{"total":55,"rows":[{"id":"2312.13286","title":"Generative Multimodal Models are In-Context Learners","created":"2023-12-20","cited_by_count":446,"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":"2403.00476","title":"TempCompass: Do Video LLMs Really Understand Videos?","created":"2024-03-01","cited_by_count":363,"area":null},{"id":"2408.13257","title":"MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?","created":"2024-08-23","cited_by_count":292,"area":"mllm"},{"id":"2311.17600","title":"MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models","created":"2023-11-29","cited_by_count":274,"area":"mllm"},{"id":"2402.07729","title":"AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension","created":"2024-02-12","cited_by_count":220,"area":null},{"id":"2312.06742","title":"Honeybee: Locality-enhanced Projector for Multimodal LLM","created":"2023-12-11","cited_by_count":197,"area":"mllm"},{"id":"2404.16790","title":"SEED-Bench-2-Plus: Benchmarking Multimodal Large Language Models with Text-Rich Visual Comprehension","created":"2024-04-25","cited_by_count":146,"area":"mllm"},{"id":"2402.02544","title":"LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model","created":"2024-02-04","cited_by_count":138,"area":"mllm"},{"id":"2402.12451","title":"The Revolution of Multimodal Large Language Models: A Survey","created":"2024-02-19","cited_by_count":137,"area":"mllm"},{"id":"2401.06591","title":"Prometheus-Vision: Vision-Language Model as a Judge for Fine-Grained Evaluation","created":"2024-01-12","cited_by_count":125,"area":"mllm"},{"id":"2405.09589","title":"A Comprehensive Survey of Hallucination in Large Language, Image, Video and Audio Foundation Models","created":"2024-05-15","cited_by_count":100,"area":null},{"id":"2311.17092","title":"SEED-Bench-2: Benchmarking Multimodal Large Language Models","created":"2023-11-28","cited_by_count":97,"area":"mllm"},{"id":"2310.20550","title":"CapsFusion: Rethinking Image-Text Data at Scale","created":"2023-10-31","cited_by_count":90,"area":"lr"},{"id":"2502.10391","title":"MM-RLHF: The Next Step Forward in Multimodal LLM Alignment","created":"2025-02-14","cited_by_count":83,"area":"mllm"},{"id":"2404.10595","title":"Automated Evaluation of Large Vision-Language Models on Self-driving Corner Cases","created":"2024-04-16","cited_by_count":77,"area":"mllm"},{"id":"2405.16640","title":"A Survey of Multimodal Large Language Model from A Data-centric Perspective","created":"2024-05-26","cited_by_count":75,"area":"mllm"},{"id":"2411.15296","title":"MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMs","created":"2024-11-22","cited_by_count":72,"area":"mllm"},{"id":"2503.23771","title":"XLRS-Bench: Could Your Multimodal LLMs Understand Extremely Large Ultra-High-Resolution Remote Sensing Imagery?","created":"2025-03-31","cited_by_count":51,"area":"mllm"},{"id":"2408.15769","title":"A Survey on Evaluation of Multimodal Large Language Models","created":"2024-08-28","cited_by_count":46,"area":"lr"},{"id":"2504.08748","title":"A Survey of Multimodal Retrieval-Augmented Generation","created":"2025-03-26","cited_by_count":37,"area":"rag"},{"id":"2503.17489","title":"Judge Anything: MLLM as a Judge Across Any Modality","created":"2025-03-21","cited_by_count":34,"area":null},{"id":"2402.06599","title":"On the Out-Of-Distribution Generalization of Multimodal Large Language Models","created":"2024-02-09","cited_by_count":30,"area":"mllm"},{"id":"2311.13951","title":"MLLM-Bench: Evaluating Multimodal LLMs with Per-sample Criteria","created":"2023-11-23","cited_by_count":27,"area":"mllm"},{"id":"2409.18142","title":"A Survey on Multimodal Benchmarks: In the Era of Large AI Models","created":"2024-09-21","cited_by_count":27,"area":"mllm"},{"id":"2402.07270","title":"Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchy","created":"2024-02-11","cited_by_count":26,"area":"mllm"},{"id":"2407.03418","title":"HEMM: Holistic Evaluation of Multimodal Foundation Models","created":"2024-07-03","cited_by_count":21,"area":null},{"id":"2510.04401","title":"Your Vision-Language Model Can't Even Count to 20: Exposing the Failures of VLMs in Compositional Counting","created":"2025-10-06","cited_by_count":18,"area":"mllm"},{"id":"2407.15350","title":"WTS: A Pedestrian-Centric Traffic Video Dataset for Fine-grained Spatial-Temporal Understanding","created":"2024-07-22","cited_by_count":17,"area":null},{"id":"2505.17104","title":"P2P: Automated Paper-to-Poster Generation and Fine-Grained Benchmark","created":"2025-05-21","cited_by_count":17,"area":null},{"id":"2503.01725","title":"HarmonySet: A Comprehensive Dataset for Understanding Video-Music Semantic Alignment and Temporal Synchronization","created":"2025-03-03","cited_by_count":14,"area":null},{"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":"2504.05457","title":"Taxonomy-Aware Evaluation of Vision-Language Models","created":"2025-04-07","cited_by_count":11,"area":"mllm"},{"id":"2311.14580","title":"Large Language Models as Automated Aligners for benchmarking Vision-Language Models","created":"2023-11-24","cited_by_count":10,"area":"mllm"},{"id":"2412.07183","title":"Exploring What Why and How: A Multifaceted Benchmark for Causation Understanding of Video Anomaly","created":"2024-12-10","cited_by_count":9,"area":null},{"id":"2502.13832","title":"ArtMentor: AI-Assisted Evaluation of Artworks to Explore Multimodal Large Language Models Capabilities","created":"2025-02-19","cited_by_count":9,"area":"mllm"},{"id":"2506.03194","title":"HueManity: Probing Fine-Grained Visual Perception in MLLMs","created":"2025-05-31","cited_by_count":9,"area":"lr"},{"id":"2403.00068","title":"Towards Artwork Explanation in Large-scale Vision Language Models","created":"2024-02-29","cited_by_count":8,"area":"mllm"},{"id":"2406.09295","title":"AlignMMBench: Evaluating Chinese Multimodal Alignment in Large Vision-Language Models","created":"2024-06-13","cited_by_count":8,"area":"mllm"},{"id":"2402.03173","title":"MULTI: Multimodal Understanding Leaderboard with Text and Images","created":"2024-02-05","cited_by_count":7,"area":"mllm"},{"id":"2412.11767","title":"IDEA-Bench: How Far are Generative Models from Professional Designing?","created":"2024-12-16","cited_by_count":7,"area":null},{"id":"2405.17475","title":"How Culturally Aware are Vision-Language Models?","created":"2024-05-24","cited_by_count":6,"area":"mllm"},{"id":"2503.16566","title":"REVAL: A Comprehension Evaluation on Reliability and Values of Large Vision-Language Models","created":"2025-03-20","cited_by_count":5,"area":"mllm"},{"id":"2401.06792","title":"LightHouse: A Survey of AGI Hallucination","created":"2024-01-08","cited_by_count":4,"area":null},{"id":"2408.03695","title":"Openstory++: A Large-scale Dataset and Benchmark for Instance-aware Open-domain Visual Storytelling","created":"2024-08-07","cited_by_count":4,"area":null},{"id":"2509.25339","title":"VisualOverload: Probing Visual Understanding of VLMs in Really Dense Scenes","created":"2025-09-29","cited_by_count":4,"area":null},{"id":"2504.16936","title":"Multifaceted Evaluation of Audio-Visual Capability for MLLMs: Effectiveness, Efficiency, Generalizability and Robustness","created":"2025-04-03","cited_by_count":3,"area":"mllm"},{"id":"2407.16686","title":"Can Large Language Models Automatically Jailbreak GPT-4V?","created":"2024-07-23","cited_by_count":2,"area":"safety"},{"id":"2506.02308","title":"MINT: Multimodal Instruction Tuning with Multimodal Interaction Grouping","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2508.08275","title":"MLLM-CTBench: A Benchmark for Continual Instruction Tuning with Reasoning Process Diagnosis","created":"2025-07-31","cited_by_count":2,"area":"lr"},{"id":"2504.10158","title":"COUNTS: Benchmarking Object Detectors and Multimodal Large Language Models under Distribution Shifts","created":"2025-04-14","cited_by_count":1,"area":"mllm"},{"id":"2604.21523","title":"Seeing Isn't Believing: Uncovering Blind Spots in Evaluator Vision-Language Models","created":"2026-04-23","cited_by_count":1,"area":"mllm"},{"id":"2606.06217","title":"DisasterBench: A Multimodal Benchmark for UAV-Based Disaster Response in Complex Environments","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2508.14045","title":"From Image Captioning to Visual Storytelling","created":"2025-07-31","cited_by_count":0,"area":null},{"id":"2605.10172","title":"V-ABS: Action-Observer Driven Beam Search for Dynamic Visual Reasoning","created":"2026-05-11","cited_by_count":0,"area":"lr"}],"next_cursor":null}