Traffic prediction serves as a cornerstone for systems and network services such as the Web of Vehicles (WoV), online navigation, and smart city applications. Despite the proliferation of model architectures in recent years, existing approaches often suffer from highly customized structures and weak transferability, making it difficult to cope with increasing task heterogeneity and modeling complexity. To address these challenges, we propose ST-LEGO, a modular assembly framework driven by large language models (LLMs) that supports flexible structural composition and automated code generation. ST-LEGO employs a multi-agent collaborative system comprising a Prompt Agent, Assemble Agent, and Code Agent, which are responsible for understanding task requirements, dynamically assembling structural modules, and automatically generating executable PyTorch code. By introducing a standardized module library and an intermediate structural description language (DSL), the framework enables controllable generation, reusable composition, and cross-task generalization of model architectures. Empirical results on multiple real-world traffic datasets demonstrate that models generated by ST-LEGO achieve superior accuracy, structural diversity, and convergence compared to a wide range of manually designed baselines. These results highlight the unique potential and scalability of LLMs as structural architects for traffic prediction, offering a new paradigm for integrating language models into web-interactive intelligent transportation systems.

Automated log analysis is crucial to ensure the high availability and reliability of complex systems. The advent of Large Language Models (LLMs) in Natural Language Processing (NLP) has ushered in a new era of language model-driven automated log analysis, garnering significant interest. Within this field, two primary paradigms based on language models for log analysis have become prominent. Small Language Models (SLMs) (such as BERT) follow the pre-train and fine-tune paradigm, focusing on the specific log analysis task through fine-tuning on supervised datasets. On the other hand, LLMs (such as ChatGPT) following the in-context learning paradigm, analyze logs by providing a few examples in prompt contexts without updating parameters. Despite their respective strengths, both models exhibit inherent limitations. By comparing SLMs and LLMs, we notice that SLMs are more cost-effective but less powerful, whereas LLMs with large parameters are highly powerful but expensive and inefficient. To tradeoff between the performance and inference costs of both models in automated log analysis, this article introduces an adaptive log analysis framework known as AdaptiveLog, which effectively reduces the costs associated with LLM while ensuring superior results. This framework collaborates an LLM and an SLM, strategically allocating the LLM to tackle complex logs while delegating simpler logs to the SLM. Specifically, to efficiently query the LLM, we propose an adaptive selection strategy based on the uncertainty estimation of the SLM, where the LLM is invoked only when the SLM is uncertain. In addition, to enhance the reasoning ability of the LLM in log analysis tasks, we propose a novel prompt strategy by retrieving similar error-prone cases as the reference, enabling the model to leverage past error experiences and learn solutions from these cases. We evaluate AdaptiveLog on different log analysis tasks, Extensive experiments demonstrate that AdaptiveLog achieves state-of-the-art results across different tasks, elevating the overall accuracy of log analysis while maintaining cost efficiency. Our source code and detailed experimental data are available at https://github.com/LeaperOvO/AdaptiveLog-review .

Variation of Arctic sea ice has significant impacts on polar ecosystems, transporting routes, coastal communities, and global climate. Tracing the change of sea ice at a finer scale is paramount for both operational applications and scientific studies. Recent pan-Arctic sea ice forecasting methods that leverage advances in artificial intelligence have made promising progress over numerical models. However, forecasting sea ice at higher resolutions is still under-explored. To bridge the gap, we propose a two-module cooperative deep learning framework, IceDiff, to forecast sea ice concentration at finer scales. IceDiff first leverages a vision transformer to generate coarse yet superior forecasting results over previous methods at a regular 25 km grid. This high-quality sea ice forecasting can be utilized as reliable guidance for the next module. Subsequently, an unconditional diffusion model pre-trained on low-resolution sea ice concentration maps is utilized for sampling down-scaled sea ice forecasting via a zero-shot guided sampling strategy and a patch-based method. For the first time, IceDiff demonstrates sea ice forecasting with a 6.25 km resolution. IceDiff extends the boundary of existing sea ice forecasting models and more importantly, its capability to generate high-resolution sea ice concentration data is vital for pragmatic usages and research. Code is available at https://github.com/EtronTech/IceDiff.

Novel view synthesis (NVS) and surface reconstruction (SR) are essential tasks in 3D Gaussian Splatting (3D-GS). Despite recent progress, these tasks are often addressed independently, with GS-based rendering methods struggling under diverse light conditions and failing to produce accurate surfaces, while GS-based reconstruction methods frequently compromise rendering quality. This raises a central question: must rendering and reconstruction always involve a trade-off? To address this, we propose MGSR, a 2D/3D Mutual-boosted Gaussian splatting for Surface Reconstruction that enhances both rendering quality and 3D reconstruction accuracy. MGSR introduces two branches--one based on 2D-GS and the other on 3D-GS. The 2D-GS branch excels in surface reconstruction, providing precise geometry information to the 3D-GS branch. Leveraging this geometry, the 3D-GS branch employs a geometry-guided illumination decomposition module that captures reflected and transmitted components, enabling realistic rendering under varied light conditions. Using the transmitted component as supervision, the 2D-GS branch also achieves high-fidelity surface reconstruction. Throughout the optimization process, the 2D-GS and 3D-GS branches undergo alternating optimization, providing mutual supervision. Prior to this, each branch completes an independent warm-up phase, with an early stopping strategy implemented to reduce computational costs. We evaluate MGSR on a diverse set of synthetic and real-world datasets, at both object and scene levels, demonstrating strong performance in rendering and surface reconstruction. Code is available at https://github.com/TsingyuanChou/MGSR.

Fine-grained traffic management and prediction are fundamental to key applications such as autonomous driving, lane change guidance, and traffic signal control. However, obtaining lane-level traffic data has become a critical bottleneck for data-driven models due to limitations in the types and number of sensors and issues with the accuracy of tracking algorithms. To address this, we propose the Fine-grained Road Traffic Inference (FRTI) task, which aims to generate more detailed lane-level traffic information using limited road data, providing a more energy-efficient and cost-effective solution for precise traffic management. This task is abstracted as the first scene of the spatio-temporal graph node generation problem. We designed a two-stage framework-RoadDiff-to solve the FRTI task. This framework leverages the Road-Lane Correlation Autoencoder-Decoder and the Lane Diffusion Module to fully utilize the limited spatio-temporal dependencies and distribution relationships of road data to accurately infer fine-grained lane traffic states. Based on existing research, we designed several baseline models with the potential to solve the FRTI task and conducted extensive experiments on six datasets representing different road conditions to validate the effectiveness of the RoadDiff model in addressing the FRTI task. The relevant datasets and code are available at https://github.com/ShuhaoLii/RoadDiff.

Traffic prediction has long been a focal and pivotal area in research, witnessing both significant strides from city-level to road-level predictions in recent years. With the advancement of Vehicle-to-Everything (V2X) technologies, autonomous driving, and large-scale models in the traffic domain, lane-level traffic prediction has emerged as an indispensable direction. However, further progress in this field is hindered by the absence of comprehensive and unified evaluation standards, coupled with limited public availability of data and code. In this paper, we present the first systematic classification framework for lane-level traffic prediction, offering a structured taxonomy and analysis of existing methods. We construct three representative datasets from two real-world road networks, covering both regular and irregular lane configurations, and make them publicly available to support future research. We further establishes a unified spatial topology structure and prediction task formulation, and proposes a simple yet effective baseline model, GraphMLP, based on graph structure and MLP networks. This unified framework enables consistent evaluation across datasets and modeling paradigms. We also reproduce previously unavailable code from existing studies and conduct extensive experiments to assess a range of models in terms of accuracy, efficiency, and applicability, providing the first benchmark that jointly considers predictive performance and training cost for lane-level traffic scenarios. All datasets and code are released athttps://github.com/ShuhaoLii/LaneLevel-Traffic-Benchmark.

Logs play a critical role in providing essential information for system monitoring and troubleshooting. Recently, with the success of pre-trained language models (PLMs) and large language models (LLMs) in natural language processing (NLP), smaller PLMs (such as BERT) and LLMs (like GPT-4) have become the current mainstream approaches for log analysis. Despite the remarkable capabilities of LLMs, their higher cost and inefficient inference present significant challenges in leveraging the full potential of LLMs to analyze logs. In contrast, smaller PLMs can be fine-tuned for specific tasks even with limited computational resources, making them more practical. However, these smaller PLMs face challenges in understanding logs comprehensively due to their limited expert knowledge. To address the lack of expert knowledge and enhance log understanding for smaller PLMs, this paper introduces a novel and practical knowledge enhancement framework, called LUK, which acquires expert knowledge from LLMs automatically and then enhances the smaller PLM for log analysis with the expert knowledge. LUK can take full advantage of both types of models. Specifically, we design a multi-expert collaboration framework based on LLMs with different roles to acquire expert knowledge. In addition, we propose two novel pre-training tasks to enhance the log pre-training with expert knowledge. LUK achieves state-of-the-art results on different log analysis tasks, and extensive experiments demonstrate that expert knowledge from LLMs can be utilized more effectively to understand logs. Our source code and detailed experimental data are available athttps://github.com/LeaperOvO/LUK.

Lane-level traffic prediction is crucial for refined smart city applications, yet the scarcity and quality issues of datasets hinder its development. To overcome these challenges, this study introduces a novel M ulti- c hannel g raph-structured V ariational A uto E ncoder model, McgVAE. This model integrates road-level information to provide a global perspective for lane prediction and performs integrated tasks through three interconnected channels: the road-level channel ensures accurate prediction of road traffic states and communicates closely with the data quality channel to share historical and predicted road information; the data quality channel leverages road-level information to identify and correct missing and noisy data; and finally, the lane channel uses the aforementioned information for lane-level traffic prediction. After extensive experimental comparisons with multiple baseline models across three datasets, the McgVAE model demonstrated outstanding predictive performance and the ability to handle data missingness and noise

With the widespread application of intelligent transportation systems and navigation software, traffic prediction should be modeled in finer granularity to facilitate lane-changing guidance and congestion mitigation. However, existing studies divide the road network into continuous segments which assumes different lanes share the same spatio-temporal patterns. This paper proposes a novel lightweight, attention-based, fully convolutional model, named the Spatio-Temporal Attention- Based Convolutional network (ST-ABC), where lane segments are treated as graph nodes and dynamically models the adjacent spatial dependencies using local attention graph convolution. The attention-based dilated convolutions can process longer sequence periods in parallel, and a global attention layer allows individual nodes to be associated with the global context. By setting a target window, it can further reduce unnecessary computations and improve the prediction effect for the targeted area. Further-more, the ST-ABC model facilitates the simultaneous integration of spatio-temporal information and relational distance metrics among lane segments, enriching the granularity of multi-scaled spatial prediction. Empirical evaluations conducted on two real-world datasets substantiate the augmented efficacy of the STABC model in comparison to established models, with a marked prominence in long-term prediction scenarios.

The pervasiveness of GPS-enabled devices and wireless communication technologies results in a proliferation of traffic data in intelligent transportation systems, where traffic prediction is often essential to enable reliability and safety. Many recent studies target traffic prediction using deep learning techniques. They model spatio-temporal dependencies among traffic states by deep learning and achieve good overall performance. However, existing studies ignore the bias on traffic prediction models, which refers to non-uniformed performance distribution across road segments, especially the significantly poor prediction results on certain road segments. To solve this issue, we propose a framework named spatio-temporal mixture-of-experts (ST-MoE) that aims to eliminate the bias on traffic prediction. In general, we refer to any traffic prediction model as the based model, and adopt the proposed ST-MoE framework as a plug-in to debias. ST-MoE uses stacked convolution-based networks to learn spatio-temporal representations of individual patterns of road segments and then adaptively assigns appropriate expert layers (sub-networks) to different patterns through a spatio-temporal gating network. To this end, the patterns can be distinguished, and biased performance among road segments can be eliminated by experts tailored for specific patterns, which also further improves the overall prediction accuracy of the base model. Extensive experimental results on various base models and real-world datasets prove the effectiveness of ST-MoE.

Traffic prediction has drawn increasing attention due to its essential role in smart city applications. To achieve precise predictions, a large number of approaches have been proposed to model spatial dependencies and temporal dynamics. Despite their superior performance, most existing studies focus datasets that are usually in large geographic scales, e.g., citywide, while ignoring the results on specific regions. However, in many scenarios, for example, route planning on time-dependent road networks, only small regions are of interest. We name the task of answering forecasting requests from any query region of interest (ROI) as ROI-demand traffic prediction (RTP). In this paper, we make a primary observation that existing methods fail to jointly achieve effectiveness and efficiency for RTP. To address this issue, a novel model-agnostic framework based on pre-Training, Querying and fine-Tuning, named TQT, is proposed, which first customizes input data given an ROI, and then makes fast adaptation from pre-trained traffic prediction backbone models by fine-tuning. We evaluate TQT on two real-world traffic datasets, performing both flow and speed prediction tasks. Extensive experiment results demonstrate the effectiveness and efficiency of the proposed method.