{"total":52,"rows":[{"id":"2401.13601","title":"MM-LLMs: Recent Advances in MultiModal Large Language Models","created":"2024-01-24","cited_by_count":278,"area":"mllm"},{"id":"2406.12030","title":"SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model","created":"2024-06-17","cited_by_count":85,"area":"mllm"},{"id":"2402.00357","title":"Safety of Multimodal Large Language Models on Images and Texts","created":"2024-02-01","cited_by_count":75,"area":"mllm"},{"id":"2401.12915","title":"Red Teaming Visual Language Models","created":"2024-01-23","cited_by_count":65,"area":"mllm"},{"id":"2406.07057","title":"MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models","created":"2024-06-11","cited_by_count":53,"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":"2405.19334","title":"LLMs Meet Multimodal Generation and Editing: A Survey","created":"2024-05-29","cited_by_count":35,"area":null},{"id":"2406.07594","title":"MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models","created":"2024-06-11","cited_by_count":34,"area":"mllm"},{"id":"2406.15279","title":"Safe Inputs but Unsafe Output: Benchmarking Cross-modality Safety Alignment of Large Vision-Language Model","created":"2024-06-21","cited_by_count":26,"area":"mllm"},{"id":"2411.05383","title":"Towards Low-Resource Harmful Meme Detection with LMM Agents","created":"2024-11-08","cited_by_count":24,"area":null},{"id":"2410.18882","title":"A Survey of Multimodal Sarcasm Detection","created":"2024-10-24","cited_by_count":19,"area":null},{"id":"2401.13298","title":"Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Models","created":"2024-01-24","cited_by_count":18,"area":null},{"id":"2406.11288","title":"MFC-Bench: Benchmarking Multimodal Fact-Checking with Large Vision-Language Models","created":"2024-06-17","cited_by_count":15,"area":"lr"},{"id":"2502.11073","title":"Demystifying Hateful Content: Leveraging Large Multimodal Models for Hateful Meme Detection with Explainable Decisions","created":"2025-02-16","cited_by_count":14,"area":"mllm"},{"id":"2406.07353","title":"Toxic Memes: A Survey of Computational Perspectives on the Detection and Explanation of Meme Toxicities","created":"2024-06-11","cited_by_count":13,"area":null},{"id":"2501.10057","title":"MSTS: A Multimodal Safety Test Suite for Vision-Language Models","created":"2025-01-17","cited_by_count":12,"area":"mllm"},{"id":"2402.12198","title":"Exploring the Limits of Zero Shot Vision Language Models for Hate Meme Detection: The Vulnerabilities and their Interpretations","created":"2024-02-19","cited_by_count":10,"area":"mllm"},{"id":"2405.00390","title":"CofiPara: A Coarse-to-fine Paradigm for Multimodal Sarcasm Target Identification with Large Multimodal Models","created":"2024-05-01","cited_by_count":8,"area":null},{"id":"2505.14035","title":"ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs","created":"2025-05-20","cited_by_count":7,"area":"lr"},{"id":"2508.03654","title":"Can Large Vision-Language Models Understand Multimodal Sarcasm?","created":"2025-08-05","cited_by_count":5,"area":"mllm"},{"id":"2411.18932","title":"ScratchEval: Are GPT-4o Smarter than My Child? Evaluating Large Multimodal Models with Visual Programming Challenges","created":"2024-11-28","cited_by_count":4,"area":"mllm"},{"id":"2505.17433","title":"MemeReaCon: Probing Contextual Meme Understanding in Large Vision-Language Models","created":"2025-05-23","cited_by_count":4,"area":"mllm"},{"id":"2507.11155","title":"Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities","created":"2025-07-15","cited_by_count":4,"area":"lr"},{"id":"2508.15370","title":"Unveiling Trust in Multimodal Large Language Models: Evaluation, Analysis, and Mitigation","created":"2025-08-21","cited_by_count":4,"area":"mllm"},{"id":"2601.04692","title":"PEST: Parameter Efficient Steering of Blackbox VLMs via Agentic Few-shot Alignment for Hateful Meme Moderation","created":"2026-01-08","cited_by_count":4,"area":null},{"id":"2510.11852","title":"Evaluating Open-Source Vision-Language Models for Multimodal Sarcasm Detection","created":"2025-10-13","cited_by_count":3,"area":"mllm"},{"id":"2603.03315","title":"M-QUEST -- Meme Question-Understanding Evaluation on Semantics and Toxicity","created":"2026-02-09","cited_by_count":3,"area":null},{"id":"2407.16686","title":"Can Large Language Models Automatically Jailbreak GPT-4V?","created":"2024-07-23","cited_by_count":2,"area":"safety"},{"id":"2408.05794","title":"HateSieve: A Contrastive Learning Framework for Detecting and Segmenting Hateful Content in Multimodal Memes","created":"2024-08-11","cited_by_count":2,"area":null},{"id":"2505.23065","title":"SNS-Bench-VL: Benchmarking Multimodal Large Language Models in Social Networking Services","created":"2025-05-29","cited_by_count":2,"area":"mllm"},{"id":"2509.04403","title":"Self-adaptive Dataset Construction for Real-World Multimodal Safety Scenarios","created":"2025-09-04","cited_by_count":2,"area":"mllm"},{"id":"2509.15476","title":"Evaluating Multimodal Large Language Models on Spoken Sarcasm Understanding","created":"2025-09-18","cited_by_count":2,"area":"mllm"},{"id":"2511.09067","title":"MM-CRITIC: A Holistic Evaluation of Large Multimodal Models as Multimodal Critique","created":"2025-11-12","cited_by_count":2,"area":"mllm"},{"id":"2505.17144","title":"MDIT-Bench: Evaluating the Dual-Implicit Toxicity in Large Multimodal Models","created":"2025-05-22","cited_by_count":1,"area":"mllm"},{"id":"2601.04567","title":"All Changes May Have Invariant Principles: Improving Ever-Shifting Harmful Meme Detection via Design Concept Reproduction","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2601.23041","title":"One-shot Optimized Steering Vector for Hallucination Mitigation for VLMs","created":"2026-01-30","cited_by_count":1,"area":"mllm"},{"id":"2603.15020","title":"MER-Bench: A Comprehensive Benchmark for Multimodal Meme Reappraisal","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2604.01268","title":"The Overlooked Repetitive Lengthening Form in Sentiment Analysis","created":"2026-04-01","cited_by_count":1,"area":null},{"id":"2605.14607","title":"ViMU: Benchmarking Video Metaphorical Understanding","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2609.26907","title":"Small Cues, Big Consequences: Learning Pivotal Cues for Multimodal Meme Classification","created":"2026-09-22","cited_by_count":1,"area":null},{"id":"2411.12287","title":"CUE-M: Contextual Understanding and Enhanced Search with Multimodal Large Language Model","created":"2024-11-19","cited_by_count":0,"area":"mllm"},{"id":"2508.04166","title":"STEMTOX: From Collaborative Tags to Fine-Grained Toxic Meme Detection via Entropy-Guided Multi-Task Learning","created":"2025-08-06","cited_by_count":0,"area":"safety"},{"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":"2601.12652","title":"Ethical Risks in Deploying Large Language Models: An Evaluation of Medical Ethics Jailbreaking","created":"2026-01-19","cited_by_count":0,"area":"safety"},{"id":"2602.03268","title":"Unveiling Covert Toxicity in Multimodal Data via Toxicity Association Graphs: A Graph-Based Metric and Interpretable Detection Framework","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2603.22985","title":"Beyond Hate: Differentiating Uncivil and Intolerant Speech in Multimodal Content Moderation","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2605.31349","title":"FBHM: Functional Benchmarking and Steering of VLMs for Hateful Meme Detection","created":"2026-05-29","cited_by_count":0,"area":"mllm"},{"id":"2606.05316","title":"I Know What You Meme, Even If it Emerged Today: Understanding Evolving Memes through Open-World Knowledge Acquisition","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.26654","title":"SocialPersona: Benchmarking Personalized Profiling and Response with Multimodal Social-Media Context","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.24082","title":"Towards High-Level Semantic Intelligence","created":"2026-07-27","cited_by_count":0,"area":"lr"},{"id":"2609.19778","title":"Learn Before You Judge: Progressive Knowledge-to-Decision Alignment for Explainable Hateful Meme Detection","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2610.19267","title":"MemeTrace: A Multimodal LLM-Based Agent for Safety-Aware Meme Provenance Analysis","created":"2026-10-13","cited_by_count":0,"area":"mllm"}],"next_cursor":null}