{"total":71,"rows":[{"id":"2406.16860","title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","created":"2024-06-24","cited_by_count":838,"area":"mllm"},{"id":"2210.01936","title":"When and why vision-language models behave like bags-of-words, and what to do about it?","created":"2022-10-04","cited_by_count":610,"area":"mllm"},{"id":"2501.09425","title":"Vision-Language Models Do Not Understand Negation","created":"2025-01-16","cited_by_count":72,"area":"mllm"},{"id":"2312.00825","title":"SocialCounterfactuals: Probing and Mitigating Intersectional Social Biases in Vision-Language Models with Counterfactual Examples","created":"2023-11-30","cited_by_count":53,"area":"mllm"},{"id":"2310.02224","title":"Can Language Models be Instructed to Protect Personal Information?","created":"2023-10-03","cited_by_count":46,"area":"mllm"},{"id":"2312.00081","title":"Synthesize, Diagnose, and Optimize: Towards Fine-Grained Vision-Language Understanding","created":"2023-11-30","cited_by_count":46,"area":"mllm"},{"id":"2406.17126","title":"MM-SpuBench: Towards Better Understanding of Spurious Biases in Multimodal LLMs","created":"2024-06-24","cited_by_count":33,"area":"mllm"},{"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":"2310.01651","title":"Fool Your (Vision and) Language Model With Embarrassingly Simple Permutations","created":"2023-10-02","cited_by_count":25,"area":"mllm"},{"id":"2403.09193","title":"Can We Talk Models Into Seeing the World Differently?","created":"2024-03-14","cited_by_count":23,"area":"mllm"},{"id":"2407.15913","title":"Test-Time Low Rank Adaptation via Confidence Maximization for Zero-Shot Generalization of Vision-Language Models","created":"2024-07-22","cited_by_count":17,"area":"mllm"},{"id":"2402.17510","title":"Demonstrating and Reducing Shortcuts in Vision-Language Representation Learning","created":"2024-02-27","cited_by_count":14,"area":"mllm"},{"id":"2506.18322","title":"Escaping the SpuriVerse: Can Large Vision-Language Models Generalize Beyond Seen Spurious Correlations?","created":"2025-06-23","cited_by_count":14,"area":"mllm"},{"id":"2410.01534","title":"Toward a Holistic Evaluation of Robustness in CLIP Models","created":"2024-10-02","cited_by_count":13,"area":"mllm"},{"id":"2502.14044","title":"Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data","created":"2025-02-19","cited_by_count":12,"area":"mllm"},{"id":"2605.12369","title":"GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization","created":"2026-05-12","cited_by_count":10,"area":"mllm"},{"id":"2607.03647","title":"Do Medical Vision Language Models Actually See? A Counterfactual Grounding Framework and Hard-Negative Contrastive Training for Visually-Reliant Medical VLMs","created":"2026-07-04","cited_by_count":7,"area":"mllm"},{"id":"2310.02988","title":"Probing Intersectional Biases in Vision-Language Models with Counterfactual Examples","created":"2023-10-04","cited_by_count":5,"area":"mllm"},{"id":"2505.13946","title":"Visual Instruction Bottleneck Tuning","created":"2025-05-20","cited_by_count":5,"area":"mllm"},{"id":"2511.18921","title":"BackdoorVLM: A Benchmark for Backdoor Attacks and Defenses on Vision-Language Models","created":"2025-11-24","cited_by_count":5,"area":"mllm"},{"id":"2602.21035","title":"Not Just What's There: Enabling CLIP to Comprehend Negated Visual Descriptions Without Fine-tuning","created":"2026-02-24","cited_by_count":5,"area":"mllm"},{"id":"2502.15678","title":"Testing the Limits of Fine-Tuning for Improving Visual Cognition in Vision Language Models","created":"2025-02-21","cited_by_count":4,"area":"mllm"},{"id":"2602.15183","title":"Seeing to Generalize: How Visual Data Corrects Binding Shortcuts","created":"2026-02-16","cited_by_count":4,"area":"mllm"},{"id":"2603.13341","title":"Mind the Discriminability Trap in Source-Free Cross-domain Few-shot Learning","created":"2026-03-07","cited_by_count":4,"area":"mllm"},{"id":"2510.03906","title":"From Filters to VLMs: Benchmarking Defogging Methods through Object Detection and Segmentation Performance","created":"2025-10-04","cited_by_count":3,"area":"mllm"},{"id":"2511.12978","title":"Concept Regions Matter: Benchmarking CLIP with a New Cluster-Importance Approach","created":"2025-11-17","cited_by_count":3,"area":"mllm"},{"id":"2511.19220","title":"Are Large Vision Language Models Truly Grounded in Medical Images? Evidence from Italian Clinical Visual Question Answering","created":"2025-11-24","cited_by_count":3,"area":"mllm"},{"id":"2509.21247","title":"Learning to Look: Cognitive Attention Alignment with Vision-Language Models","created":"2025-09-25","cited_by_count":2,"area":"mllm"},{"id":"2510.26466","title":"Representation-Level Counterfactual Calibration for Debiased Zero-Shot Recognition","created":"2025-10-30","cited_by_count":2,"area":"mllm"},{"id":"2602.06033","title":"Can Vision Language Models Learn Intuitive Physics from Interaction?","created":"2026-02-05","cited_by_count":2,"area":"mllm"},{"id":"2606.17710","title":"Vision-language models for chest radiography do not always need the image","created":"2026-06-16","cited_by_count":2,"area":"mllm"},{"id":"2408.09706","title":"MePT: Multi-Representation Guided Prompt Tuning for Vision-Language Model","created":"2024-08-19","cited_by_count":1,"area":"mllm"},{"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":"2503.08368","title":"Debiased Prompt Tuning in Vision-Language Model without Annotations","created":"2025-03-11","cited_by_count":1,"area":"mllm"},{"id":"2504.21344","title":"Vision-Language Model-Based Semantic-Guided Imaging Biomarker for Lung Nodule Malignancy Prediction","created":"2025-04-30","cited_by_count":1,"area":"mllm"},{"id":"2511.13005","title":"SAGE: Spuriousness-Aware Guided Prompt Exploration for Mitigating Multimodal Bias","created":"2025-11-17","cited_by_count":1,"area":"mllm"},{"id":"2603.15134","title":"Confusion-Aware In-Context-Learning for Vision-Language Models in Robotic Manipulation","created":"2026-03-16","cited_by_count":1,"area":"mllm"},{"id":"2603.20985","title":"Consistent but Dangerous: Per-Sample Safety Classification Reveals False Reliability in Medical Vision-Language Models","created":"2026-03-22","cited_by_count":1,"area":"mllm"},{"id":"2604.11632","title":"CArtBench: Evaluating Vision-Language Models on Chinese Art Understanding, Interpretation, and Authenticity","created":"2026-04-13","cited_by_count":1,"area":"mllm"},{"id":"2606.13288","title":"Cross-Modal Masked Compositional Concept Modeling for Enhancing Visio-Linguistic Compositionality","created":"2026-06-11","cited_by_count":1,"area":"mllm"},{"id":"2606.20244","title":"SPOT-E: Test-Time Entropy Shaping with Visual Spotlights for Frozen VLMs","created":"2026-06-18","cited_by_count":1,"area":"mllm"},{"id":"2412.04939","title":"Verb Mirage: Unveiling and Assessing Verb Concept Hallucinations in Multimodal Large Language Models","created":"2024-12-06","cited_by_count":0,"area":"mllm"},{"id":"2507.08000","title":"Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models","created":"2025-07-10","cited_by_count":0,"area":"mllm"},{"id":"2509.23781","title":"GroupCoOp: Group-robust Fine-tuning via Group Prompt Learning","created":"2025-09-28","cited_by_count":0,"area":"mllm"},{"id":"2511.11831","title":"TopoPerception: A Shortcut-Free Evaluation of Global Visual Perception in Large Vision-Language Models","created":"2025-11-14","cited_by_count":0,"area":"mllm"},{"id":"2603.28387","title":"Prompts Without Evidence: How Neuroimaging Mentions Shift Clinical Vision-Language Model Predictions","created":"2026-03-30","cited_by_count":0,"area":"mllm"},{"id":"2604.13803","title":"Gaslight, Gatekeep, V1-V3: Early Visual Cortex Alignment Shields Vision-Language Models from Sycophantic Manipulation","created":"2026-04-15","cited_by_count":0,"area":"mllm"},{"id":"2605.13047","title":"Revealing the Gap in Human and VLM Scene Perception through Counterfactual Semantic Saliency","created":"2026-05-13","cited_by_count":0,"area":"mllm"},{"id":"2605.27315","title":"Real Images, Worse Judgments: Evaluating Vision-Language Models on Concreteness and Imagery","created":"2026-05-26","cited_by_count":0,"area":"mllm"},{"id":"2605.31312","title":"Learning from Fine-Grained Visual Discrepancies: Mitigating Multimodal Hallucinations via In-Context Visual Contrastive Optimization","created":"2026-05-29","cited_by_count":0,"area":"mllm"},{"id":"2606.14740","title":"GridVQA-X: A Framework for Evaluating Multimodal Explainability Methods","created":"2026-06-02","cited_by_count":0,"area":"mllm"},{"id":"2606.29232","title":"When Does Synthetic CT Transfer? A Label-Free Donor/Host Diagnostic for Medical Vision-Language Model Routing on Real Lung CT","created":"2026-06-28","cited_by_count":0,"area":"mllm"},{"id":"2606.30201","title":"SHOVIR: A Benchmark for Evaluating Vision Shortcut Learning in Radiology Report Generation","created":"2026-06-29","cited_by_count":0,"area":"mllm"},{"id":"2607.13597","title":"Semantic Anchoring for Robotic Action Representations","created":"2026-07-15","cited_by_count":0,"area":"mllm"},{"id":"2607.28211","title":"Scaling Vision-Language Models Is Not Enough to Mitigate Bias","created":"2026-07-30","cited_by_count":0,"area":"mllm"},{"id":"2608.02252","title":"HarMoE: Multi-Source Chest Radiograph Pretraining with Dataset-Disentangled Experts","created":"2026-08-03","cited_by_count":0,"area":"mllm"},{"id":"2608.06154","title":"Visual Grounding in Zero-Shot Vision-Language Control","created":"2026-08-06","cited_by_count":0,"area":"mllm"},{"id":"2608.12086","title":"Look What the Probes Dragged In! Real-World Chest X-ray Shortcuts in MedCLIP","created":"2026-08-12","cited_by_count":0,"area":"mllm"},{"id":"2608.17306","title":"Learning What Not to Learn: Adversarial Disentangled Prompt Tuning for Robust Vision-Language Models","created":"2026-08-18","cited_by_count":0,"area":"mllm"},{"id":"2608.24118","title":"MC-CXR: A Multi-Context Chest X-ray Benchmark for Context-Induced Disruption in Vision-Language Models","created":"2026-08-25","cited_by_count":0,"area":"mllm"},{"id":"2608.29996","title":"Partition-Aware Unlearning for Removing Spurious Correlations in Large Vision-Language Models","created":"2026-08-30","cited_by_count":0,"area":"mllm"},{"id":"2608.30210","title":"Frontier vision-language models have overtaken young adults at detecting AI-generated portraits -- but not their calibration","created":"2026-08-31","cited_by_count":0,"area":"mllm"},{"id":"2608.30712","title":"GUIDE: Guiding Internal Evidence with Language Instructions","created":"2026-08-31","cited_by_count":0,"area":"mllm"},{"id":"2609.03985","title":"IchthyoNoma: Nomenclature and Context Sensitivity of Zero-Shot Biological Vision--Language Models for Bangladeshi Freshwater Fish Recognition","created":"2026-09-03","cited_by_count":0,"area":"mllm"},{"id":"2609.04014","title":"InSituMeasure: Probing Situated Measurement Grounding in Industrial Scenes with Multimodal Large Language Models","created":"2026-09-03","cited_by_count":0,"area":"mllm"},{"id":"2609.13308","title":"GroundBench: A Factorized, Counterfactual Benchmark for Locating VLM Affordance Failures","created":"2026-09-10","cited_by_count":0,"area":"mllm"},{"id":"2609.31356","title":"Open Vocabulary Domain Unlearning","created":"2026-09-25","cited_by_count":0,"area":"mllm"},{"id":"2609.31450","title":"From Reward Signal to Visual Utility: A Controlled Audit of Medical VLM Post-Training","created":"2026-09-25","cited_by_count":0,"area":"mllm"},{"id":"2609.32653","title":"From Knowing to Abstaining: Bridging the Representation-Action Gap in Vision-Language Models","created":"2026-09-26","cited_by_count":0,"area":"mllm"},{"id":"2610.15467","title":"Semantic Saliency from Multi-Modal Large Language Model Scene Understanding Maps","created":"2026-10-11","cited_by_count":0,"area":"mllm"}],"next_cursor":null}