{"total":71,"rows":[{"id":"2111.12085","title":"UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling","created":"2021-11-23","cited_by_count":122,"area":"mllm"},{"id":"2212.00259","title":"Super-CLEVR: A Virtual Benchmark to Diagnose Domain Robustness in Visual Reasoning","created":"2022-12-01","cited_by_count":92,"area":"lr"},{"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":"2111.04138","title":"Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis","created":"2021-11-07","cited_by_count":65,"area":null},{"id":"2412.05149","title":"Findings of the Second BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora","created":"2024-12-06","cited_by_count":48,"area":null},{"id":"2501.00569","title":"Probing Visual Language Priors in VLMs","created":"2024-12-31","cited_by_count":45,"area":"lr"},{"id":"2205.14304","title":"Multimodal Fake News Detection via CLIP-Guided Learning","created":"2022-05-28","cited_by_count":42,"area":null},{"id":"2312.02896","title":"BenchLMM: Benchmarking Cross-style Visual Capability of Large Multimodal Models","created":"2023-12-05","cited_by_count":41,"area":"lr"},{"id":"2204.02285","title":"SwapMix: Diagnosing and Regularizing the Over-Reliance on Visual Context in Visual Question Answering","created":"2022-04-05","cited_by_count":38,"area":null},{"id":"2201.12382","title":"Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices","created":"2022-01-28","cited_by_count":37,"area":"lr"},{"id":"2201.05729","title":"CLIP-TD: CLIP Targeted Distillation for Vision-Language Tasks","created":"2022-01-15","cited_by_count":32,"area":null},{"id":"2404.10193","title":"Consistency and Uncertainty: Identifying Unreliable Responses From Black-Box Vision-Language Models for Selective Visual Question Answering","created":"2024-04-16","cited_by_count":32,"area":"mllm"},{"id":"2210.04692","title":"Language Prior Is Not the Only Shortcut: A Benchmark for Shortcut Learning in VQA","created":"2022-10-10","cited_by_count":30,"area":null},{"id":"2310.00647","title":"Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context Learning","created":"2023-10-01","cited_by_count":30,"area":"mllm"},{"id":"2511.04655","title":"Benchmark Designers Should \"Train on the Test Set\" to Expose Exploitable Non-Visual Shortcuts","created":"2025-11-06","cited_by_count":29,"area":"mllm"},{"id":"2207.02598","title":"Predicting is not Understanding: Recognizing and Addressing Underspecification in Machine Learning","created":"2022-07-06","cited_by_count":26,"area":null},{"id":"2206.05741","title":"Bootstrapping Multi-view Representations for Fake News Detection","created":"2022-06-12","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":"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":"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":"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":"2205.12466","title":"Eye-gaze-guided Vision Transformer for Rectifying Shortcut Learning","created":"2022-05-25","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":"2306.03932","title":"Q: How to Specialize Large Vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images!","created":"2023-06-06","cited_by_count":19,"area":"mllm"},{"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":"2304.00827","title":"Multi-modal Fake News Detection on Social Media via Multi-grained Information Fusion","created":"2023-04-03","cited_by_count":15,"area":null},{"id":"2206.08567","title":"Rectify ViT Shortcut Learning by Visual Saliency","created":"2022-06-17","cited_by_count":14,"area":null},{"id":"2411.11288","title":"Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognition","created":"2024-11-18","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":"2409.14057","title":"Co-occurrence is not Factual Association in Language Models","created":"2024-09-21","cited_by_count":12,"area":null},{"id":"2403.12693","title":"As Firm As Their Foundations: Can open-sourced foundation models be used to create adversarial examples for downstream tasks?","created":"2024-03-19","cited_by_count":11,"area":null},{"id":"2502.15895","title":"Directional Gradient Projection for Robust Fine-Tuning of Foundation Models","created":"2025-02-21","cited_by_count":11,"area":null},{"id":"2305.06407","title":"Combo of Thinking and Observing for Outside-Knowledge VQA","created":"2023-05-10","cited_by_count":9,"area":null},{"id":"2411.01713","title":"Rethinking Weight Decay for Robust Fine-Tuning of Foundation Models","created":"2024-11-03","cited_by_count":9,"area":null},{"id":"2306.08889","title":"Dissecting Multimodality in VideoQA Transformer Models by Impairing Modality Fusion","created":"2023-06-15","cited_by_count":8,"area":null},{"id":"2405.17613","title":"Jointly Modeling Inter- & Intra-Modality Dependencies for Multi-modal Learning","created":"2024-05-27","cited_by_count":8,"area":null},{"id":"2106.05597","title":"Supervising the Transfer of Reasoning Patterns in VQA","created":"2021-06-10","cited_by_count":7,"area":null},{"id":"2209.06954","title":"Correlation Information Bottleneck: Towards Adapting Pretrained Multimodal Models for Robust Visual Question Answering","created":"2022-09-14","cited_by_count":7,"area":"mllm"},{"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":"2303.09427","title":"Logical Implications for Visual Question Answering Consistency","created":"2023-03-16","cited_by_count":6,"area":"lr"},{"id":"2407.08707","title":"Extracting Training Data from Document-Based VQA Models","created":"2024-07-11","cited_by_count":6,"area":"mllm"},{"id":"2211.05895","title":"Understanding ME? Multimodal Evaluation for Fine-grained Visual Commonsense","created":"2022-11-10","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":"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":"2111.10756","title":"TraVLR: Now You See It, Now You Don't! A Bimodal Dataset for Evaluating Visio-Linguistic Reasoning","created":"2021-11-21","cited_by_count":4,"area":null},{"id":"2309.03726","title":"Interpretable Visual Question Answering via Reasoning Supervision","created":"2023-09-07","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":"2401.10712","title":"Q&A Prompts: Discovering Rich Visual Clues through Mining Question-Answer Prompts for VQA requiring Diverse World Knowledge","created":"2024-01-19","cited_by_count":3,"area":"lr"},{"id":"2509.23499","title":"Multi-modal Data Spectrum: Multi-modal Datasets are Multi-dimensional","created":"2025-09-27","cited_by_count":3,"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":"2512.22183","title":"Unbiased Visual Reasoning with Controlled Visual Inputs","created":"2025-12-19","cited_by_count":2,"area":"lr"},{"id":"2411.19688","title":"SURE-VQA: Systematic Understanding of Robustness Evaluation in Medical VQA Tasks","created":"2024-11-29","cited_by_count":1,"area":"mllm"},{"id":"2506.17903","title":"Cause-Effect Driven Optimization for Robust Medical Visual Question Answering with Language Biases","created":"2025-06-22","cited_by_count":1,"area":null},{"id":"2603.02865","title":"Nodes Are Early, Edges Are Late: Probing Diagram Representations in Large Vision-Language Models","created":"2026-03-03","cited_by_count":1,"area":"mllm"},{"id":"2606.29915","title":"H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning","created":"2026-06-29","cited_by_count":1,"area":"lr"},{"id":"2606.30220","title":"From Accuracy to Visual Dependence: Auditing and Filtering Modality Collapse in Traffic VideoQA","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2607.13305","title":"Accuracy Without Grounding: Diagnosing Visual Dependency Dissociation in Video LLM Benchmarks","created":"2026-07-14","cited_by_count":1,"area":null},{"id":"2206.14355","title":"EBMs vs. CL: Exploring Self-Supervised Visual Pretraining for Visual Question Answering","created":"2022-06-29","cited_by_count":0,"area":null},{"id":"2211.11190","title":"Cross-Modal Contrastive Learning for Robust Reasoning in VQA","created":"2022-11-21","cited_by_count":0,"area":null},{"id":"2301.08874","title":"Improving Zero-Shot Action Recognition using Human Instruction with Text Description","created":"2023-01-21","cited_by_count":0,"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":"2505.12861","title":"RMMSS: Towards Advanced Robust Multi-Modal Semantic Segmentation with Hybrid Prototype Distillation and Feature Selection","created":"2025-05-19","cited_by_count":0,"area":"distill"},{"id":"2506.12394","title":"LARGO: Low-Rank Regulated Gradient Projection for Robust Parameter Efficient Fine-Tuning","created":"2025-06-14","cited_by_count":0,"area":null},{"id":"2507.01800","title":"HCNQA: Enhancing 3D VQA with Hierarchical Concentration Narrowing Supervision","created":"2025-07-02","cited_by_count":0,"area":"lr"},{"id":"2602.16979","title":"Characterizing the Predictive Impact of Modalities with Supervised Latent-Variable Modeling","created":"2026-02-19","cited_by_count":0,"area":"mllm"},{"id":"2605.14787","title":"Do Composed Image Retrieval Benchmarks Require Multimodal Composition?","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2607.16105","title":"Attention-Guided Saliency Maps for Interpreting Visualization Literacy in VLMs","created":"2026-07-17","cited_by_count":0,"area":"mllm"},{"id":"2609.03142","title":"Sensing Which Modality Matters: Evidence-Gated Regularization for Robust VLA Policies","created":"2026-09-02","cited_by_count":0,"area":"vla"},{"id":"2609.34563","title":"Rethinking Latent Visual Reasoning: Grounding Latent Reasoning in Visual Evidence","created":"2026-09-28","cited_by_count":0,"area":"lr"}],"next_cursor":null}