{"list":"other","total":58,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"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":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"1908.09635","title":"A Survey on Bias and Fairness in Machine Learning","created":"2019-08-23","cited_by_count":1917},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"1607.06520","title":"Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings","created":"2016-07-21","cited_by_count":1312},{"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":"1810.03993","title":"Model Cards for Model Reporting","created":"2018-10-05","cited_by_count":1080},{"id":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","created":"2024-03-13","cited_by_count":916},{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698},{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644},{"id":"2309.00770","title":"Bias and Fairness in Large Language Models: A Survey","created":"2023-09-02","cited_by_count":639},{"id":"2204.03162","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","created":"2022-04-07","cited_by_count":529},{"id":"2107.09044","title":"Just Train Twice: Improving Group Robustness without Training Group Information","created":"2021-07-19","cited_by_count":523},{"id":"1707.09457","title":"Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints","created":"2017-07-29","cited_by_count":420},{"id":"2306.14610","title":"SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality","created":"2023-06-26","cited_by_count":243},{"id":"1803.09797","title":"Women also Snowboard: Overcoming Bias in Captioning Models","created":"2018-03-26","cited_by_count":236},{"id":"2011.12945","title":"No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems","created":"2020-11-25","cited_by_count":209},{"id":"2203.14960","title":"Domino: Discovering Systematic Errors with Cross-Modal Embeddings","created":"2022-03-24","cited_by_count":156},{"id":"2004.07999","title":"REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasets","created":"2020-04-16","cited_by_count":136},{"id":"2201.08371","title":"Revisiting Weakly Supervised Pre-Training of Visual Perception Models","created":"2022-01-20","cited_by_count":116},{"id":"2110.04301","title":"Salient ImageNet: How to discover spurious features in Deep Learning?","created":"2021-10-08","cited_by_count":114},{"id":"2106.08503","title":"Understanding and Evaluating Racial Biases in Image Captioning","created":"2021-06-16","cited_by_count":108},{"id":"2008.11600","title":"Estimating Example Difficulty Using Variance of Gradients","created":"2020-08-26","cited_by_count":97},{"id":"2210.11841","title":"Diffusion Visual Counterfactual Explanations","created":"2022-10-21","cited_by_count":96},{"id":"1904.05419","title":"FairVis: Visual Analytics for Discovering Intersectional Bias in Machine Learning","created":"2019-04-10","cited_by_count":93},{"id":"2206.14754","title":"Distilling Model Failures as Directions in Latent Space","created":"2022-06-29","cited_by_count":82},{"id":"2107.00758","title":"The Spotlight: A General Method for Discovering Systematic Errors in Deep Learning Models","created":"2021-07-01","cited_by_count":63},{"id":"2404.14394","title":"A Multimodal Automated Interpretability Agent","created":"2024-04-22","cited_by_count":63},{"id":"2205.04596","title":"When does dough become a bagel? Analyzing the remaining mistakes on ImageNet","created":"2022-05-09","cited_by_count":61},{"id":"2404.07990","title":"OpenBias: Open-set Bias Detection in Text-to-Image Generative Models","created":"2024-04-11","cited_by_count":61},{"id":"2301.11104","title":"Discovering and Mitigating Visual Biases through Keyword Explanation","created":"2023-01-26","cited_by_count":58},{"id":"2012.01750","title":"Understanding Failures of Deep Networks via Robust Feature Extraction","created":"2020-12-03","cited_by_count":56},{"id":"2207.10077","title":"Discover and Mitigate Unknown Biases with Debiasing Alternate Networks","created":"2022-07-20","cited_by_count":47},{"id":"2104.14556","title":"Discover the Unknown Biased Attribute of an Image Classifier","created":"2021-04-29","cited_by_count":46},{"id":"2208.08831","title":"Discovering Bugs in Vision Models using Off-the-shelf Image Generation and Captioning","created":"2022-08-18","cited_by_count":45},{"id":"2211.01866","title":"ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations","created":"2022-11-03","cited_by_count":44},{"id":"2212.02774","title":"Adaptive Testing of Computer Vision Models","created":"2022-12-06","cited_by_count":39},{"id":"2204.08945","title":"Missingness Bias in Model Debugging","created":"2022-04-19","cited_by_count":38},{"id":"1806.09809","title":"Generating Counterfactual Explanations with Natural Language","created":"2018-06-26","cited_by_count":37},{"id":"2403.12960","title":"FaceXFormer: A Unified Transformer for Facial Analysis","created":"2024-03-19","cited_by_count":34},{"id":"2403.19964","title":"FairRAG: Fair Human Generation via Fair Retrieval Augmentation","created":"2024-03-29","cited_by_count":34},{"id":"2110.15499","title":"UDIS: Unsupervised Discovery of Bias in Deep Visual Recognition Models","created":"2021-10-29","cited_by_count":23},{"id":"2204.13749","title":"Learning to Split for Automatic Bias Detection","created":"2022-04-28","cited_by_count":16},{"id":"2403.12777","title":"Discover and Mitigate Multiple Biased Subgroups in Image Classifiers","created":"2024-03-19","cited_by_count":11},{"id":"2310.00164","title":"PRIME: Prioritizing Interpretability in Failure Mode Extraction","created":"2023-09-29","cited_by_count":9},{"id":"2408.04471","title":"What could go wrong? Discovering and describing failure modes in computer vision","created":"2024-08-08","cited_by_count":5},{"id":"2408.09570","title":"Say My Name: a Model's Bias Discovery Framework","created":"2024-08-18","cited_by_count":4},{"id":"2406.02889","title":"Language-guided Detection and Mitigation of Unknown Dataset Bias","created":"2024-06-05","cited_by_count":2}],"next_cursor":null}