{"total":42,"rows":[{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"id":"2203.01225","title":"Video Question Answering: Datasets, Algorithms and Challenges","created":"2022-03-02","cited_by_count":84,"area":null},{"id":"2106.02280","title":"Human-Adversarial Visual Question Answering","created":"2021-06-04","cited_by_count":57,"area":null},{"id":"2110.02526","title":"Coarse-to-Fine Reasoning for Visual Question Answering","created":"2021-10-06","cited_by_count":25,"area":null},{"id":"2306.08751","title":"Improving Selective Visual Question Answering by Learning from Your Peers","created":"2023-06-14","cited_by_count":25,"area":null},{"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":"2212.09993","title":"Are Deep Neural Networks SMARTer than Second Graders?","created":"2022-12-20","cited_by_count":24,"area":null},{"id":"2203.06414","title":"A Survey of Adversarial Defences and Robustness in NLP","created":"2022-03-12","cited_by_count":23,"area":null},{"id":"2203.07653","title":"Generalized but not Robust? Comparing the Effects of Data Modification Methods on Out-of-Domain Generalization and Adversarial Robustness","created":"2022-03-15","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":"2205.12191","title":"Reassessing Evaluation Practices in Visual Question Answering: A Case Study on Out-of-Distribution Generalization","created":"2022-05-24","cited_by_count":20,"area":null},{"id":"2404.12020","title":"Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question Answering","created":"2024-04-18","cited_by_count":18,"area":null},{"id":"2204.01906","title":"Dynatask: A Framework for Creating Dynamic AI Benchmark Tasks","created":"2022-04-05","cited_by_count":16,"area":null},{"id":"2407.03386","title":"Visual Robustness Benchmark for Visual Question Answering (VQA)","created":"2024-07-03","cited_by_count":12,"area":null},{"id":"2110.07165","title":"Semantically Distributed Robust Optimization for Vision-and-Language Inference","created":"2021-10-14","cited_by_count":9,"area":null},{"id":"2209.05401","title":"MaXM: Towards Multilingual Visual Question Answering","created":"2022-09-12","cited_by_count":9,"area":null},{"id":"2511.19413","title":"UniGame: Turning a Unified Multimodal Model Into Its Own Adversary","created":"2025-11-24","cited_by_count":9,"area":null},{"id":"2110.08438","title":"Unsupervised Natural Language Inference Using PHL Triplet Generation","created":"2021-10-16","cited_by_count":6,"area":null},{"id":"2112.04453","title":"MLP Architectures for Vision-and-Language Modeling: An Empirical Study","created":"2021-12-08","cited_by_count":6,"area":null},{"id":"2408.13175","title":"Identifying Crucial Objects in Blind and Low-Vision Individuals' Navigation","created":"2024-08-23","cited_by_count":6,"area":null},{"id":"2306.01125","title":"Reconstruction Distortion of Learned Image Compression with Imperceptible Perturbations","created":"2023-06-01","cited_by_count":5,"area":null},{"id":"2407.16777","title":"A Dataset for Crucial Object Recognition in Blind and Low-Vision Individuals' Navigation","created":"2024-07-23","cited_by_count":5,"area":null},{"id":"2505.21755","title":"FRAMES-VQA: Benchmarking Fine-Tuning Robustness across Multi-Modal Shifts in Visual Question Answering","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2211.02646","title":"Robustness of Fusion-based Multimodal Classifiers to Cross-Modal Content Dilutions","created":"2022-11-04","cited_by_count":4,"area":null},{"id":"2505.21027","title":"TabAttackBench: A Benchmark for Adversarial Attacks on Tabular Data","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2508.13428","title":"Mitigating Easy Option Bias in Multiple-Choice Question Answering","created":"2025-08-19","cited_by_count":4,"area":null},{"id":"2306.11065","title":"Cross-Modal Attribute Insertions for Assessing the Robustness of Vision-and-Language Learning","created":"2023-06-19","cited_by_count":3,"area":null},{"id":"2406.03728","title":"Evaluating Durability: Benchmark Insights into Multimodal Watermarking","created":"2024-06-06","cited_by_count":3,"area":null},{"id":"2606.08277","title":"Remember with Confidence: Uncertainty Quantification for Spatio-temporal Memory with Probabilistic Guarantees","created":"2026-06-06","cited_by_count":3,"area":null},{"id":"2110.05159","title":"Beyond Accuracy: A Consolidated Tool for Visual Question Answering Benchmarking","created":"2021-10-11","cited_by_count":2,"area":null},{"id":"2207.01772","title":"Vision-and-Language Pretraining","created":"2022-07-05","cited_by_count":2,"area":null},{"id":"2307.03798","title":"Fooling Contrastive Language-Image Pre-trained Models with CLIPMasterPrints","created":"2023-07-07","cited_by_count":2,"area":null},{"id":"2310.12147","title":"InViG: Benchmarking Interactive Visual Grounding with 500K Human-Robot Interactions","created":"2023-10-18","cited_by_count":2,"area":null},{"id":"2506.10912","title":"Breaking Bad Molecules: Are MLLMs Ready for Structure-Level Molecular Detoxification?","created":"2025-06-12","cited_by_count":2,"area":null},{"id":"2301.12032","title":"BinaryVQA: A Versatile Test Set to Evaluate the Out-of-Distribution Generalization of VQA Models","created":"2023-01-28","cited_by_count":1,"area":null},{"id":"2307.10405","title":"Generative Visual Question Answering","created":"2023-07-18","cited_by_count":1,"area":null},{"id":"2310.07259","title":"Uncovering Hidden Connections: Iterative Search and Reasoning for Video-grounded Dialog","created":"2023-10-11","cited_by_count":1,"area":null},{"id":"2604.21766","title":"AUDITA: A New Dataset to Audit Humans vs. AI Skill at Audio QA","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2501.08771","title":"Admitting Ignorance Helps the Video Question Answering Models to Answer","created":"2025-01-15","cited_by_count":0,"area":null},{"id":"2607.16243","title":"RobustMAD: Evaluating Real-World Robustness of Multimodal Small Language Models for Deployable Anomaly Detection Assistants","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2609.34480","title":"When Does an Image Determine the Answer? Benchmarking Visual Answerability across Charts and Scenes","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.34967","title":"Semantic Uncertainty Quantification Needs Factual Equivalence","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}