从位置认知到功能理解：为多模态大语言模型设立空间功能智能基准
From Where Things Are to What They’re For: Benchmarking Spatial–Functional Intelligence for Multimodal LLMs
现有基准如VSI-Bench主要评估基础几何感知能力，但未能触及具身智能所需的高阶认知。为此，研究团队推出了空间功能智能基准SFI-Bench，该基准包含超过1700个问题，数据来源于多样化的第一人称室内扫描视频。SFI-Bench旨在系统评估多模态大模型从物体位置感知到功能意图理解的高级空间推理能力，标志着对智能体空间认知的评估从几何层面迈向功能层面。
Apple 自己搞的 SFI-Bench 把评估从几何定位推进到功能理解，这个方向很对，做具身智能和空间推理的团队该跟一下。
AuthorsLe Zhang†**, Jihan Yang‡, Soundarya Krishnan, Jimit Majmudar, Xiou Ge, Prasoon Puri, Prathamesh Saraf, Shruti Bhargava, Dhivya Piraviperumal, Yinan Ling, Cindy Pan, Hong Yu, Aishwarya Agrawal†, Bo-Hsiang Tseng
True spatial intelligence for multimodal agents transcends low-level geometric perception, evolving from knowing where things are to understanding what they are for. While existing benchmarks, such as VSI-Bench, effectively evaluate this foundational geometric stage, they fall short of probing the higher-order cognitive abilities essential for grounded intelligence. To bridge this gap, we introduce the Spatial-Functional Intelligence Benchmark (SFI-Bench), a video-based benchmark with over 1700 questions derived from diverse, egocentric indoor video scans. SFI-Bench is designed to systematically evaluate two complementary dimensions of advanced reasoning: (1) Structured Spatial Reasoning, understanding complex layouts and forming coherent spatial representations, and (2) Functional Reasoning, inferring object affordances and context-dependent utility. Its tasks, including conditional counting, multi-hop relational reasoning, functional pairing, and knowledge-grounded troubleshooting, directly challenge a model’s ability to integrate perception, memory, and inference. Our experiments reveal that current MLLMs consistently struggle to integrate spatial memory with functional and external knowledge, highlighting a critical bottleneck. SFI-Bench thus provides an essential tool for measuring and driving progress towards more cognitively capable and truly grounded multimodal agents.
- † Mila, Université de Montréal
- ‡ New York University
- ** Work done while at Apple
来源：Apple Machine Learning Research（RSS） · machinelearning.apple.com