Breaking Data Silos: Towards Open and Scalable Mobility Foundation Models via Generative Continual Learning

• URL: http://arxiv.org/abs/2506.06694v4
• Date: Tue, 26 Aug 2025 05:07:29 GMT
• Title: Breaking Data Silos: Towards Open and Scalable Mobility Foundation Models via Generative Continual Learning
• Authors: Yuan Yuan, Yukun Liu, Chonghua Han, Jie Feng, Yong Li,
• Abstract summary: MoveGCL is a scalable and privacy-preserving framework for training mobility foundation models.<n>We show MoveGCL achieves performance comparable to joint training and significantly outperforms federated learning baselines.<n>To facilitate and future research, we have released the code and models at https://github.com/tsinghua-fib-lab/MoveGCL.
• Score: 12.039720343078038
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Foundation models have revolutionized fields such as natural language processing and computer vision by enabling general-purpose learning across diverse tasks and datasets. However, building analogous models for human mobility remains challenging due to the privacy-sensitive nature of mobility data and the resulting data silos across institutions. To bridge this gap, we propose MoveGCL, a scalable and privacy-preserving framework for training mobility foundation models via generative continual learning. Without sharing raw data, MoveGCL enables decentralized and progressive model evolution by replaying synthetic trajectories generated from a frozen teacher model, and reinforces knowledge retention through a tailored distillation strategy that mitigates catastrophic forgetting. To address the heterogeneity of mobility patterns, MoveGCL incorporates a Mixture-of-Experts Transformer with a mobility-aware expert routing mechanism, and employs a layer-wise progressive adaptation strategy to stabilize continual updates. Experiments on six real-world urban datasets demonstrate that MoveGCL achieves performance comparable to joint training and significantly outperforms federated learning baselines, while offering strong privacy protection. MoveGCL marks a crucial step toward unlocking foundation models for mobility, offering a practical blueprint for open, scalable, and privacy-preserving model development in the era of foundation models. To facilitate reproducibility and future research, we have released the code and models at https://github.com/tsinghua-fib-lab/MoveGCL.

Related papers

• Modular Memory is the Key to Continual Learning Agents [100.09688599754465]
  We argue that combining the strengths of In-Weight Learning (IWL) and the newly emerged capabilities of In-Context Learning (ICL) through the design of modular memory is the missing piece for continual adaptation at scale.<n>We outline a conceptual framework for modular memory-centric architectures that leverage ICL for rapid adaptation and knowledge accumulation, and IWL for stable updates to model capabilities.
  arXiv  Detail & Related papers  (2026-03-02T11:40:05Z)
• TrajGPT-R: Generating Urban Mobility Trajectory with Reinforcement Learning-Enhanced Generative Pre-trained Transformer [22.847988014952488]
  Mobility trajectories are essential for understanding urban dynamics and enhancing urban planning.<n>Yet access to such data is frequently hindered by privacy concerns.<n>This research introduces a transformative framework for generating large-scale urban mobility trajectories.
  arXiv  Detail & Related papers  (2026-02-24T07:44:19Z)
• HiMoE-VLA: Hierarchical Mixture-of-Experts for Generalist Vision-Language-Action Policies [83.41714103649751]
  Development of embodied intelligence models depends on access to high-quality robot demonstration data.<n>We present HiMoE-VLA, a novel vision-language-action framework tailored to handle diverse robotic data with heterogeneity.<n>HiMoE-VLA demonstrates a consistent performance boost over existing VLA baselines, achieving higher accuracy and robust generalizations.
  arXiv  Detail & Related papers  (2025-12-05T13:21:05Z)
• Learning Primitive Embodied World Models: Towards Scalable Robotic Learning [50.32986780156215]
  We propose a novel paradigm for world modeling--Primitive Embodied World Models (PEWM)<n>By restricting video generation to fixed short horizons, our approach enables fine-grained alignment between linguistic concepts and visual representations of robotic actions.<n>Our framework bridges the gap between fine-grained physical interaction and high-level reasoning, paving the way toward scalable, interpretable, and general-purpose embodied intelligence.
  arXiv  Detail & Related papers  (2025-08-28T14:31:48Z)
• From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learning [59.88543114325153]
  We introduce the Seeing-to-Experiencing framework to scale the capability of navigation foundation models with reinforcement learning.<n>S2E combines the strengths of pre-training on videos and post-training through RL.<n>We establish a comprehensive end-to-end evaluation benchmark, NavBench-GS, built on photorealistic 3DGS reconstructions of real-world scenes.
  arXiv  Detail & Related papers  (2025-07-29T17:26:10Z)
• MobiVerse: Scaling Urban Mobility Simulation with Hybrid Lightweight Domain-Specific Generator and Large Language Models [11.90100976089832]
  We propose MobiVerse, a hybrid framework to bridge the gap in mobility simulation.<n>A case study was conducted in Westwood, Los Angeles, where we efficiently generated and dynamically adjusted schedules.<n>Results show our approach maintains computational efficiency while enhancing behavioral realism.
  arXiv  Detail & Related papers  (2025-06-26T21:46:18Z)
• 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)
• FedAWA: Adaptive Optimization of Aggregation Weights in Federated Learning Using Client Vectors [50.131271229165165]
  Federated Learning (FL) has emerged as a promising framework for distributed machine learning.<n>Data heterogeneity resulting from differences across user behaviors, preferences, and device characteristics poses a significant challenge for federated learning.<n>We propose Adaptive Weight Aggregation (FedAWA), a novel method that adaptively adjusts aggregation weights based on client vectors during the learning process.
  arXiv  Detail & Related papers  (2025-03-20T04:49:40Z)
• TrajLLM: A Modular LLM-Enhanced Agent-Based Framework for Realistic Human Trajectory Simulation [3.8106509573548286]
  This work leverages Large Language Models (LLMs) to simulate human mobility, addressing challenges like high costs and privacy concerns in traditional models.<n>Our hierarchical framework integrates persona generation, activity selection, and destination prediction, using real-world demographic and psychological data.
  arXiv  Detail & Related papers  (2025-02-26T00:13:26Z)
• Pre-Trained Video Generative Models as World Simulators [59.546627730477454]
  We propose Dynamic World Simulation (DWS) to transform pre-trained video generative models into controllable world simulators.<n>To achieve precise alignment between conditioned actions and generated visual changes, we introduce a lightweight, universal action-conditioned module.<n> Experiments demonstrate that DWS can be versatilely applied to both diffusion and autoregressive transformer models.
  arXiv  Detail & Related papers  (2025-02-10T14:49:09Z)
• 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)
• Long Term Memory: The Foundation of AI Self-Evolution [48.39506286931116]
  Large language models (LLMs) like GPTs, trained on vast datasets, have demonstrated impressive capabilities in language understanding, reasoning, and planning.<n>Most studies focus on enhancing these models by training on ever-larger datasets to build more powerful foundation models.<n>Unlike large-scale training, enabling models to evolve during inference is equally crucial, a process we refer to as AI self-evolution.
  arXiv  Detail & Related papers  (2024-10-21T06:09:30Z)
• Reconstructing Human Mobility Pattern: A Semi-Supervised Approach for Cross-Dataset Transfer Learning [10.864774173935535]
  We have developed a model that reconstructs and learns human mobility patterns by focusing on semantic activity chains. We introduce a semi-supervised iterative transfer learning algorithm to adapt models to diverse geographical contexts.
  arXiv  Detail & Related papers  (2024-10-03T20:29:56Z)
• Human Mobility Modeling with Household Coordination Activities under Limited Information via Retrieval-Augmented LLMs [11.90100976089832]
  We propose a retrieval-augmented large language model (LLM) framework that generates activity chains with household coordination using only public accessible statistical and socio-demographic information.<n>Our validation with NHTS and SCAG-ABM datasets demonstrates effective mobility synthesis and strong adaptability for regions with limited mobility data availability.
  arXiv  Detail & Related papers  (2024-09-26T03:07:32Z)
• Diffusion-Based Neural Network Weights Generation [80.89706112736353]
  D2NWG is a diffusion-based neural network weights generation technique that efficiently produces high-performing weights for transfer learning. Our method extends generative hyper-representation learning to recast the latent diffusion paradigm for neural network weights generation. Our approach is scalable to large architectures such as large language models (LLMs), overcoming the limitations of current parameter generation techniques.
  arXiv  Detail & Related papers  (2024-02-28T08:34:23Z)
• Chain-of-Planned-Behaviour Workflow Elicits Few-Shot Mobility Generation in LLMs [20.70758465552438]
  Chain-of-Planned Behaviour significantly reduces the error rate of mobility intention generation from 57.8% to 19.4%. We find mechanistic mobility models, such as gravity model, can effectively map mobility intentions to physical mobility. The proposed CoPB workflow can facilitate GPT-4-turbo to automatically generate high quality labels for mobility behaviour reasoning.
  arXiv  Detail & Related papers  (2024-02-15T09:58:23Z)
• MobilityGPT: Enhanced Human Mobility Modeling with a GPT model [12.01839817432357]
  We reformat human mobility modeling as an autoregressive generation task to address these issues. We propose a geospatially-aware generative model, MobilityGPT, to ensure its controllable generation. Experiments on real-world datasets demonstrate MobilityGPT's superior performance over state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-02-05T18:22:21Z)
• Towards Efficient Task-Driven Model Reprogramming with Foundation Models [52.411508216448716]
  Vision foundation models exhibit impressive power, benefiting from the extremely large model capacity and broad training data. However, in practice, downstream scenarios may only support a small model due to the limited computational resources or efficiency considerations. This brings a critical challenge for the real-world application of foundation models: one has to transfer the knowledge of a foundation model to the downstream task.
  arXiv  Detail & Related papers  (2023-04-05T07:28:33Z)
• Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning [53.73083199055093]
  We show that attention-based architectures (e.g., Transformers) are fairly robust to distribution shifts. Our experiments show that replacing convolutional networks with Transformers can greatly reduce catastrophic forgetting of previous devices.
  arXiv  Detail & Related papers  (2021-06-10T21:04:18Z)

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.