SpatialTree: How Spatial Intelligence Branches Out in MLLMs
Yuxi Xiao, Longfei Li, Shen Yan, Xinhang Liu, Sida Peng, Yunchao Wei, Xiaowei Zhou, Bingyi Kang
2026年份
摘要
Cognitive science suggests that spatial ability develops progressively-from perception to reasoning and interaction. Yet in multimodal LLMs (MLLMs), this hierarchy remains poorly understood, as most studies focus on a narrow set of tasks. We introduce SpatialTree, a cognitive-scienceinspired hierarchy that organizes spatial abilities into four levels: low-level perception (L1), mental mapping (L2), simulation (L3), and agentic competence (L4). Based on this taxonomy, we construct the first capability-centric hi-
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper26
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah 等NeurIPS 2020 · 被引用 64,255 次
- Visual Instruction TuningHaotian Liu, Chunyuan Li, Qingyang Wu, Yong Jae LeeNeurIPS 2023 · 被引用 11,349 次
- Depth Anything: Unleashing the Power of Large-Scale Unlabeled DataLihe Yang, Bingyi Kang, Zilong Huang, Xiaogang Xu 等CVPR 2024 · 被引用 847 次
- Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category ReconstructionJeremy Reizenstein, Roman Shapovalov, Philipp Henzler, Luca Sbordone 等ICCV 2021 · 被引用 686 次
- 3D-LLM: Injecting the 3D World into Large Language ModelsYining Hong, Haoyu Zhen, Peihao Chen, Shuhong Zheng 等NeurIPS 2023 · 被引用 662 次
相关 Paper
- Defining and Evaluating Visual Language Models' Basic Spatial Abilities: A Perspective from PsychometricsWenrui Xu, Dalin Lyu, Weihang Wang, Jie Feng 等ACL 2025 · 被引用 19 次
- SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language ModelsHongxing Li, Dingming Li, Zixuan Wang, Yuchen Yan 等ICLR 2026 · 被引用 75 次
- VSP: Diagnosing the Dual Challenges of Perception and Reasoning in Spatial Planning Tasks for MLLMSQiucheng Wu, Handong Zhao, Michael Saxon, Trung Bui 等ICCV 2025 · 被引用 1 次
- Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall SpacesJihan Yang, Shusheng Yang, Anjali W. Gupta, Rilyn Han 等CVPR 2025
- SpaCE-10: A Comprehensive Benchmark for Multimodal Large Language Models in Compositional Spatial IntelligenceZiyang Gong, Wenhao Li, Xianzheng Ma, Songyuan Li 等ICLR 2026 · 被引用 23 次
