JWJinming Wang

Jinming Wang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Jinming Wang has a total of 4 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Foundation Model for Conditional Trajectory Generation with Unstable Context Availability

    by Jinming Wang, Hai Wang, Hongkai Wen, Geyong Min, Man Luo

    With the proliferation of data-driven smart city applications, massive amounts of trajectory data are being collected. These trajectories are typically captured as sequences of GPS coordinates, and are often enriched with diverse contextual information, such as timestamps, user IDs, and service metadata. They form the backbone of many smart city applications such as navigation, logistics, and urban planning. Generative tasks on this data - such as trajectory prediction, recovery, and synthesis - play a critical role in these applications by filling data gaps, simulating scenarios, or augmenting datasets, which all require generating coordinates conditioned on partial observations and auxiliary context. There are two weaknesses in most existing methods: i) they are typically tailored for a specific task and rely on fixed sets of contextual features, leading to repeated efforts across tasks and domains; ii) they are not robust to unstable context availability, as contextual information is often incomplete, unavailable, or inconsistent in real-world settings. In this work, we present TrajWeaver , a novel diffusion-based foundation model designed to support multiple conditional trajectory generation tasks within a single framework, while being flexible to diverse conetxts and robust to unstable context availability. TrajWeaver introduces a novel State Propagation Pipeline (SPP) on top of the diffusion model, which uses multi-scale state features as messengers to proprgate and refine contextual information and knowledge across denoising steps. This design improves robustness to missing or partial context and enables seamless adaptation to new types of conditional features without retraining the full model. Experiments across three trajectory generation tasks demonstrate that TrajWeaver achieves strong performance and generalization under different settings, showcasing its potential as a foundation model for trajectory generation.

  • Open Access

    TRACE: Trajectory Recovery with State Propagation Diffusion for Urban Mobility

    by Jinming Wang, Hai Wang, Hongkai Wen, Geyong Min, Man Luo

  • Road Network Generation From Noisy Trajectories With Graph Latent Diffusion Models

    by Jinming Wang, Hongkai Wen, Geyong Min, Man Luo

    Modern navigation systems and logistics services rely heavily on digital road networks, which can be accurately constructed from crowd-sourced GPS trajectories. Yet, most existing trajectory-based road network generators project GPS coordinates to 2D grid, followed by semantic segmentation to obtain road heatmap, and further processed to road network graph via heuristic processing. The data through this pipeline involve multiple cross-modal heuristic conversions, which cause serious information loss and harm overall robustness. In this paper, we propose a novel end-to-end learnable deep learning approach, named GraphWalker, to generate accurate road network graphs directly from raw trajectories with minimal information loss. In particular, GraphWalker is a latent diffusion model (LDM) consisting of two key components: the Trajectory-to-Walks Diffusion Transformer (T2W-DiT) generates walks with trajectories as conditions, and the Walks-to-Graph Variational Auto-Encoder (W2G-VAE) reconstructs road network graphs from walks. GraphWalker keeps the data in geographical space throughout the pipeline to retain all information within raw trajectories. Additionally, the end-to-end learnable design removes the heuristic processing and enhances the robustness and generalizability. Extensive experiments on multiple datasets demonstrate that the proposed GraphWalker can effectively generate high-quality road networks from noisy and sparse trajectories, showcasing significant improvements of up to 55.43% over state-of-the-art.