{"total":21,"rows":[{"id":"2312.14115","title":"LingoQA: Visual Question Answering for Autonomous Driving","created":"2023-12-21","cited_by_count":145,"area":"mllm"},{"id":"2406.02575","title":"Cross-Modal Safety Alignment: Is textual unlearning all you need?","created":"2024-05-27","cited_by_count":25,"area":"mllm"},{"id":"2412.13702","title":"Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models","created":"2024-12-18","cited_by_count":12,"area":"mllm"},{"id":"2406.10701","title":"MIND: Multimodal Shopping Intention Distillation from Large Vision-language Models for E-commerce Purchase Understanding","created":"2024-06-15","cited_by_count":10,"area":"mllm"},{"id":"2408.13461","title":"Probing the Robustness of Vision-Language Pretrained Models: A Multimodal Adversarial Attack Approach","created":"2024-08-24","cited_by_count":7,"area":"mllm"},{"id":"2410.02613","title":"NL-Eye: Abductive NLI for Images","created":"2024-10-03","cited_by_count":5,"area":"mllm"},{"id":"2411.04291","title":"Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models","created":"2024-11-06","cited_by_count":4,"area":"mllm"},{"id":"2505.20638","title":"Music Audio-Visual Question Answering Requires Specialized Multimodal Designs","created":"2025-05-27","cited_by_count":4,"area":"mllm"},{"id":"2602.21864","title":"DynamicGTR: Leveraging Graph Topology Representation Preferences to Boost VLM Capabilities on Graph QAs","created":"2026-02-25","cited_by_count":4,"area":"mllm"},{"id":"2605.31513","title":"Personalize Your Large Vision-language Models With In-context Prompt Tuning","created":"2026-05-29","cited_by_count":3,"area":"mllm"},{"id":"2503.15778","title":"AutoDrive-QA: A Multiple-Choice Benchmark for Vision-Language Evaluation in Urban Autonomous Driving","created":"2025-03-20","cited_by_count":2,"area":"mllm"},{"id":"2505.24007","title":"Preemptive Hallucination Reduction: An Input-Level Approach for Multimodal Language Model","created":"2025-05-29","cited_by_count":2,"area":"mllm"},{"id":"2508.10444","title":"DiFaR: Enhancing Multimodal Misinformation Detection with Diverse, Factual, and Relevant Rationales","created":"2025-08-14","cited_by_count":2,"area":"mllm"},{"id":"2504.09979","title":"Resampling Benchmark for Efficient Comprehensive Evaluation of Large Vision-Language Models","created":"2025-04-14","cited_by_count":1,"area":"mllm"},{"id":"2512.00087","title":"Exploring Automated Recognition of Instructional Activity and Discourse from Multimodal Classroom Data","created":"2025-11-26","cited_by_count":1,"area":"mllm"},{"id":"2607.11621","title":"Lesioned Multimodal Language Models Reproduce Aphasic Picture-Naming Patterns","created":"2026-07-13","cited_by_count":1,"area":"mllm"},{"id":"2608.15574","title":"Catching Hallucinated Citations in Video-LLM Question Answering: A Self-Verification Pipeline and Verifier Ablation Study","created":"2026-08-16","cited_by_count":1,"area":"mllm"},{"id":"2603.16113","title":"PathGLS: Evaluating Pathology Vision-Language Models without Ground Truth through Multi-Dimensional Consistency","created":"2026-03-17","cited_by_count":0,"area":"mllm"},{"id":"2609.01383","title":"InSight: A Benchmark for Agentic Claim Verification in Interactive Visualizations","created":"2026-09-01","cited_by_count":0,"area":"mllm"},{"id":"2610.07339","title":"A doctrine-grounded visual question answering dataset for Tactical Combat Casualty Care","created":"2026-10-05","cited_by_count":0,"area":"mllm"},{"id":"2610.19901","title":"Multimodal Medical Image Parsing with Task-Specific Low-Rank Adapters","created":"2026-10-14","cited_by_count":0,"area":"mllm"}],"next_cursor":null}