11","cited_by_count":4,"area":null},{"id":"2404.01490","title":"AAdaM at SemEval-2024 Task 1: Augmentation and Adaptation for Multilingual Semantic Textual Relatedness","created":"2024-04-01","cited_by_count":4,"area":null},{"id":"2412.12409","title":"Improving Cooperation in Language Games with Bayesian Inference and the Cognitive Hierarchy","created":"2024-12-16","cited_by_count":4,"area":null},{"id":"2001.06944","title":"Nested-Wasserstein Self-Imitation Learning for Sequence Generation","created":"2020-01-20","cited_by_count":3,"area":"offlinerl"},{"id":"2104.07868","title":"Segmenting Subtitles for Correcting ASR Segmentation Errors","created":"2021-04-16","cited_by_count":3,"area":null},{"id":"2104.12852","title":"Geographic ratemaking with spatial embeddings","created":"2021-04-26","cited_by_count":3,"area":null},{"id":"2105.12192","title":"NukeLM: Pre-Trained and Fine-Tuned Language Models for the Nuclear and Energy Domains","created":"2021-05-25","cited_by_count":3,"area":null}],"next_cursor":"100"}