{"total":32,"rows":[{"id":"2404.18416","title":"Capabilities of Gemini Models in Medicine","created":"2024-04-29","cited_by_count":237,"area":null},{"id":"2107.07502","title":"MultiBench: Multiscale Benchmarks for Multimodal Representation Learning","created":"2021-07-15","cited_by_count":146,"area":null},{"id":"2204.05991","title":"ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension","created":"2022-04-12","cited_by_count":120,"area":null},{"id":"2209.03430","title":"Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions","created":"2022-09-07","cited_by_count":116,"area":null},{"id":"2304.01008","title":"Self-Supervised Multimodal Learning: A Survey","created":"2023-03-31","cited_by_count":58,"area":null},{"id":"2304.02828","title":"Uncurated Image-Text Datasets: Shedding Light on Demographic Bias","created":"2023-04-06","cited_by_count":52,"area":null},{"id":"2106.06683","title":"Assessing Multilingual Fairness in Pre-trained Multimodal Representations","created":"2021-06-12","cited_by_count":35,"area":null},{"id":"2303.06167","title":"Overwriting Pretrained Bias with Finetuning Data","created":"2023-03-10","cited_by_count":32,"area":null},{"id":"2210.10040","title":"The Tail Wagging the Dog: Dataset Construction Biases of Social Bias Benchmarks","created":"2022-10-18","cited_by_count":31,"area":null},{"id":"2404.03242","title":"Would Deep Generative Models Amplify Bias in Future Models?","created":"2024-04-04","cited_by_count":24,"area":null},{"id":"2304.03693","title":"Model-Agnostic Gender Debiased Image Captioning","created":"2023-04-07","cited_by_count":17,"area":null},{"id":"2410.19314","title":"Revealing and Reducing Gender Biases in Vision and Language Assistants (VLAs)","created":"2024-10-25","cited_by_count":15,"area":null},{"id":"2308.06198","title":"DIG In: Evaluating Disparities in Image Generations with Indicators for Geographic Diversity","created":"2023-08-11","cited_by_count":9,"area":null},{"id":"2407.00138","title":"Analyzing Quality, Bias, and Performance in Text-to-Image Generative Models","created":"2024-06-28","cited_by_count":9,"area":null},{"id":"2309.06703","title":"VLSlice: Interactive Vision-and-Language Slice Discovery","created":"2023-09-13","cited_by_count":7,"area":null},{"id":"2407.08219","title":"Generating Contextually-Relevant Navigation Instructions for Blind and Low Vision People","created":"2024-07-11","cited_by_count":7,"area":null},{"id":"2205.06253","title":"What's in a Caption? Dataset-Specific Linguistic Diversity and Its Effect on Visual Description Models and Metrics","created":"2022-05-12","cited_by_count":6,"area":null},{"id":"2305.14468","title":"Run Like a Girl! Sports-Related Gender Bias in Language and Vision","created":"2023-05-23","cited_by_count":6,"area":null},{"id":"2310.17530","title":"Evaluating Bias and Fairness in Gender-Neutral Pretrained Vision-and-Language Models","created":"2023-10-26","cited_by_count":6,"area":null},{"id":"2212.07877","title":"Manifestations of Xenophobia in AI Systems","created":"2022-12-15","cited_by_count":4,"area":null},{"id":"2311.06694","title":"Which One? Leveraging Context Between Objects and Multiple Views for Language Grounding","created":"2023-11-12","cited_by_count":3,"area":null},{"id":"2412.03567","title":"Streaming Detection of Queried Event Start","created":"2024-12-04","cited_by_count":3,"area":null},{"id":"2207.01772","title":"Vision-and-Language Pretraining","created":"2022-07-05","cited_by_count":2,"area":null},{"id":"2207.08104","title":"A Multibias-mitigated and Sentiment Knowledge Enriched Transformer for Debiasing in Multimodal Conversational Emotion Recognition","created":"2022-07-17","cited_by_count":1,"area":null},{"id":"2312.03151","title":"Multitask Learning Can Improve Worst-Group Outcomes","created":"2023-12-05","cited_by_count":1,"area":null},{"id":"2404.18976","title":"Foundations of Multisensory Artificial Intelligence","created":"2024-04-29","cited_by_count":1,"area":null},{"id":"2412.17505","title":"More is Less? A Simulation-Based Approach to Dynamic Interactions between Biases in Multimodal Models","created":"2024-12-23","cited_by_count":1,"area":null},{"id":"2502.02072","title":"ASCenD-BDS: Adaptable, Stochastic and Context-aware framework for Detection of Bias, Discrimination and Stereotyping","created":"2025-02-04","cited_by_count":1,"area":null},{"id":"2504.11104","title":"Using LLMs as prompt modifier to avoid biases in AI image generators","created":"2025-04-15","cited_by_count":1,"area":null},{"id":"2410.12839","title":"Capturing Bias Diversity in LLMs","created":"2024-10-09","cited_by_count":0,"area":null},{"id":"2506.17372","title":"Multimodal Political Bias Identification and Neutralization","created":"2025-06-20","cited_by_count":0,"area":null},{"id":"2602.04687","title":"Investigating Disability Representations in Text-to-Image Models","created":"2026-02-04","cited_by_count":0,"area":null}],"next_cursor":null}