MMR-V：未言明的是什么？视频中多模态深度推理的基准测试
MMR-V: What's Left Unsaid? A Benchmark for Multimodal Deep Reasoning in Videos
AI总结：
针对视频多模态推理挑战，提出MMR-V基准测试，具有长程多帧推理等特点。该基准测试含317个视频和1257个任务，实验发现当前模型多模态推理困难，最佳模型准确率低，现有增强策略收益有限，旨在推动多模态推理能力研究。
摘要：
视频的序列结构对多模态大语言模型定位多帧证据和进行多模态推理的能力构成挑战。现有视频基准测试主要关注理解任务，仅要求模型匹配问题中提到的帧并感知相邻几帧。为填补这一空白，我们提出MMR-V：视频中多模态深度推理的基准测试。其具有长程多帧推理、超越感知、可靠性、可混淆性等特点。MMR-V由317个视频和1257个任务组成。实验表明当前模型在多模态推理方面仍有困难，最佳模型Gemini-2.5-pro准确率仅64.3%，当前推理增强策略收益有限。错误分析表明多模态推理所需的思维链与文本推理不同，这部分解释了性能提升有限的原因。我们希望MMR-V能激发对增强多模态推理能力的进一步研究。
英文摘要：
The sequential structure of videos poses a challenge to the ability of multimodal large language models (MLLMs) to locate multi-frame evidence and conduct multimodal reasoning. However, existing video benchmarks mainly focus on understanding tasks, which only require models to match frames mentioned in the question (hereafter referred to as "question frame") and perceive a few adjacent frames. To address this gap, we propose MMR-V: A Benchmark for Multimodal Deep Reasoning in Videos. The benchmark is characterized by the following features. (1) Long-range, multi-frame reasoning: Models are required to infer and analyze evidence frames that may be far from the question frame. (2) Beyond perception: Questions cannot be answered through direct perception alone but require reasoning over hidden information. (3) Reliability: All tasks are manually annotated, referencing extensive real-world user understanding to align with common perceptions. (4) Confusability: Carefully designed distractor annotation strategies to reduce model shortcuts. MMR-V consists of 317 videos and 1,257 tasks. Our experiments reveal that current models still struggle with multi-modal reasoning; even the best-performing model, Gemini-2.5-pro, achieves only 64.3% accuracy. Additionally, current reasoning enhancement strategies (Chain-of-Thought and scaling test-time compute) bring limited gains. Error analysis indicates that the CoT demanded for multi-modal reasoning differs from it in textual reasoning, which partly explains the limited performance gains. We hope that MMR-V can inspire further research into enhancing multi-modal reasoning capabilities.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
