{"total":23,"rows":[{"id":"2504.14348","title":"Manipulating Multimodal Agents via Cross-Modal Prompt Injection","created":"2025-04-19","cited_by_count":44,"area":"mllm"},{"id":"2504.09083","title":"Using Vision Language Models for Safety Hazard Identification in Construction","created":"2025-04-12","cited_by_count":13,"area":"mllm"},{"id":"2510.00047","title":"Explanation-Driven Counterfactual Testing for Faithfulness in Vision-Language Model Explanations","created":"2025-09-27","cited_by_count":12,"area":"mllm"},{"id":"2601.06843","title":"Speak While Watching: Unleashing TRUE Real-Time Video Understanding Capability of Multimodal Large Language Models","created":"2026-01-11","cited_by_count":8,"area":"mllm"},{"id":"2605.22645","title":"AtelierEval: Agentic Evaluation of Humans & LLMs as Text-to-Image Prompters","created":"2026-05-21","cited_by_count":8,"area":"mllm"},{"id":"2502.14834","title":"LongWriter-V: Enabling Ultra-Long and High-Fidelity Generation in Vision-Language Models","created":"2025-02-20","cited_by_count":5,"area":"mllm"},{"id":"2602.06013","title":"GenArena: How Can We Achieve Human-Aligned Evaluation for Visual Generation Tasks?","created":"2026-02-05","cited_by_count":4,"area":"mllm"},{"id":"2603.09573","title":"More than the Sum: Panorama-Language Models for Adverse Omni-Scenes","created":"2026-03-10","cited_by_count":4,"area":"mllm"},{"id":"2604.18164","title":"MM-JudgeBias: A Benchmark for Evaluating Compositional Biases in MLLM-as-a-Judge","created":"2026-04-20","cited_by_count":4,"area":"mllm"},{"id":"2603.16934","title":"AgriChat: A Multimodal Large Language Model for Agriculture Image Understanding","created":"2026-03-14","cited_by_count":3,"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":"2509.08777","title":"Calibrating MLLM-as-a-judge via Multimodal Bayesian Prompt Ensembles","created":"2025-09-10","cited_by_count":2,"area":"mllm"},{"id":"2510.20743","title":"Empathic Prompting: Non-Verbal Context Integration for Multimodal LLM Conversations","created":"2025-10-23","cited_by_count":2,"area":"mllm"},{"id":"2507.12414","title":"AutoVDC: Automated Vision Data Cleaning Using Vision-Language Models","created":"2025-07-16","cited_by_count":1,"area":"mllm"},{"id":"2603.08800","title":"Granulon: Awakening Pixel-Level Visual Encoders with Adaptive Multi-Granularity Semantics for MLLM","created":"2026-03-09","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":"2604.20544","title":"Evian: Towards Explainable Visual Instruction-tuning Data Auditing","created":"2026-04-22","cited_by_count":1,"area":"mllm"},{"id":"2606.25084","title":"Are We There Yet? Exploring the Capabilities of MLLMs in Assistive AI Applications","created":"2026-06-23","cited_by_count":1,"area":"mllm"},{"id":"2502.16137","title":"Chain-of-Description: What I can understand, I can put into words","created":"2025-02-22","cited_by_count":0,"area":"mllm"},{"id":"2609.03611","title":"FailBench: How Reliable are VLMs at Judging Robot Task Success?","created":"2026-09-03","cited_by_count":0,"area":"mllm"},{"id":"2609.17953","title":"EDCT-Bench: Uncovering Faithfulness Gaps in VLMs via Explanation-Driven Counterfactual Testing","created":"2026-09-16","cited_by_count":0,"area":"mllm"},{"id":"2609.22778","title":"MIS-Bench: Benchmarking Multimodal LLMs for Psychotherapeutic Interpersonal Skills Assessment","created":"2026-09-19","cited_by_count":0,"area":"mllm"},{"id":"2609.25040","title":"BananaVLM: A Domain-Adapted Vision Language Model for Banana Crop Disease Diagnosis","created":"2026-08-27","cited_by_count":0,"area":"mllm"}],"next_cursor":null}