{"total":18,"rows":[{"id":"2501.05444","title":"Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark","created":"2025-01-09","cited_by_count":134,"area":"lr"},{"id":"2505.04921","title":"Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models","created":"2025-05-08","cited_by_count":90,"area":"lr"},{"id":"2502.02871","title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning","created":"2025-02-05","cited_by_count":33,"area":"lr"},{"id":"2506.10857","title":"VRBench: A Benchmark for Multi-Step Reasoning in Long Narrative Videos","created":"2025-06-12","cited_by_count":24,"area":"lr"},{"id":"2410.18976","title":"CAMEL-Bench: A Comprehensive Arabic LMM Benchmark","created":"2024-10-24","cited_by_count":17,"area":"lr"},{"id":"2504.05782","title":"MDK12-Bench: A Multi-Discipline Benchmark for Evaluating Reasoning in Multimodal Large Language Models","created":"2025-04-08","cited_by_count":15,"area":"lr"},{"id":"2405.15638","title":"M4U: Evaluating Multilingual Understanding and Reasoning for Large Multimodal Models","created":"2024-05-24","cited_by_count":13,"area":"lr"},{"id":"2506.02803","title":"SemVink: Advancing VLMs' Semantic Understanding of Optical Illusions via Visual Global Thinking","created":"2025-06-03","cited_by_count":6,"area":"lr"},{"id":"2506.11604","title":"VLM@school -- Evaluation of AI image understanding on German middle school knowledge","created":"2025-06-13","cited_by_count":2,"area":"lr"},{"id":"2601.16218","title":"M3Kang: Evaluating Multilingual Multimodal Mathematical Reasoning in Vision-Language Models","created":"2026-01-03","cited_by_count":2,"area":"lr"},{"id":"2505.11141","title":"Human-Aligned Bench: Fine-Grained Assessment of Reasoning Ability in MLLMs vs. Humans","created":"2025-05-16","cited_by_count":1,"area":"lr"},{"id":"2507.11114","title":"MSA at ImageCLEF 2025 Multimodal Reasoning: Multilingual Multimodal Reasoning With Ensemble Vision Language Models","created":"2025-07-15","cited_by_count":1,"area":"lr"},{"id":"2508.03737","title":"GanitBench: A bi-lingual benchmark for evaluating mathematical reasoning in Vision Language Models","created":"2025-07-31","cited_by_count":1,"area":"lr"},{"id":"2601.10649","title":"MINERVA-Cultural: A Benchmark for Cultural and Multilingual Long Video Reasoning","created":"2026-01-15","cited_by_count":1,"area":"lr"},{"id":"2607.09438","title":"Test-Time Scaling for Small VLMs on Multilingual Visual MCQ","created":"2026-07-10","cited_by_count":1,"area":"lr"},{"id":"2608.01664","title":"FAU at ImageCLEF 2026 Task on Multimodal Reasoning Robust Candidate Scoring and Concise Multilingual Visual Answering","created":"2026-08-03","cited_by_count":0,"area":"lr"},{"id":"2609.13158","title":"TestHallVQA: Exploring LVLMs' Document-Level Reasoning under Redundant Contexts from Scientific Exams","created":"2026-07-15","cited_by_count":0,"area":"lr"},{"id":"2609.39142","title":"When Can Text Replace Vision? Structural Bottlenecks in Diagram Reasoning","created":"2026-09-30","cited_by_count":0,"area":"lr"}],"next_cursor":null}