{"total":22,"rows":[{"id":"2502.01977","title":"AutoGUI: Scaling GUI Grounding with Automatic Functionality Annotations from LLMs","created":"2025-02-04","cited_by_count":19,"area":"mllm"},{"id":"2504.13861","title":"3MDBench: Medical Multimodal Multi-agent Dialogue Benchmark","created":"2025-03-26","cited_by_count":16,"area":"mllm"},{"id":"2503.17827","title":"4D-Bench: Benchmarking Multi-modal Large Language Models for 4D Object Understanding","created":"2025-03-22","cited_by_count":8,"area":"mllm"},{"id":"2509.26165","title":"Human-MME: A Holistic Evaluation Benchmark for Human-Centric Multimodal Large Language Models","created":"2025-09-30","cited_by_count":6,"area":"mllm"},{"id":"2503.23730","title":"KOFFVQA: An Objectively Evaluated Free-form VQA Benchmark for Large Vision-Language Models in the Korean Language","created":"2025-03-31","cited_by_count":5,"area":"mllm"},{"id":"2511.20515","title":"HalDec-Bench: Benchmarking Hallucination Detector in Image Captioning","created":"2025-11-25","cited_by_count":5,"area":"mllm"},{"id":"2605.16386","title":"Auditing Multimodal LLM Raters: Central Tendency Bias in Clinical Ordinal Scoring","created":"2026-05-11","cited_by_count":3,"area":"mllm"},{"id":"2412.11145","title":"The Superalignment of Superhuman Intelligence with Large Language Models","created":"2024-12-15","cited_by_count":2,"area":"mllm"},{"id":"2508.03079","title":"Bias Beyond Demographics: Probing Decision Boundaries in Black-Box LVLMs via Counterfactual VQA","created":"2025-08-05","cited_by_count":2,"area":"mllm"},{"id":"2509.08777","title":"Calibrating MLLM-as-a-judge via Multimodal Bayesian Prompt Ensembles","created":"2025-09-10","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":"2605.10850","title":"Verification Mirage: Mapping the Reliability Boundary of Self-Verification in Medical VQA","created":"2026-05-11","cited_by_count":2,"area":"mllm"},{"id":"2506.03371","title":"Toward Reliable VLM: A Fine-Grained Benchmark and Framework for Exposure, Bias, and Inference in Korean Street Views","created":"2025-06-03","cited_by_count":1,"area":"mllm"},{"id":"2604.11589","title":"MLLM-as-a-Judge Exhibits Model Preference Bias","created":"2026-04-13","cited_by_count":1,"area":"mllm"},{"id":"2510.27196","title":"MemeArena: Automating Context-Aware Unbiased Evaluation of Harmfulness Understanding for Multimodal Large Language Models","created":"2025-10-31","cited_by_count":0,"area":"mllm"},{"id":"2603.15253","title":"HalDec-Bench: Benchmarking Hallucination Detector in Image Captioning","created":"2026-03-16","cited_by_count":0,"area":"mllm"},{"id":"2604.24346","title":"SycoPhantasy: Quantifying Sycophancy and Hallucination in Small Open Weight VLMs for Vision-Language Scoring of Fantasy Characters","created":"2026-04-27","cited_by_count":0,"area":"mllm"},{"id":"2606.21194","title":"MEDLAYXPLAIN: Benchmarking the Expert-Lay Gap in Medical Vision-Language Models","created":"2026-06-19","cited_by_count":0,"area":"mllm"},{"id":"2608.03884","title":"BanglaWild: An In-the-Wild Bengali Scene Text Recognition Benchmark for OCR and Vision-Language Models","created":"2026-08-04","cited_by_count":0,"area":"mllm"},{"id":"2609.06245","title":"VDiff-Bench: A Challenging Benchmark for Fine-Grained Image Difference Identification","created":"2026-09-05","cited_by_count":0,"area":"mllm"},{"id":"2609.27395","title":"PRISM-VLM: A Multi-Axis Discriminative Benchmark for Compact Vision-Language Models","created":"2026-09-23","cited_by_count":0,"area":"mllm"},{"id":"2610.01670","title":"Do MLLM Judges Judge the Edit? Auditing Bias in Image Editing Evaluation with Verified Quality Preservation","created":"2026-10-01","cited_by_count":0,"area":"mllm"}],"next_cursor":null}