{"total":30,"rows":[{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386,"area":"mllm"},{"id":"2203.11933","title":"A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning","created":"2022-03-22","cited_by_count":104,"area":"mllm"},{"id":"2408.02900","title":"MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine","created":"2024-08-06","cited_by_count":81,"area":"mllm"},{"id":"2303.10431","title":"DeAR: Debiasing Vision-Language Models with Additive Residuals","created":"2023-03-18","cited_by_count":70,"area":"mllm"},{"id":"2406.10328","title":"From Pixels to Prose: A Large Dataset of Dense Image Captions","created":"2024-06-14","cited_by_count":54,"area":"mllm"},{"id":"2306.12424","title":"VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolution","created":"2023-06-21","cited_by_count":52,"area":"mllm"},{"id":"2503.23771","title":"XLRS-Bench: Could Your Multimodal LLMs Understand Extremely Large Ultra-High-Resolution Remote Sensing Imagery?","created":"2025-03-31","cited_by_count":51,"area":"mllm"},{"id":"2505.21375","title":"GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution","created":"2025-05-27","cited_by_count":44,"area":"mllm"},{"id":"2401.17600","title":"Good at captioning, bad at counting: Benchmarking GPT-4V on Earth observation data","created":"2024-01-31","cited_by_count":39,"area":"mllm"},{"id":"2406.19097","title":"Fairness and Bias in Multimodal AI: A Survey","created":"2024-06-27","cited_by_count":20,"area":"mllm"},{"id":"2505.11454","title":"HumaniBench: A Human-Centric Framework for Large Multimodal Models Evaluation","created":"2025-05-16","cited_by_count":19,"area":"mllm"},{"id":"2407.08101","title":"What to Say and When to Say it: Live Fitness Coaching as a Testbed for Situated Interaction","created":"2024-07-11","cited_by_count":18,"area":"mllm"},{"id":"2410.07540","title":"CoPESD: A Multi-Level Surgical Motion Dataset for Training Large Vision-Language Models to Co-Pilot Endoscopic Submucosal Dissection","created":"2024-10-10","cited_by_count":15,"area":"mllm"},{"id":"2405.17423","title":"Privacy-Aware Visual Language Models","created":"2024-05-27","cited_by_count":12,"area":"mllm"},{"id":"2311.05746","title":"Bridging the Digital Divide: Performance Variation across Socio-Economic Factors in Vision-Language Models","created":"2023-11-09","cited_by_count":11,"area":"mllm"},{"id":"2401.08212","title":"Human vs. LMMs: Exploring the Discrepancy in Emoji Interpretation and Usage in Digital Communication","created":"2024-01-16","cited_by_count":8,"area":"mllm"},{"id":"2311.17315","title":"Explaining CLIP's performance disparities on data from blind/low vision users","created":"2023-11-29","cited_by_count":7,"area":"mllm"},{"id":"2406.11331","title":"They're All Doctors: Synthesizing Diverse Counterfactuals to Mitigate Associative Bias","created":"2024-06-17","cited_by_count":3,"area":"mllm"},{"id":"2507.19262","title":"OVFact: Measuring and Improving Open-Vocabulary Factuality for Long Caption Models","created":"2025-07-25","cited_by_count":2,"area":"mllm"},{"id":"2601.13839","title":"DisasterVQA: A Visual Question Answering Benchmark Dataset for Disaster Scenes","created":"2026-01-20","cited_by_count":1,"area":"mllm"},{"id":"2605.22109","title":"Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality?","created":"2026-05-21","cited_by_count":1,"area":"mllm"},{"id":"2606.00871","title":"Benchmarks for Vision-Language Models in Urban Perception Should Be Reliability-Aware and Negotiated","created":"2026-05-30","cited_by_count":1,"area":"mllm"},{"id":"2607.05264","title":"SteelBench: Evaluating Vision-Language Models in Real-World Industrial Environments","created":"2026-07-06","cited_by_count":1,"area":"mllm"},{"id":"2607.12278","title":"Auditing Data Leakage in Whole-Slide Image Multimodal Benchmarks","created":"2026-07-14","cited_by_count":1,"area":"mllm"},{"id":"2607.25589","title":"Forensic Reproducibility Audit of a Radiology Vision-Language Model Benchmark: From Intended Protocol to Released Artifact","created":"2026-07-28","cited_by_count":0,"area":"mllm"},{"id":"2608.03884","title":"BanglaWild: An In-the-Wild Bengali Scene Text Recognition Benchmark for OCR and Vision-Language Models","created":"2026-08-04","cited_by_count":0,"area":"mllm"},{"id":"2608.24430","title":"Vision Language Model Fusion for Explainable Face Recognition","created":"2026-08-25","cited_by_count":0,"area":"mllm"},{"id":"2608.29483","title":"GeoAgent: Evaluating VLM Geolocalization Through Embodied Navigation","created":"2026-08-30","cited_by_count":0,"area":"mllm"},{"id":"2609.00103","title":"Good Memory Has ECC: Evaluating the Memory of Vision-Language Models Beyond Accuracy","created":"2026-08-31","cited_by_count":0,"area":"mllm"},{"id":"2610.19102","title":"The Gap Is in the Geometry: A Convergent Meta-Analysis of Multi-Facet Aerial and Remote Sensing Video Understanding","created":"2026-10-13","cited_by_count":0,"area":"mllm"}],"next_cursor":null}