{"total":19,"rows":[{"id":"2308.02490","title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","created":"2023-08-04","cited_by_count":1239,"area":"mllm"},{"id":"2402.04788","title":"MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark","created":"2024-02-07","cited_by_count":372,"area":"mllm"},{"id":"2312.06742","title":"Honeybee: Locality-enhanced Projector for Multimodal LLM","created":"2023-12-11","cited_by_count":197,"area":"mllm"},{"id":"2406.06004","title":"FLEUR: An Explainable Reference-Free Evaluation Metric for Image Captioning Using a Large Multimodal Model","created":"2024-06-10","cited_by_count":45,"area":"mllm"},{"id":"2403.17830","title":"Assessment of Multimodal Large Language Models in Alignment with Human Values","created":"2024-03-26","cited_by_count":36,"area":"mllm"},{"id":"2404.13306","title":"FakeBench: Probing Explainable Fake Image Detection via Large Multimodal Models","created":"2024-04-20","cited_by_count":36,"area":"mllm"},{"id":"2508.04650","title":"EncQA: Benchmarking Vision-Language Models on Visual Encodings for Charts","created":"2025-08-06","cited_by_count":12,"area":"mllm"},{"id":"2501.07244","title":"Can Vision-Language Models Evaluate Handwritten Math?","created":"2025-01-13","cited_by_count":10,"area":"mllm"},{"id":"2412.03565","title":"INST-IT: Boosting Instance Understanding via Explicit Visual Prompt Instruction Tuning","created":"2024-12-04","cited_by_count":8,"area":"mllm"},{"id":"2502.15210","title":"PairBench: Are Vision-Language Models Reliable at Comparing What They See?","created":"2025-02-21","cited_by_count":6,"area":"mllm"},{"id":"2507.19362","title":"LOTUS: A Leaderboard for Detailed Image Captioning from Quality to Societal Bias and User Preferences","created":"2025-07-25","cited_by_count":2,"area":"mllm"},{"id":"2601.14569","title":"Social Caption: Evaluating Social Understanding in Multimodal Models","created":"2026-01-21","cited_by_count":2,"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":"2510.09253","title":"On the Robustness of Vision-Language Models in Zero-shot Privacy Classification","created":"2025-10-10","cited_by_count":1,"area":"mllm"},{"id":"2602.07931","title":"Which private attributes do VLMs agree on and predict well?","created":"2026-02-08","cited_by_count":0,"area":"mllm"},{"id":"2603.26769","title":"Edge Reliability Gap in Vision-Language Models: Quantifying Failure Modes of Compressed VLMs Under Visual Corruption","created":"2026-03-24","cited_by_count":0,"area":"mllm"},{"id":"2605.28215","title":"Explaining is Harder Than Predicting Alone: Evaluating Concept-based Explanations of MLLMs as ICL Visual Classifiers","created":"2026-05-27","cited_by_count":0,"area":"mllm"},{"id":"2608.11816","title":"How China-Origin Vision-Language Models Move from Refusal to Reframing in State Alignment","created":"2026-08-12","cited_by_count":0,"area":"mllm"},{"id":"2609.31690","title":"Adapting Vision-Language Models for Human-Readable XAI in Industrial Object Detection","created":"2026-09-17","cited_by_count":0,"area":"mllm"}],"next_cursor":null}