{"total":109,"rows":[{"id":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1919,"area":"lr"},{"id":"2305.10355","title":"Evaluating Object Hallucination in Large Vision-Language Models","created":"2023-05-17","cited_by_count":1729,"area":"mllm"},{"id":"2102.09542","title":"SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering","created":"2021-02-18","cited_by_count":449,"area":null},{"id":"2110.13214","title":"IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning","created":"2021-10-25","cited_by_count":267,"area":null},{"id":"2203.14072","title":"Learning to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2022-03-26","cited_by_count":191,"area":null},{"id":"2104.06039","title":"MultiModalQA: Complex Question Answering over Text, Tables and Images","created":"2021-04-13","cited_by_count":179,"area":null},{"id":"2206.03428","title":"Revealing Single Frame Bias for Video-and-Language Learning","created":"2022-06-07","cited_by_count":133,"area":null},{"id":"2204.09634","title":"Clotho-AQA: A Crowdsourced Dataset for Audio Question Answering","created":"2022-04-20","cited_by_count":85,"area":null},{"id":"2303.07274","title":"Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images","created":"2023-03-13","cited_by_count":80,"area":null},{"id":"2307.02469","title":"What Matters in Training a GPT4-Style Language Model with Multimodal Inputs?","created":"2023-07-05","cited_by_count":64,"area":null},{"id":"2108.11945","title":"SASRA: Semantically-aware Spatio-temporal Reasoning Agent for Vision-and-Language Navigation in Continuous Environments","created":"2021-08-26","cited_by_count":48,"area":null},{"id":"2103.10095","title":"On Semantic Similarity in Video Retrieval","created":"2021-03-18","cited_by_count":46,"area":null},{"id":"2501.00569","title":"Probing Visual Language Priors in VLMs","created":"2024-12-31","cited_by_count":45,"area":"lr"},{"id":"2111.14725","title":"Searching the Search Space of Vision Transformer","created":"2021-11-29","cited_by_count":41,"area":null},{"id":"2112.08359","title":"3D Question Answering","created":"2021-12-15","cited_by_count":41,"area":null},{"id":"2107.12651","title":"Greedy Gradient Ensemble for Robust Visual Question Answering","created":"2021-07-27","cited_by_count":34,"area":null},{"id":"2201.05729","title":"CLIP-TD: CLIP Targeted Distillation for Vision-Language Tasks","created":"2022-01-15","cited_by_count":32,"area":null},{"id":"2410.00193","title":"Do Vision-Language Models Really Understand Visual Language?","created":"2024-09-30","cited_by_count":32,"area":"mllm"},{"id":"2103.09591","title":"Automatic Generation of Contrast Sets from Scene Graphs: Probing the Compositional Consistency of GQA","created":"2021-03-17","cited_by_count":30,"area":null},{"id":"2310.06238","title":"Tackling Data Bias in MUSIC-AVQA: Crafting a Balanced Dataset for Unbiased Question-Answering","created":"2023-10-10","cited_by_count":29,"area":null},{"id":"2112.09331","title":"Contrastive Vision-Language Pre-training with Limited Resources","created":"2021-12-17","cited_by_count":25,"area":"mllm"},{"id":"2310.10942","title":"UNK-VQA: A Dataset and a Probe into the Abstention Ability of Multi-modal Large Models","created":"2023-10-17","cited_by_count":25,"area":null},{"id":"2311.00308","title":"From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities","created":"2023-11-01","cited_by_count":25,"area":null},{"id":"2406.11030","title":"FoodieQA: A Multimodal Dataset for Fine-Grained Understanding of Chinese Food Culture","created":"2024-06-16","cited_by_count":25,"area":null},{"id":"2204.12037","title":"Causal Reasoning Meets Visual Representation Learning: A Prospective Study","created":"2022-04-26","cited_by_count":24,"area":"lr"},{"id":"2204.10496","title":"Multimodal Adaptive Distillation for Leveraging Unimodal Encoders for Vision-Language Tasks","created":"2022-04-22","cited_by_count":23,"area":null},{"id":"2307.11471","title":"Robust Visual Question Answering: Datasets, Methods, and Future Challenges","created":"2023-07-21","cited_by_count":23,"area":null},{"id":"2103.03872","title":"Rissanen Data Analysis: Examining Dataset Characteristics via Description Length","created":"2021-03-05","cited_by_count":22,"area":null},{"id":"2110.01013","title":"Counterfactual Samples Synthesizing and Training for Robust Visual Question Answering","created":"2021-10-03","cited_by_count":22,"area":null},{"id":"2412.08687","title":"VisionArena: 230K Real World User-VLM Conversations with Preference Labels","created":"2024-12-11","cited_by_count":22,"area":"mllm"},{"id":"2103.09669","title":"Large-Scale Zero-Shot Image Classification from Rich and Diverse Textual Descriptions","created":"2021-03-17","cited_by_count":21,"area":null},{"id":"2109.13139","title":"Multimodal Integration of Human-Like Attention in Visual Question Answering","created":"2021-09-27","cited_by_count":20,"area":null},{"id":"2109.02040","title":"Data Efficient Masked Language Modeling for Vision and Language","created":"2021-09-05","cited_by_count":19,"area":"mllm"},{"id":"2312.00935","title":"Understanding Unimodal Bias in Multimodal Deep Linear Networks","created":"2023-12-01","cited_by_count":19,"area":null},{"id":"2504.09724","title":"A Survey on Efficient Vision-Language Models","created":"2025-04-13","cited_by_count":19,"area":"mllm"},{"id":"2106.04605","title":"Check It Again: Progressive Visual Question Answering via Visual Entailment","created":"2021-06-08","cited_by_count":18,"area":null},{"id":"2207.08739","title":"Rethinking Data Augmentation for Robust Visual Question Answering","created":"2022-07-18","cited_by_count":18,"area":"distill"},{"id":"2109.13116","title":"VQA-MHUG: A Gaze Dataset to Study Multimodal Neural Attention in Visual Question Answering","created":"2021-09-27","cited_by_count":16,"area":null},{"id":"2112.08587","title":"SGEITL: Scene Graph Enhanced Image-Text Learning for Visual Commonsense Reasoning","created":"2021-12-16","cited_by_count":16,"area":null},{"id":"2204.02380","title":"CLEVR-X: A Visual Reasoning Dataset for Natural Language Explanations","created":"2022-04-05","cited_by_count":16,"area":"lr"},{"id":"2209.08529","title":"Overcoming Language Priors in Visual Question Answering via Distinguishing Superficially Similar Instances","created":"2022-09-18","cited_by_count":16,"area":null},{"id":"2110.06894","title":"Audio-Visual Scene-Aware Dialog and Reasoning using Audio-Visual Transformers with Joint Student-Teacher Learning","created":"2021-10-13","cited_by_count":15,"area":null},{"id":"2103.04037","title":"Perspectives and Prospects on Transformer Architecture for Cross-Modal Tasks with Language and Vision","created":"2021-03-06","cited_by_count":14,"area":null},{"id":"2212.13296","title":"VQA and Visual Reasoning: An Overview of Recent Datasets, Methods and Challenges","created":"2022-12-26","cited_by_count":14,"area":"lr"},{"id":"2402.17205","title":"Measuring Vision-Language STEM Skills of Neural Models","created":"2024-02-27","cited_by_count":14,"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":"2410.10799","title":"Towards Foundation Models for 3D Vision: How Close Are We?","created":"2024-10-14","cited_by_count":13,"area":null},{"id":"2208.00690","title":"Generative Bias for Robust Visual Question Answering","created":"2022-08-01","cited_by_count":12,"area":null},{"id":"2410.14690","title":"Rethinking VLMs and LLMs for Image Classification","created":"2024-10-03","cited_by_count":12,"area":"lr"},{"id":"2412.13989","title":"What makes a good metric? Evaluating automatic metrics for text-to-image consistency","created":"2024-12-18","cited_by_count":12,"area":null},{"id":"2105.00421","title":"A survey on VQA_Datasets and Approaches","created":"2021-05-02","cited_by_count":11,"area":null},{"id":"2203.07613","title":"CARETS: A Consistency And Robustness Evaluative Test Suite for VQA","created":"2022-03-15","cited_by_count":11,"area":null},{"id":"2107.11576","title":"X-GGM: Graph Generative Modeling for Out-of-Distribution Generalization in Visual Question Answering","created":"2021-07-24","cited_by_count":10,"area":null},{"id":"2310.16754","title":"CAD -- Contextual Multi-modal Alignment for Dynamic AVQA","created":"2023-10-25","cited_by_count":10,"area":null},{"id":"2411.00394","title":"Right this way: Can VLMs Guide Us to See More to Answer Questions?","created":"2024-11-01","cited_by_count":10,"area":null},{"id":"2102.01916","title":"Answer Questions with Right Image Regions: A Visual Attention Regularization Approach","created":"2021-02-03","cited_by_count":9,"area":null},{"id":"2209.06650","title":"WildQA: In-the-Wild Video Question Answering","created":"2022-09-14","cited_by_count":9,"area":null},{"id":"2304.03147","title":"Improving Visual Question Answering Models through Robustness Analysis and In-Context Learning with a Chain of Basic Questions","created":"2023-04-06","cited_by_count":9,"area":null},{"id":"2411.11150","title":"A Comprehensive Survey on Visual Question Answering Datasets and Algorithms","created":"2024-11-17","cited_by_count":8,"area":null},{"id":"2112.10572","title":"General Greedy De-bias Learning","created":"2021-12-20","cited_by_count":7,"area":null},{"id":"2304.10727","title":"RoCOCO: Robustness Benchmark of MS-COCO to Stress-test Image-Text Matching Models","created":"2023-04-21","cited_by_count":7,"area":"mllm"},{"id":"2305.16944","title":"Learning to Imagine: Visually-Augmented Natural Language Generation","created":"2023-05-26","cited_by_count":7,"area":null},{"id":"2310.14670","title":"Dataset Bias Mitigation in Multiple-Choice Visual Question Answering and Beyond","created":"2023-10-23","cited_by_count":7,"area":null},{"id":"2509.22437","title":"Chimera: Diagnosing Shortcut Learning in Visual-Language Understanding","created":"2025-09-26","cited_by_count":7,"area":null},{"id":"2308.08628","title":"Learning the meanings of function words from grounded language using a visual question answering model","created":"2023-08-16","cited_by_count":6,"area":null},{"id":"2401.17862","title":"Proximity QA: Unleashing the Power of Multi-Modal Large Language Models for Spatial Proximity Analysis","created":"2024-01-31","cited_by_count":6,"area":"mllm"},{"id":"2504.09426","title":"BabyVLM: Data-Efficient Pretraining of VLMs Inspired by Infant Learning","created":"2025-04-13","cited_by_count":6,"area":"lr"},{"id":"2211.05895","title":"Understanding ME? Multimodal Evaluation for Fine-grained Visual Commonsense","created":"2022-11-10","cited_by_count":5,"area":null},{"id":"2211.08736","title":"AlignVE: Visual Entailment Recognition Based on Alignment Relations","created":"2022-11-16","cited_by_count":5,"area":null},{"id":"2305.01888","title":"Fairness in AI Systems: Mitigating gender bias from language-vision models","created":"2023-05-03","cited_by_count":5,"area":null},{"id":"2404.00973","title":"VideoDistill: Language-aware Vision Distillation for Video Question Answering","created":"2024-04-01","cited_by_count":5,"area":null},{"id":"2406.18253","title":"On the Role of Visual Grounding in VQA","created":"2024-06-26","cited_by_count":5,"area":null},{"id":"2408.05334","title":"Revisiting Multi-Modal LLM Evaluation","created":"2024-08-09","cited_by_count":5,"area":"mllm"},{"id":"2502.18536","title":"FilterRAG: Zero-Shot Informed Retrieval-Augmented Generation to Mitigate Hallucinations in VQA","created":"2025-02-25","cited_by_count":5,"area":"rag"},{"id":"2104.06365","title":"Neuro-Symbolic VQA: A review from the perspective of AGI desiderata","created":"2021-04-13","cited_by_count":4,"area":null},{"id":"2201.03342","title":"COIN: Counterfactual Image Generation for VQA Interpretation","created":"2022-01-10","cited_by_count":4,"area":null},{"id":"2301.03238","title":"MAQA: A Multimodal QA Benchmark for Negation","created":"2023-01-09","cited_by_count":4,"area":null},{"id":"2311.16941","title":"Debiasing Multimodal Models via Causal Information Minimization","created":"2023-11-28","cited_by_count":4,"area":null},{"id":"2403.11317","title":"Few-Shot VQA with Frozen LLMs: A Tale of Two Approaches","created":"2024-03-17","cited_by_count":4,"area":null},{"id":"2404.18413","title":"3AM: An Ambiguity-Aware Multi-Modal Machine Translation Dataset","created":"2024-04-29","cited_by_count":4,"area":null},{"id":"2501.15693","title":"Beyond Benchmarks: On The False Promise of AI Regulation","created":"2025-01-26","cited_by_count":4,"area":null},{"id":"2509.25339","title":"VisualOverload: Probing Visual Understanding of VLMs in Really Dense Scenes","created":"2025-09-29","cited_by_count":4,"area":null},{"id":"2106.06147","title":"NAAQA: A Neural Architecture for Acoustic Question Answering","created":"2021-06-11","cited_by_count":3,"area":null},{"id":"2410.10184","title":"Eliminating the Language Bias for Visual Question Answering with fine-grained Causal Intervention","created":"2024-10-14","cited_by_count":3,"area":null},{"id":"2411.00828","title":"Dreaming Out Loud: A Self-Synthesis Approach For Training Vision-Language Models With Developmentally Plausible Data","created":"2024-10-29","cited_by_count":3,"area":"mllm"},{"id":"2106.08914","title":"$C^3$: Compositional Counterfactual Contrastive Learning for Video-grounded Dialogues","created":"2021-06-16","cited_by_count":2,"area":null},{"id":"2108.04097","title":"Deep Learning for Embodied Vision Navigation: A Survey","created":"2021-07-07","cited_by_count":2,"area":null},{"id":"2307.04532","title":"Read, Look or Listen? What's Needed for Solving a Multimodal Dataset","created":"2023-07-06","cited_by_count":2,"area":null},{"id":"2408.04102","title":"ArtVLM: Attribute Recognition Through Vision-Based Prefix Language Modeling","created":"2024-08-07","cited_by_count":2,"area":null},{"id":"2504.07247","title":"Resource-efficient Inference with Foundation Model Programs","created":"2025-04-09","cited_by_count":2,"area":null},{"id":"2603.09512","title":"Probing the Reliability of Driving VLMs: From Inconsistent Responses to Grounded Temporal Reasoning","created":"2026-03-10","cited_by_count":2,"area":"lr"},{"id":"2202.02567","title":"Catch Me if You Can: A Novel Task for Detection of Covert Geo-Locations (CGL)","created":"2022-02-05","cited_by_count":1,"area":null},{"id":"2312.17109","title":"MIVC: Multiple Instance Visual Component for Visual-Language Models","created":"2023-12-28","cited_by_count":1,"area":"mllm"},{"id":"2408.13898","title":"Evaluating Attribute Comprehension in Large Vision-Language Models","created":"2024-08-25","cited_by_count":1,"area":"mllm"},{"id":"2410.22648","title":"SimpsonsVQA: Enhancing Inquiry-Based Learning with a Tailored Dataset","created":"2024-10-30","cited_by_count":1,"area":null},{"id":"2501.11469","title":"MASS: Overcoming Language Bias in Image-Text Matching","created":"2025-01-20","cited_by_count":1,"area":"mllm"},{"id":"2502.18725","title":"Talking to the brain: Using Large Language Models as Proxies to Model Brain Semantic Representation","created":"2025-02-26","cited_by_count":1,"area":null},{"id":"2507.12916","title":"Argus: Leveraging Multiview Images for Improved 3-D Scene Understanding With Large Language Models","created":"2025-07-17","cited_by_count":1,"area":null},{"id":"2602.16138","title":"IRIS: Intent Resolution via Inference-time Saccades for Open-Ended VQA in Large Vision-Language Models","created":"2026-02-18","cited_by_count":1,"area":"mllm"},{"id":"2305.01668","title":"Visual Reasoning: from State to Transformation","created":"2023-05-02","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}