{"total":128,"rows":[{"id":"2112.12143","title":"Scaling Open-Vocabulary Image Segmentation with Image-Level Labels","created":"2021-12-22","cited_by_count":473,"area":null},{"id":"2112.03221","title":"Text2Mesh: Text-Driven Neural Stylization for Meshes","created":"2021-12-06","cited_by_count":334,"area":null},{"id":"2304.06712","title":"What does CLIP know about a red circle? Visual prompt engineering for VLMs","created":"2023-04-13","cited_by_count":218,"area":"mllm"},{"id":"2405.17247","title":"An Introduction to Vision-Language Modeling","created":"2024-05-27","cited_by_count":178,"area":"mllm"},{"id":"2306.11300","title":"RS5M and GeoRSCLIP: A Large Scale Vision-Language Dataset and A Large Vision-Language Model for Remote Sensing","created":"2023-06-20","cited_by_count":151,"area":"mllm"},{"id":"2302.00070","title":"Debiasing Vision-Language Models via Biased Prompts","created":"2023-01-31","cited_by_count":149,"area":"mllm"},{"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":"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":"2110.11316","title":"CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP","created":"2021-10-21","cited_by_count":89,"area":null},{"id":"2404.06511","title":"MoReVQA: Exploring Modular Reasoning Models for Video Question Answering","created":"2024-04-09","cited_by_count":74,"area":"lr"},{"id":"2312.06960","title":"Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment","created":"2023-12-12","cited_by_count":71,"area":"mllm"},{"id":"2309.05569","title":"ITI-GEN: Inclusive Text-to-Image Generation","created":"2023-09-11","cited_by_count":64,"area":null},{"id":"2401.12425","title":"The Neglected Tails in Vision-Language Models","created":"2024-01-23","cited_by_count":63,"area":"mllm"},{"id":"2301.11104","title":"Discovering and Mitigating Visual Biases through Keyword Explanation","created":"2023-01-26","cited_by_count":58,"area":null},{"id":"2304.01008","title":"Self-Supervised Multimodal Learning: A Survey","created":"2023-03-31","cited_by_count":58,"area":null},{"id":"2205.08508","title":"A CLIP-Hitchhiker's Guide to Long Video Retrieval","created":"2022-05-17","cited_by_count":57,"area":null},{"id":"2404.07983","title":"Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models","created":"2024-04-11","cited_by_count":57,"area":"mllm"},{"id":"2307.05845","title":"PIGEON: Predicting Image Geolocations","created":"2023-07-11","cited_by_count":56,"area":null},{"id":"2402.05779","title":"Examining Gender and Racial Bias in Large Vision-Language Models Using a Novel Dataset of Parallel Images","created":"2024-02-08","cited_by_count":55,"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":"2308.11485","title":"Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features","created":"2023-08-22","cited_by_count":52,"area":null},{"id":"2306.05392","title":"Modular Visual Question Answering via Code Generation","created":"2023-06-08","cited_by_count":48,"area":null},{"id":"2304.03916","title":"Mitigating Spurious Correlations in Multi-modal Models during Fine-tuning","created":"2023-04-08","cited_by_count":47,"area":null},{"id":"2212.11261","title":"Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Bias","created":"2022-12-21","cited_by_count":43,"area":null},{"id":"2207.00691","title":"American == White in Multimodal Language-and-Image AI","created":"2022-07-01","cited_by_count":39,"area":null},{"id":"2402.07220","title":"KVQ: Kwai Video Quality Assessment for Short-form Videos","created":"2024-02-11","cited_by_count":38,"area":null},{"id":"2301.11100","title":"Vision-Language Models Performing Zero-Shot Tasks Exhibit Gender-based Disparities","created":"2023-01-26","cited_by_count":31,"area":"mllm"},{"id":"2407.00600","title":"GenderBias-\\emph{VL}: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probing","created":"2024-06-30","cited_by_count":31,"area":"mllm"},{"id":"2205.10764","title":"Evidence for Hypodescent in Visual Semantic AI","created":"2022-05-22","cited_by_count":30,"area":null},{"id":"2205.11378","title":"Markedness in Visual Semantic AI","created":"2022-05-23","cited_by_count":29,"area":null},{"id":"2406.00783","title":"AI-Face: A Million-Scale Demographically Annotated AI-Generated Face Dataset and Fairness Benchmark","created":"2024-06-02","cited_by_count":28,"area":null},{"id":"2305.15407","title":"Balancing the Picture: Debiasing Vision-Language Datasets with Synthetic Contrast Sets","created":"2023-05-24","cited_by_count":27,"area":"mllm"},{"id":"2309.14381","title":"Survey of Social Bias in Vision-Language Models","created":"2023-09-24","cited_by_count":26,"area":"mllm"},{"id":"2302.07159","title":"A Friendly Face: Do Text-to-Image Systems Rely on Stereotypes when the Input is Under-Specified?","created":"2023-02-14","cited_by_count":25,"area":null},{"id":"2403.15593","title":"FairerCLIP: Debiasing CLIP's Zero-Shot Predictions using Functions in RKHSs","created":"2024-03-22","cited_by_count":25,"area":"mllm"},{"id":"2305.14711","title":"Gender Biases in Automatic Evaluation Metrics for Image Captioning","created":"2023-05-24","cited_by_count":24,"area":null},{"id":"2306.15521","title":"What a MESS: Multi-Domain Evaluation of Zero-Shot Semantic Segmentation","created":"2023-06-27","cited_by_count":24,"area":null},{"id":"2303.12734","title":"MultiModal Bias: Introducing a Framework for Stereotypical Bias Assessment beyond Gender and Race in Vision Language Models","created":"2023-03-16","cited_by_count":23,"area":"mllm"},{"id":"2302.03675","title":"Auditing Gender Presentation Differences in Text-to-Image Models","created":"2023-02-07","cited_by_count":22,"area":null},{"id":"2210.14562","title":"FairCLIP: Social Bias Elimination based on Attribute Prototype Learning and Representation Neutralization","created":"2022-10-26","cited_by_count":20,"area":null},{"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":"2410.07593","title":"A Unified Debiasing Approach for Vision-Language Models across Modalities and Tasks","created":"2024-10-10","cited_by_count":18,"area":"mllm"},{"id":"2411.12785","title":"Joint Vision-Language Social Bias Removal for CLIP","created":"2024-11-19","cited_by_count":18,"area":null},{"id":"2308.01313","title":"PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts","created":"2023-08-02","cited_by_count":17,"area":"mllm"},{"id":"2312.14232","title":"Parrot Captions Teach CLIP to Spot Text","created":"2023-12-21","cited_by_count":17,"area":null},{"id":"2411.04420","title":"BendVLM: Test-Time Debiasing of Vision-Language Embeddings","created":"2024-11-07","cited_by_count":17,"area":"mllm"},{"id":"2112.08594","title":"Twitter-COMMs: Detecting Climate, COVID, and Military Multimodal Misinformation","created":"2021-12-16","cited_by_count":16,"area":null},{"id":"2210.12637","title":"Neural Eigenfunctions Are Structured Representation Learners","created":"2022-10-23","cited_by_count":16,"area":null},{"id":"2405.13777","title":"No Filter: Cultural and Socioeconomic Diversity in Contrastive Vision-Language Models","created":"2024-05-22","cited_by_count":16,"area":"mllm"},{"id":"2401.16092","title":"Multilingual Text-to-Image Generation Magnifies Gender Stereotypes and Prompt Engineering May Not Help You","created":"2024-01-29","cited_by_count":15,"area":null},{"id":"2405.08209","title":"Who's in and who's out? A case study of multimodal CLIP-filtering in DataComp","created":"2024-05-13","cited_by_count":15,"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":"2203.07511","title":"Contrastive Visual Semantic Pretraining Magnifies the Semantics of Natural Language Representations","created":"2022-03-14","cited_by_count":14,"area":null},{"id":"2206.04530","title":"DORA: Exploring Outlier Representations in Deep Neural Networks","created":"2022-06-09","cited_by_count":14,"area":null},{"id":"2210.15110","title":"Masked Vision-Language Transformer in Fashion","created":"2022-10-27","cited_by_count":14,"area":null},{"id":"2212.00784","title":"Improving Zero-Shot Models with Label Distribution Priors","created":"2022-12-01","cited_by_count":14,"area":null},{"id":"2404.02900","title":"DeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets","created":"2024-04-03","cited_by_count":14,"area":null},{"id":"2503.23398","title":"A Large Scale Analysis of Gender Biases in Text-to-Image Generative Models","created":"2025-03-30","cited_by_count":14,"area":null},{"id":"2403.02580","title":"What do we learn from inverting CLIP models?","created":"2024-03-05","cited_by_count":13,"area":null},{"id":"2408.02464","title":"Fairness and Bias Mitigation in Computer Vision: A Survey","created":"2024-08-05","cited_by_count":13,"area":null},{"id":"2307.12980","title":"A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models","created":"2023-07-24","cited_by_count":12,"area":"mllm"},{"id":"2404.16123","title":"FairDeDup: Detecting and Mitigating Vision-Language Fairness Disparities in Semantic Dataset Deduplication","created":"2024-04-24","cited_by_count":11,"area":"mllm"},{"id":"2502.08779","title":"BBQ-V: Benchmarking Visual Stereotype Bias in Large Multimodal Models","created":"2025-02-12","cited_by_count":11,"area":"mllm"},{"id":"2403.02695","title":"Controllable Prompt Tuning For Balancing Group Distributional Robustness","created":"2024-03-05","cited_by_count":10,"area":null},{"id":"2408.14435","title":"Social Perception of Faces in a Vision-Language Model","created":"2024-08-26","cited_by_count":10,"area":"mllm"},{"id":"2507.09500","title":"Advancing Reliable Test-Time Adaptation of Vision-Language Models under Visual Variations","created":"2025-07-13","cited_by_count":9,"area":"mllm"},{"id":"2210.05248","title":"Self-supervised debiasing using low rank regularization","created":"2022-10-11","cited_by_count":8,"area":null},{"id":"2211.07275","title":"Zero-shot Image Captioning by Anchor-augmented Vision-Language Space Alignment","created":"2022-11-14","cited_by_count":8,"area":null},{"id":"2406.09353","title":"Enhancing Domain Adaptation through Prompt Gradient Alignment","created":"2024-06-13","cited_by_count":8,"area":"mllm"},{"id":"2501.00962","title":"OASIS Uncovers: High-Quality T2I Models, Same Old Stereotypes","created":"2025-01-01","cited_by_count":8,"area":null},{"id":"2309.10361","title":"Improving CLIP Robustness with Knowledge Distillation and Self-Training","created":"2023-09-19","cited_by_count":7,"area":"distill"},{"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":"2211.02580","title":"Evaluating and Improving Factuality in Multimodal Abstractive Summarization","created":"2022-11-04","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":"2401.02651","title":"Benchmarking PathCLIP for Pathology Image Analysis","created":"2024-01-05","cited_by_count":6,"area":null},{"id":"2302.08572","title":"Towards Reliable Assessments of Demographic Disparities in Multi-Label Image Classifiers","created":"2023-02-16","cited_by_count":5,"area":null},{"id":"2402.07329","title":"The Bias of Harmful Label Associations in Vision-Language Models","created":"2024-02-11","cited_by_count":5,"area":"mllm"},{"id":"2412.10604","title":"EvalGIM: A Library for Evaluating Generative Image Models","created":"2024-12-13","cited_by_count":5,"area":null},{"id":"2503.18324","title":"Plug-and-Play Interpretable Responsible Text-to-Image Generation via Dual-Space Multi-facet Concept Control","created":"2025-03-24","cited_by_count":5,"area":null},{"id":"2507.08979","title":"PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection","created":"2025-07-11","cited_by_count":5,"area":"mllm"},{"id":"2307.09233","title":"Distilling Knowledge from Text-to-Image Generative Models Improves Visio-Linguistic Reasoning in CLIP","created":"2023-07-18","cited_by_count":4,"area":null},{"id":"2505.23798","title":"Unveiling the \"Fairness Seesaw\": Discovering and Mitigating Gender and Race Bias in Vision-Language Models","created":"2025-05-26","cited_by_count":4,"area":"mllm"},{"id":"2510.03721","title":"Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Models","created":"2025-10-04","cited_by_count":4,"area":"mllm"},{"id":"2601.13942","title":"Glance-or-Gaze: Incentivizing LMMs to Adaptively Focus Search via Reinforcement Learning","created":"2026-01-20","cited_by_count":4,"area":"lr"},{"id":"2206.08349","title":"Know your audience: specializing grounded language models with listener subtraction","created":"2022-06-16","cited_by_count":3,"area":null},{"id":"2303.02688","title":"Text2Face: A Multi-Modal 3D Face Model","created":"2023-03-05","cited_by_count":3,"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":"2406.17462","title":"EvolvED: Evolutionary Embeddings to Understand the Generation Process of Diffusion Models","created":"2024-06-25","cited_by_count":3,"area":"diffusion"},{"id":"2505.13429","title":"Understanding Complexity in VideoQA via Visual Program Generation","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2509.19659","title":"Bias in the Picture: Benchmarking VLMs with Social-Cue News Images and LLM-as-Judge Assessment","created":"2025-09-24","cited_by_count":3,"area":"mllm"},{"id":"2403.00376","title":"Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation Model","created":"2024-03-01","cited_by_count":2,"area":"mllm"},{"id":"2406.18562","title":"Views Can Be Deceiving: Improved SSL Through Feature Space Augmentation","created":"2024-05-28","cited_by_count":2,"area":null},{"id":"2407.21001","title":"GABInsight: Exploring Gender-Activity Binding Bias in Vision-Language Models","created":"2024-07-30","cited_by_count":2,"area":"mllm"},{"id":"2410.00704","title":"Contrastive Abstraction for Reinforcement Learning","created":"2024-10-01","cited_by_count":2,"area":"deeprl"},{"id":"2503.13652","title":"Web Artifact Attacks Disrupt Vision Language Models","created":"2025-03-17","cited_by_count":2,"area":"mllm"},{"id":"2508.08570","title":"Superclass-Guided Representation Disentanglement for Spurious Correlation Mitigation","created":"2025-08-12","cited_by_count":2,"area":"mllm"},{"id":"2508.09450","title":"From Charts to Fair Narratives: Uncovering and Mitigating Geo-Economic Biases in Chart-to-Text","created":"2025-08-13","cited_by_count":2,"area":null},{"id":"2508.17750","title":"From Global to Local: Social Bias Transfer in CLIP","created":"2025-08-25","cited_by_count":2,"area":null},{"id":"2508.18989","title":"Ask Me Again Differently: GRAS for Measuring Bias in Vision Language Models on Gender, Race, Age, and Skin Tone","created":"2025-08-26","cited_by_count":2,"area":"mllm"},{"id":"2603.11793","title":"Locating Demographic Bias at the Attention-Head Level in CLIP's Vision Encoder","created":"2026-03-12","cited_by_count":2,"area":null}],"next_cursor":"100"}