Vision-LLMs for Spatiotemporal Traffic Forecasting

• URL: http://arxiv.org/abs/2510.11282v1
• Date: Mon, 13 Oct 2025 11:15:56 GMT
• Title: Vision-LLMs for Spatiotemporal Traffic Forecasting
• Authors: Ning Yang, Hengyu Zhong, Haijun Zhang, Randall Berry,
• Abstract summary: Large Language Models (LLMs) inherently struggle to model the complex spatial dependencies of grid-based traffic data.<n>We propose ST-Vision-LLM, a novel framework reframe thatstemporal forecasting as a vision-language fusion problem.<n>We show that ST-Vision-LLM outperforms existing methods by 15.6% in long-term prediction accuracy and exceeds the second-best baseline by over 30.04% in cross-domain scenarios.
• Score: 14.700408329373998
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Accurate spatiotemporal traffic forecasting is a critical prerequisite for proactive resource management in dense urban mobile networks. While Large Language Models (LLMs) have shown promise in time series analysis, they inherently struggle to model the complex spatial dependencies of grid-based traffic data. Effectively extending LLMs to this domain is challenging, as representing the vast amount of information from dense geographical grids can be inefficient and overwhelm the model's context. To address these challenges, we propose ST-Vision-LLM, a novel framework that reframes spatiotemporal forecasting as a vision-language fusion problem. Our approach leverages a Vision-LLM visual encoder to process historical global traffic matrices as image sequences, providing the model with a comprehensive global view to inform cell-level predictions. To overcome the inefficiency of LLMs in handling numerical data, we introduce an efficient encoding scheme that represents floating-point values as single tokens via a specialized vocabulary, coupled with a two-stage numerical alignment fine-tuning process. The model is first trained with Supervised Fine-Tuning (SFT) and then further optimized for predictive accuracy using Group Relative Policy Optimization (GRPO), a memory-efficient reinforcement learning method. Evaluations on real-world mobile traffic datasets demonstrate that ST-Vision-LLM outperforms existing methods by 15.6% in long-term prediction accuracy and exceeds the second-best baseline by over 30.04% in cross-domain few-shot scenarios. Our extensive experiments validate the model's strong generalization capabilities across various data-scarce environments.

Related papers

• Wireless Traffic Prediction with Large Language Model [54.07581399989292]
  TIDES is a novel framework that captures spatial-temporal correlations for wireless traffic prediction.<n> TIDES achieves efficient adaptation to domain-specific patterns without incurring excessive training overhead.<n>Our results indicate that integrating spatial awareness into LLM-based predictors is the key to unlocking scalable and intelligent network management in future 6G systems.
  arXiv  Detail & Related papers  (2025-12-19T04:47:40Z)
• Co-Training Vision Language Models for Remote Sensing Multi-task Learning [68.15604397741753]
  Vision language models (VLMs) have achieved promising results in RS image understanding, grounding, and ultra-high-resolution (UHR) image reasoning.<n>We present RSCoVLM, a simple yet flexible VLM baseline for RS MTL.<n>We propose a unified dynamic-resolution strategy to address the diverse image scales inherent in RS imagery.
  arXiv  Detail & Related papers  (2025-11-26T10:55:07Z)
• CronusVLA: Towards Efficient and Robust Manipulation via Multi-Frame Vision-Language-Action Modeling [84.51372201195132]
  CronusVLA is a unified framework that extends single-frame VLA models to the multi-frame paradigm.<n>CronusVLA achieves leading performance and superior robustness, with a 70.9% success rate.<n>These results highlight the potential of efficient multi-frame adaptation in VLA models for more powerful and robust real-world deployment.
  arXiv  Detail & Related papers  (2025-06-24T17:30:27Z)
• Federated Dynamic Modeling and Learning for Spatiotemporal Data Forecasting [1.492694722803554]
  This paper presents an advanced Federated Learning (FL) framework for forecasting complextemporal data.<n>We replace the Gated Recurrent Unit (RU) module with a Long Short-Term Memory (LSTM) network.<n>The resulting architecture significantly improves the model's capacity to handle complex temporal patterns in diverse forecasting applications.
  arXiv  Detail & Related papers  (2025-03-06T15:16:57Z)
• PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection [68.8373788348678]
  Visual instruction tuning adapts pre-trained Multimodal Large Language Models to follow human instructions.<n>PRISM is the first training-free framework for efficient visual instruction selection.<n>It reduces the end-to-end time for data selection and model tuning to just 30% of conventional pipelines.
  arXiv  Detail & Related papers  (2025-02-17T18:43:41Z)
• Scenario Understanding of Traffic Scenes Through Large Visual Language Models [2.3302708486956454]
  Large Visual Language Models (LVLMs) present a compelling solution by automating image analysis and categorization through contextual queries.<n>In this study, we evaluate the capabilities of LVLMs to understand and classify urban traffic scenes on both an in-house dataset and the BDD100K.<n>We propose a scalable captioning pipeline that integrates state-of-the-art models, enabling a flexible deployment on new datasets.
  arXiv  Detail & Related papers  (2025-01-28T18:23:12Z)
• Strada-LLM: Graph LLM for traffic prediction [62.2015839597764]
  A considerable challenge in traffic prediction lies in handling the diverse data distributions caused by vastly different traffic conditions.<n>We propose a graph-aware LLM for traffic prediction that considers proximal traffic information.<n>We adopt a lightweight approach for efficient domain adaptation when facing new data distributions in few-shot fashion.
  arXiv  Detail & Related papers  (2024-10-28T09:19:29Z)
• Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language Alignment [57.0121616203175]
  We propose FiSAO, a novel self-alignment method that utilizes the model's own visual encoder as a fine-grained verifier to improve vision-language alignment.<n>By leveraging token-level feedback from the vision encoder, FiSAO significantly improves vision-language alignment, even surpassing traditional preference tuning methods that require additional data.
  arXiv  Detail & Related papers  (2024-10-18T03:34:32Z)
• TPLLM: A Traffic Prediction Framework Based on Pretrained Large Language Models [27.306180426294784]
  We introduce TPLLM, a novel traffic prediction framework leveraging Large Language Models (LLMs) In this framework, we construct a sequence embedding layer based on Conal Neural Networks (LoCNNs) and a graph embedding layer based on Graph Contemporalal Networks (GCNs) to extract sequence features and spatial features. Experiments on two real-world datasets demonstrate commendable performance in both full-sample and few-shot prediction scenarios.
  arXiv  Detail & Related papers  (2024-03-04T17:08:57Z)
• Spatial-Temporal Large Language Model for Traffic Prediction [21.69991612610926]
  We propose a Spatial-Temporal Large Language Model (ST-LLM) for traffic prediction. In the ST-LLM, we define timesteps at each location as tokens and design a spatial-temporal embedding to learn the spatial location and global temporal patterns of these tokens. In experiments on real traffic datasets, ST-LLM is a powerful spatial-temporal learner that outperforms state-of-the-art models.
  arXiv  Detail & Related papers  (2024-01-18T17:03:59Z)

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.