MoveGPT: Scaling Mobility Foundation Models with Spatially-Aware Mixture of Experts

• URL: http://arxiv.org/abs/2505.18670v2
• Date: Wed, 01 Oct 2025 08:50:20 GMT
• Title: MoveGPT: Scaling Mobility Foundation Models with Spatially-Aware Mixture of Experts
• Authors: Chonghua Han, Yuan Yuan, Jingtao Ding, Jie Feng, Fanjin Meng, Yong Li,
• Abstract summary: MoveGPT is a large-scale foundation model specifically architected to overcome barriers to scaling.<n>It establishes a new state-of-the-art across a wide range of downstream tasks, achieving performance gains of up to 35% on average.<n>It also demonstrates strong generalization capabilities to unseen cities.
• Score: 17.430772832222793
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The success of foundation models in language has inspired a new wave of general-purpose models for human mobility. However, existing approaches struggle to scale effectively due to two fundamental limitations: a failure to use meaningful basic units to represent movement, and an inability to capture the vast diversity of patterns found in large-scale data. In this work, we develop MoveGPT, a large-scale foundation model specifically architected to overcome these barriers. MoveGPT is built upon two key innovations: (1) a unified location encoder that maps geographically disjoint locations into a shared semantic space, enabling pre-training on a global scale; and (2) a Spatially-Aware Mixture-of-Experts Transformer that develops specialized experts to efficiently capture diverse mobility patterns. Pre-trained on billion-scale datasets, MoveGPT establishes a new state-of-the-art across a wide range of downstream tasks, achieving performance gains of up to 35% on average. It also demonstrates strong generalization capabilities to unseen cities. Crucially, our work provides empirical evidence of scaling ability in human mobility, validating a clear path toward building increasingly capable foundation models in this domain.

Related papers

• UniMove: A Unified Model for Multi-city Human Mobility Prediction [18.826615430413373]
  Human mobility prediction is vital for urban planning, transportation optimization, and personalized services.<n>Existing solutions often require training separate models for each city due to distinct spatial representations and geographic coverage.<n>We propose UniMove, a unified model for multi-city human mobility prediction.
  arXiv  Detail & Related papers  (2025-08-09T13:47:22Z)
• From Points to Places: Towards Human Mobility-Driven Spatiotemporal Foundation Models via Understanding Places [0.30693357740321775]
  This paper advocates for a new class of spatial foundation models that integrate geolocation semantics with human mobility across multiple scales.<n>Our goal is to guide the development of scalable, context-aware models for next-generation geospatial intelligence.
  arXiv  Detail & Related papers  (2025-06-17T14:27:24Z)
• CAMS: A CityGPT-Powered Agentic Framework for Urban Human Mobility Simulation [9.907406552578607]
  textbfCAMS is an agentic framework that leverages the language based urban foundation model to simulate human mobility in urban space.<n>textbfCAMS achieves superior performance without relying on externally provided geospatial information.
  arXiv  Detail & Related papers  (2025-06-16T15:24:07Z)
• TerraFM: A Scalable Foundation Model for Unified Multisensor Earth Observation [65.74990259650984]
  We introduce TerraFM, a scalable self-supervised learning model that leverages globally distributed Sentinel-1 and Sentinel-2 imagery.<n>Our training strategy integrates local-global contrastive learning and introduces a dual-centering mechanism.<n>TerraFM achieves strong generalization on both classification and segmentation tasks, outperforming prior models on GEO-Bench and Copernicus-Bench.
  arXiv  Detail & Related papers  (2025-06-06T17:59:50Z)
• Mixture-of-Experts for Personalized and Semantic-Aware Next Location Prediction [20.726107072683575]
  NextLocMoE is a novel framework built upon large language models (LLMs) and structured around a dual-level Mixture-of-Experts (MoE) design.<n>Our architecture comprises two specialized modules: a Location Semantics MoE that operates at the embedding level to encode rich functional semantics of locations, and a Personalized MoE embedded within the Transformer backbone to dynamically adapt to individual user mobility patterns.
  arXiv  Detail & Related papers  (2025-05-30T13:45:19Z)
• Learning Universal Human Mobility Patterns with a Foundation Model for Cross-domain Data Fusion [11.332722237426987]
  We present a foundation model framework for universal human mobility.<n>We leverage cross-domain data fusion and large language models to address limitations.<n>Our framework demonstrates adaptability through domain transfer techniques.
  arXiv  Detail & Related papers  (2025-03-20T01:41:28Z)
• Collaborative Imputation of Urban Time Series through Cross-city Meta-learning [54.438991949772145]
  We propose a novel collaborative imputation paradigm leveraging meta-learned implicit neural representations (INRs)<n>We then introduce a cross-city collaborative learning scheme through model-agnostic meta learning.<n>Experiments on a diverse urban dataset from 20 global cities demonstrate our model's superior imputation performance and generalizability.
  arXiv  Detail & Related papers  (2025-01-20T07:12:40Z)
• UniTraj: Learning a Universal Trajectory Foundation Model from Billion-Scale Worldwide Traces [64.24594320103066]
  Building a universal trajectory foundation model is a promising solution to address the limitations of existing trajectory modeling approaches.<n>We introduce UniTraj, a Universal Trajectory foundation model that aims to address these limitations through three key innovations.<n>First, we construct WorldTrace, an unprecedented dataset of 2.45 million trajectories with billions of GPS points spanning 70 countries.
  arXiv  Detail & Related papers  (2024-11-06T12:06:43Z)
• Specialized Foundation Models Struggle to Beat Supervised Baselines [60.23386520331143]
  We look at three modalities -- genomics, satellite imaging, and time series -- with multiple recent FMs and compare them to a standard supervised learning workflow.<n>We find that it is consistently possible to train simple supervised models that match or even outperform the latest foundation models.
  arXiv  Detail & Related papers  (2024-11-05T04:10:59Z)
• Multi-Transmotion: Pre-trained Model for Human Motion Prediction [68.87010221355223]
  Multi-Transmotion is an innovative transformer-based model designed for cross-modality pre-training. Our methodology demonstrates competitive performance across various datasets on several downstream tasks.
  arXiv  Detail & Related papers  (2024-11-04T23:15:21Z)
• ST-MoE-BERT: A Spatial-Temporal Mixture-of-Experts Framework for Long-Term Cross-City Mobility Prediction [6.0588503913405045]
  We propose a robust approach to predict human mobility patterns called ST-MoE-BERT. Our methodology integrates the Mixture-of-Experts architecture with BERT model to capture complex mobility dynamics. We demonstrate the effectiveness of the proposed model on GEO-BLEU and DTW, comparing it to several state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-10-18T00:32:18Z)
• MetaUrban: An Embodied AI Simulation Platform for Urban Micromobility [52.0930915607703]
  Recent advances in Robotics and Embodied AI make public urban spaces no longer exclusive to humans. Micromobility enabled by AI for short-distance travel in public urban spaces plays a crucial component in the future transportation system. We present MetaUrban, a compositional simulation platform for the AI-driven urban micromobility research.
  arXiv  Detail & Related papers  (2024-07-11T17:56:49Z)
• Pretrained Mobility Transformer: A Foundation Model for Human Mobility [11.713796525742405]
  textbfPretrained textbfMobility textbfTransformer (PMT) textbfMobility textbfTransformer (PMT) textbfPretrained textbfMobility textbfTransformer (PMT)
  arXiv  Detail & Related papers  (2024-05-29T00:07:22Z)
• Deep Activity Model: A Generative Approach for Human Mobility Pattern Synthesis [11.90100976089832]
  We develop a novel generative deep learning approach for human mobility modeling and synthesis. It incorporates both activity patterns and location trajectories using open-source data. The model can be fine-tuned with local data, allowing it to adapt to accurately represent mobility patterns across diverse regions.
  arXiv  Detail & Related papers  (2024-05-24T02:04:10Z)
• COLA: Cross-city Mobility Transformer for Human Trajectory Simulation [44.157114416533915]
  We develop a Cross-city mObiLity trAnsformer (COLA) with a dedicated model-agnostic transfer framework. COLA divides the Transformer into the private modules for city-specific characteristics and the shared modules for city-universal mobility patterns. Our implemented cross-city baselines have demonstrated its superiority and effectiveness.
  arXiv  Detail & Related papers  (2024-03-04T07:45:29Z)
• Synthetic location trajectory generation using categorical diffusion models [50.809683239937584]
  Diffusion models (DPMs) have rapidly evolved to be one of the predominant generative models for the simulation of synthetic data. We propose using DPMs for the generation of synthetic individual location trajectories (ILTs) which are sequences of variables representing physical locations visited by individuals.
  arXiv  Detail & Related papers  (2024-02-19T15:57:39Z)
• Recognize Any Regions [55.76437190434433]
  RegionSpot integrates position-aware localization knowledge from a localization foundation model with semantic information from a ViL model.<n>Experiments in open-world object recognition show that our RegionSpot achieves significant performance gain over prior alternatives.
  arXiv  Detail & Related papers  (2023-11-02T16:31:49Z)
• Transferring Foundation Models for Generalizable Robotic Manipulation [82.12754319808197]
  We propose a novel paradigm that effectively leverages language-reasoning segmentation mask generated by internet-scale foundation models.<n>Our approach can effectively and robustly perceive object pose and enable sample-efficient generalization learning.<n>Demos can be found in our submitted video, and more comprehensive ones can be found in link1 or link2.
  arXiv  Detail & Related papers  (2023-06-09T07:22:12Z)
• Mobility signatures: a tool for characterizing cities using intercity mobility flows [1.1602089225841632]
  We introduce the mobility signature as a tool for understanding how a city is embedded in the wider mobility network. We demonstrate the potential of the mobility signature approach through two applications that build on mobile-phone-based data from Finland.
  arXiv  Detail & Related papers  (2021-12-03T08:53:58Z)
• Learning to Move with Affordance Maps [57.198806691838364]
  The ability to autonomously explore and navigate a physical space is a fundamental requirement for virtually any mobile autonomous agent. Traditional SLAM-based approaches for exploration and navigation largely focus on leveraging scene geometry. We show that learned affordance maps can be used to augment traditional approaches for both exploration and navigation, providing significant improvements in performance.
  arXiv  Detail & Related papers  (2020-01-08T04:05:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.