{"total":22,"rows":[{"id":"2308.06595","title":"VisIT-Bench: A Benchmark for Vision-Language Instruction Following Inspired by Real-World Use","created":"2023-08-12","cited_by_count":102,"area":"mllm"},{"id":"2405.01474","title":"Understanding Figurative Meaning through Explainable Visual Entailment","created":"2024-05-02","cited_by_count":19,"area":"mllm"},{"id":"2402.11281","title":"Can Large Multimodal Models Uncover Deep Semantics Behind Images?","created":"2024-02-17","cited_by_count":17,"area":"mllm"},{"id":"2410.13854","title":"Can MLLMs Understand the Deep Implication Behind Chinese Images?","created":"2024-10-17","cited_by_count":14,"area":"mllm"},{"id":"2404.02415","title":"What Are We Measuring When We Evaluate Large Vision-Language Models? An Analysis of Latent Factors and Biases","created":"2024-04-03","cited_by_count":13,"area":"mllm"},{"id":"2407.03000","title":"VIVA: A Benchmark for Vision-Grounded Decision-Making with Human Values","created":"2024-07-03","cited_by_count":12,"area":"mllm"},{"id":"2405.19088","title":"Cracking the Code of Juxtaposition: Can AI Models Understand the Humorous Contradictions","created":"2024-05-29","cited_by_count":11,"area":"mllm"},{"id":"2406.10318","title":"Creating a Lens of Chinese Culture: A Multimodal Dataset for Chinese Pun Rebus Art Understanding","created":"2024-06-14","cited_by_count":11,"area":"mllm"},{"id":"2409.13592","title":"YesBut: A High-Quality Annotated Multimodal Dataset for evaluating Satire Comprehension capability of Vision-Language Models","created":"2024-09-20","cited_by_count":9,"area":"mllm"},{"id":"2410.13088","title":"Self-Comparison for Dataset-Level Membership Inference in Large (Vision-)Language Models","created":"2024-10-16","cited_by_count":7,"area":"mllm"},{"id":"2508.11011","title":"Are Large Pre-trained Vision Language Models Effective Construction Safety Inspectors?","created":"2025-08-14","cited_by_count":7,"area":"mllm"},{"id":"2406.13564","title":"HumorDB: Can AI understand graphical humor?","created":"2024-06-19","cited_by_count":6,"area":"mllm"},{"id":"2410.10112","title":"Can We Predict Performance of Large Models across Vision-Language Tasks?","created":"2024-10-14","cited_by_count":6,"area":"mllm"},{"id":"2504.13120","title":"Probing and Inducing Combinational Creativity in Vision-Language Models","created":"2025-04-17","cited_by_count":6,"area":"mllm"},{"id":"2509.12248","title":"Humor in Pixels: Benchmarking Large Multimodal Models Understanding of Online Comics","created":"2025-09-12","cited_by_count":5,"area":"mllm"},{"id":"2502.13925","title":"Beyond Single Frames: Can LMMs Comprehend Temporal and Contextual Narratives in Image Sequences?","created":"2025-02-19","cited_by_count":4,"area":"mllm"},{"id":"2406.04470","title":"DiffuSyn Bench: Evaluating Vision-Language Models on Real-World Complexities with Diffusion-Generated Synthetic Benchmarks","created":"2024-06-06","cited_by_count":2,"area":"mllm"},{"id":"2511.22805","title":"From Pixels to Feelings: Aligning MLLMs with Human Cognitive Perception of Images","created":"2025-11-27","cited_by_count":2,"area":"mllm"},{"id":"2603.23229","title":"I Came, I Saw, I Explained: Benchmarking Multimodal LLMs on Figurative Meaning in Memes","created":"2026-03-24","cited_by_count":2,"area":"mllm"},{"id":"2509.25568","title":"Probing the Limits of Stylistic Alignment in Vision-Language Models","created":"2025-09-29","cited_by_count":0,"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":"2607.19011","title":"Computational Humor with Multimodal LLMs: Methods, Datasets, Evaluation, and Challenges","created":"2026-07-21","cited_by_count":0,"area":"mllm"}],"next_cursor":null}