{"total":14,"rows":[{"id":"2412.02104","title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey","created":"2024-12-03","cited_by_count":52,"area":"mllm"},{"id":"2502.12520","title":"SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning","created":"2025-02-18","cited_by_count":32,"area":"mllm"},{"id":"2408.09429","title":"Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Models","created":"2024-08-18","cited_by_count":30,"area":"mllm"},{"id":"2502.11051","title":"MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Models","created":"2025-02-16","cited_by_count":30,"area":"mllm"},{"id":"2408.17267","title":"UrBench: A Comprehensive Benchmark for Evaluating Large Multimodal Models in Multi-View Urban Scenarios","created":"2024-08-30","cited_by_count":28,"area":"mllm"},{"id":"2410.04819","title":"MINER: Mining the Underlying Pattern of Modality-Specific Neurons in Multimodal Large Language Models","created":"2024-10-07","cited_by_count":7,"area":"mllm"},{"id":"2502.11916","title":"EssayJudge: A Multi-Granular Benchmark for Assessing Automated Essay Scoring Capabilities of Multimodal Large Language Models","created":"2025-02-17","cited_by_count":7,"area":"mllm"},{"id":"2506.00530","title":"CityLens: Evaluating Large Vision-Language Models for Urban Socioeconomic Sensing","created":"2025-05-31","cited_by_count":7,"area":"mllm"},{"id":"2603.02435","title":"VL-KGE: Vision-Language Models Meet Knowledge Graph Embeddings","created":"2026-03-02","cited_by_count":2,"area":"mllm"},{"id":"2512.03558","title":"CartoMapQA: A Fundamental Benchmark Dataset Evaluating Vision-Language Models on Cartographic Map Understanding","created":"2025-12-03","cited_by_count":1,"area":"mllm"},{"id":"2602.19442","title":"UrbanAlign: Post-hoc Semantic Calibration for VLM-Human Preference Alignment","created":"2026-02-23","cited_by_count":1,"area":"mllm"},{"id":"2606.00871","title":"Benchmarks for Vision-Language Models in Urban Perception Should Be Reliability-Aware and Negotiated","created":"2026-05-30","cited_by_count":1,"area":"mllm"},{"id":"2606.15890","title":"UrbanWell: Benchmarking Multimodal Large Language Models for Spatio-Temporal Urban Wellbeing Analytics","created":"2026-06-14","cited_by_count":0,"area":"mllm"},{"id":"2608.01753","title":"Can Urban Blight Be Accessed with Vision-language Models: A Case Study in Detroit","created":"2026-08-03","cited_by_count":0,"area":"mllm"}],"next_cursor":null}