从零构建轨迹基础模型，手把手教用GPT-2处理时空数据
Building a Foundation Model for Trajectory from Scratch
- 基于GPT-2改造，适配轨迹的时空序列建模
- 对比TrajFM、TrajGPT等模型架构差异与性能表现
- 适合想入门移动轨迹基础模型的研究者与工程师
基础模型在人工智能中具有变革性，但针对移动轨迹的基础模型从零构建尚不清晰且缺乏文档。本文通过简洁、分步、代码驱动的方式，演示从GPT-2出发构建轨迹导向基础模型的最小实现过程。我们展示了如何将GPT-2适配于时空数据，并回顾与比较代表性轨迹基础模型（如TrajFM和TrajGPT），突出其架构创新与差异。此外，引入相关领域互补技术，如TimesFM的分块策略。本教程面向研究人员与实践者，旨在从实现层面解释基础模型的概念与术语。我们认为，此时推出此类教育材料对支持SIGSPATIAL社区构建与评估移动基础模型至关重要，有助于提升移动AI研究的清晰度与同行评审效率。
原文摘要 · Abstract (English)
Foundation models are transformative in artificial intelligence, but building them from scratch, especially for mobility trajectories, is not yet clear or documented. This tutorial bridges this gap by demonstrating the steps and code of a minimal implementation of a trajectory-focused foundation model starting from GPT-2. Through a concise, step-by-step, code-driven process, we demonstrate adapting GPT-2 for spatiotemporal data. We then review and compare representative trajectory foundation models, such as TrajFM and TrajGPT, highlighting their architectural innovations and differences. Additionally, we introduce complementary techniques from related domains, like TimesFM's patching approach. Targeted at researchers and practitioners, this tutorial aims to explain the concepts and terminology of foundation models, at the implementation level. We find it timely and indispensable to create this educational material in order to support the SIGSPATIAL community in building and evaluating mobility foundation models, enhancing both research clarity and peer-review effectiveness in mobility AI.
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。