6亿参数小模型实现仓库空间推理，效率高且准确。
SmolRGPT: Efficient Spatial Reasoning for Warehouse Environments with 600M Parameters
- 用三阶段训练融合图像与深度信息，强化空间理解
- 仅6亿参数就在仓库任务上媲美大模型表现
- 适合部署在资源受限的仓储机器人等场景
视觉语言模型（VLMs）虽已具备强大多模态推理能力，但主流方法依赖超大规模模型，计算与内存开销巨大，难以在仓库、机器人等资源受限场景部署。本文提出SmolRGPT，一个仅含600M参数的紧凑视觉语言架构，通过整合RGB与深度信息，在区域级别显式建模空间关系。采用三阶段课程学习，逐步对齐视觉与语言特征，提升空间关系理解，并适配特定任务数据集。实验表明，该模型在挑战性的仓库空间推理基准上表现优异，性能可与更大模型比肩甚至超越。结果表明，无需牺牲核心空间推理能力，即可实现高效可部署的多模态智能。代码将公开于：https://github.com/abtraore/SmolRGPT。
原文摘要 · Abstract (English)
Recent advances in vision-language models (VLMs) have enabled powerful multimodal reasoning, but state-of-the-art approaches typically rely on extremely large models with prohibitive computational and memory requirements. This makes their deployment challenging in resource-constrained environments such as warehouses, robotics, and industrial applications, where both efficiency and robust spatial understanding are critical. In this work, we present SmolRGPT, a compact vision-language architecture that explicitly incorporates region-level spatial reasoning by integrating both RGB and depth cues. SmolRGPT employs a three-stage curriculum that progressively align visual and language features, enables spatial relationship understanding, and adapts to task-specific datasets. We demonstrate that with only 600M parameters, SmolRGPT achieves competitive results on challenging warehouse spatial reasoning benchmarks, matching or exceeding the performance of much larger alternatives. These findings highlight the potential for efficient, deployable multimodal intelligence in real-world settings without sacrificing core spatial reasoning capabilities. The code of the experimentation will be available at: https://github.com/abtraore/SmolRGPT
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。