外观
论文arXiv 2610.1910815 天前
迈向对多模态大型语言模型中空间推理的数据中心理解
原文链接：Towards a Data-Centric Understanding of Spatial Reasoning in Multimodal Large Language Models（arXiv 2610.19108 · 发布日期：2026-10-13）
Towards a Data-Centric Understanding of Spatial Reasoning in Multimodal Large Language Models
综述预训练 MLLM 空间推理微调方法，重点分析数据集构建、标注模态与模型评估。
核心要点
- MLLM 已用于具身智能和机器人视觉任务，但空间推理与感知仍有限。
- 综述从监督学习到强化学习的微调方法，强调所用数据集的作用。
- 将相关研究归为数据集设计、数据集构建和评估三类主题。
- 总结固定空间标注构建方法，并指出评估方式差异及未来研究机会。
验证范围与局限：综述范围限于面向空间推理任务微调预训练 MLLM 的方法与数据集。
英文摘要 (Abstract)
Multimodal Large Language Models (MLLMs) have been widely applied in embodied agents and robotics for vision tasks. However, MLLMs suffer from limitations in spatial reasoning and perception. Post-training techniques have shown promise for improving these capabilities; yet, there are limited data-driven surveys of such approaches. In this survey, we consider approaches to fine-tuning pretrained MLLMs for spatial reasoning tasks, ranging from supervised to reinforcement learning, with an emphasis on the datasets used. We investigate themes of dataset construction, data modality and annotation, and evaluation of the resulting models. Based on these themes, we categorize research into three groups: dataset design, dataset construction and evaluation. We find four main methods for constructing fixed spatial annotations: rules and templates, LLM prompting, procedural generation, and human-in-the-loop. We also observe substantial variation in evaluation approaches, including different scoring methods, tolerance metrics, and benchmark types. Finally, we identify opportunities for future research in unified dynamic annotation, efficient spatial reasoning, standardization of evaluation, expanded spatial range, and human-centered spatial interactions.
作者：Mahdieh Mallahnezhad, Masoud Jafaripour, Mohamadali Tofigh, Sheila Schoepp, Osmar R. Zai͏̈ane
来源
本页事实对应的公开页面，以原文为准。