{"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"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":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"1907.10902","title":"Optuna: A Next-generation Hyperparameter Optimization Framework","created":"2019-07-25","cited_by_count":2501},{"id":"1910.10045","title":"Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI","created":"2019-10-22","cited_by_count":1552},{"id":"1610.01644","title":"Understanding intermediate layers using linear classifier probes","created":"2016-10-05","cited_by_count":1353},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"1703.04009","title":"Automated Hate Speech Detection and the Problem of Offensive Language","created":"2017-03-11","cited_by_count":736},{"id":"2212.07677","title":"Transformers learn in-context by gradient descent","created":"2022-12-15","cited_by_count":732},{"id":"2010.14701","title":"Scaling Laws for Autoregressive Generative Modeling","created":"2020-10-28","cited_by_count":522},{"id":"2005.04790","title":"The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes","created":"2020-05-10","cited_by_count":490},{"id":"2305.00050","title":"Causal Reasoning and Large Language Models: Opening a New Frontier for Causality","created":"2023-04-28","cited_by_count":353},{"id":"2006.04315","title":"Counterfactual VQA: A Cause-Effect Look at Language Bias","created":"2020-06-08","cited_by_count":266},{"id":"2103.05677","title":"SMIL: Multimodal Learning with Severely Missing Modality","created":"2021-03-09","cited_by_count":245},{"id":"2006.16934","title":"ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graph","created":"2020-06-30","cited_by_count":211},{"id":"2212.10559","title":"Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizers","created":"2022-12-20","cited_by_count":204},{"id":"1809.04444","title":"Hate Speech Dataset from a White Supremacy Forum","created":"2018-09-12","cited_by_count":198},{"id":"2110.07814","title":"Meta-learning via Language Model In-context Tuning","created":"2021-10-15","cited_by_count":164},{"id":"2307.14126","title":"Multi-modal Learning with Missing Modality via Shared-Specific Feature Modelling","created":"2023-07-26","cited_by_count":163},{"id":"2004.11207","title":"Self-Attention Attribution: Interpreting Information Interactions Inside Transformer","created":"2020-04-23","cited_by_count":125},{"id":"1910.03814","title":"Exploring Hate Speech Detection in Multimodal Publications","created":"2019-10-09","cited_by_count":103},{"id":"2205.11402","title":"Causal Machine Learning for Healthcare and Precision Medicine","created":"2022-05-23","cited_by_count":68},{"id":"2305.12907","title":"Meta-in-context learning in large language models","created":"2023-05-22","cited_by_count":59},{"id":"2306.16902","title":"Integrating Large Language Model for Improved Causal Discovery","created":"2023-06-29","cited_by_count":54},{"id":"2012.07788","title":"Vilio: State-of-the-art Visio-Linguistic Models applied to Hateful Memes","created":"2020-12-14","cited_by_count":51},{"id":"2012.12871","title":"A Multimodal Framework for the Detection of Hateful Memes","created":"2020-12-23","cited_by_count":49},{"id":"2105.07878","title":"A Review on Explainability in Multimodal Deep Neural Nets","created":"2021-05-17","cited_by_count":46},{"id":"2108.06207","title":"Disentangling Hate in Online Memes","created":"2021-08-09","cited_by_count":46},{"id":"2202.05798","title":"The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns via Spotlights of Attention","created":"2022-02-11","cited_by_count":46},{"id":"2109.08013","title":"Detecting Propaganda Techniques in Memes","created":"2021-08-07","cited_by_count":44},{"id":"2305.03915","title":"HateMM: A Multi-Modal Dataset for Hate Video Classification","created":"2023-05-06","cited_by_count":42},{"id":"2012.14891","title":"Detecting Hate Speech in Multi-modal Memes","created":"2020-12-29","cited_by_count":38},{"id":"2010.08660","title":"Semantics of the Black-Box: Can knowledge graphs help make deep learning systems more interpretable and explainable?","created":"2020-10-16","cited_by_count":31},{"id":"1910.02334","title":"Hate Speech in Pixels: Detection of Offensive Memes towards Automatic Moderation","created":"2019-10-05","cited_by_count":29},{"id":"2204.01734","title":"On Explaining Multimodal Hateful Meme Detection Models","created":"2022-04-04","cited_by_count":29},{"id":"2101.06426","title":"A Survey on Extraction of Causal Relations from Natural Language Text","created":"2021-01-16","cited_by_count":25},{"id":"2204.12037","title":"Causal Reasoning Meets Visual Representation Learning: A Prospective Study","created":"2022-04-26","cited_by_count":24},{"id":"2205.05738","title":"DISARM: Detecting the Victims Targeted by Harmful Memes","created":"2022-05-11","cited_by_count":20},{"id":"2206.05498","title":"A Review of Causality for Learning Algorithms in Medical Image Analysis","created":"2022-06-11","cited_by_count":18},{"id":"2006.08688","title":"Causal intersectionality for fair ranking","created":"2020-06-15","cited_by_count":12},{"id":"1909.08442","title":"Semantically Interpretable Activation Maps: what-where-how explanations within CNNs","created":"2019-09-18","cited_by_count":10},{"id":"2101.06535","title":"Dissecting the Meme Magic: Understanding Indicators of Virality in Image Memes","created":"2021-01-16","cited_by_count":10},{"id":"2108.10069","title":"An Interpretable Approach to Hateful Meme Detection","created":"2021-08-09","cited_by_count":3},{"id":"2202.00471","title":"Causal effect of racial bias in data and machine learning algorithms on user persuasiveness & discriminatory decision making: An Empirical Study","created":"2022-01-22","cited_by_count":2}],"next_cursor":null}