During the During the National People's Congress and the Chinese Political Consultative Conference in 2024, the ‘low-altitude economy’ was included in the government work report as a significant factor driving new quality productive forces. In the New Radio (NR) network, when a terminal is accessed, the base station uses SSB (Synchronization Signal Block) beam sweeping to detect the optimal beam for the terminal. After the terminal accesses and obtains the configuration information of the reference signal, it feeds back the channel state information (CSI), and the base station uses the optimal beam from CSI-RS (Channel State Information Reference Signal) beam sweeping. In low-altitude communications, 5G antennas flexibly configure the number of beams, considering horizontal and vertical dimensions. Combining SSB frequency offset technology, the SSB frequency points of the low-altitude network can be staggered with the configuration of the ground network, forming a virtual airground heterogeneous frequency network. This approach enhances performance by reducing handover times and interference.

This paper investigates the workflow and requirement of telecommunications operators in handling 4G/5G user network quality complaints and proposes a solution that combines large and small models to achieve more intelligent complaint handling. The large model is responsible for comprehensively analyzing unstructured data such as user complaint texts, extracting key information, and understanding user intentions. Small models are used for indepth processing of structured data related to network performance indicators, conducting root cause analysis, and providing targeted solutions. The models and systems are applied to current network operations, significantly reducing network maintenance optimization work orders, saving labor costs, and improving work efficiency.

With the rapid development in 6G networks, traditional network operation and maintenance (O&M) approaches are insufficient to handle the scale and real-time demands. This paper presents a novel O&M system, applying a multiagent scheduling algorithm to autonomously detect, diagnose, and resolve network faults. The system is structured in five layers: Data, Data Model, Agent, Application, and Interaction layers. And five classes of agents are integrated. Experimental results show the system's ability to outperform manual processes, which demonstrates the efficiency for the demanding needs of nextgeneration network management.

Temporal action proposal generation plays a vital role in the analysis of untrimmed videos and has garnered growing interest from researchers. Nevertheless, the presence of long-term temporal dependencies and the large variation in action durations within untrimmed videos pose significant challenges for accurately localizing action boundaries. To overcome the aforementioned issues, we design a novel Transformer-based Temporal Feature Pyramid Network (TTFPN) tailored for generating action proposals. Specifically, we introduce a local transformer to capture longterm temporal information while reducing computational complexity through the substitution of conventional selfattention with a localized variant. Subsequently, a temporal feature pyramid is built to produce multi-scale representations, enabling the model to effectively handle action instances of varying durations. Based on this temporal feature pyramid, we employ a convolutional network-based predictor to generate action proposals in an anchor-free manner. We evaluate TTFPN on THUMOS14, a standard benchmark for temporal action detection, to validate its effectiveness. The results show that TTFPN achieves competitive performance and significantly outperforms previous methods.

UV unwrapping flattens 3D surfaces to 2D with minimal distortion, often requiring the complex surface to be decomposed into multiple charts. Although extensively studied, existing UV unwrapping methods frequently struggle with AI-generated meshes, which are typically noisy, bumpy, and poorly conditioned. These methods often produce highly fragmented charts and suboptimal boundaries, introducing artifacts and hindering downstream tasks. We introduce PartUV, a part-based UV unwrapping pipeline that generates significantly fewer, part-aligned charts while maintaining low distortion. Built on top of a recent learning-based part decomposition method PartField, PartUV combines high-level semantic part decomposition with novel geometric heuristics in a top-down recursive framework. It ensures each chart’s distortion remains below a user-specified threshold while minimizing the total number of charts. The pipeline integrates and extends parameterization and packing algorithms, incorporates dedicated handling of non-manifold and degenerate meshes, and is extensively parallelized for efficiency. Evaluated across four diverse datasets—including man-made, CAD, AI-generated, and Common Shapes—PartUV outperforms existing tools and recent neural methods in chart count and seam length, achieves comparable distortion, exhibits high success rates on challenging meshes, and enables new applications like part-specific multi-tiles packing. Code for this paper is at https://github.com/EricWang12/PartUV.

This paper proposes a lightweight video semantic communication (LVSC) method to enable end-to-end wireless video transmissions. The proposed LVSC method cuts down the model parameters through designing a spatial pyramid structure for the residual codec and a one-dimensional CNN-based channel attention model for the joint source-channel coding (JSCC) codec, respectively. Additionally, the Swin Transformer is introduced to the JSCC codec to accelerate the semantic coding. Extensive experiments validate that the proposed LVSC performs better than the baseline methods in terms of PSNR and MS-SSIM while inferring much faster at the same time.

Open-world 3D reconstruction models have recently garnered significant attention. However, without sufficient 3D inductive bias, existing methods typically entail expensive training costs and struggle to extract high-quality 3D meshes. In this work, we introduce MeshFormer, a sparse-view reconstruction model that explicitly leverages 3D native structure, input guidance, and training supervision. Specifically, instead of using a triplane representation, we store features in 3D sparse voxels and combine transformers with 3D convolutions to leverage an explicit 3D structure and projective bias. In addition to sparse-view RGB input, we require the network to take input and generate corresponding normal maps. The input normal maps can be predicted by 2D diffusion models, significantly aiding in the guidance and refinement of the geometry's learning. Moreover, by combining Signed Distance Function (SDF) supervision with surface rendering, we directly learn to generate high-quality meshes without the need for complex multi-stage training processes. By incorporating these explicit 3D biases, MeshFormer can be trained efficiently and deliver high-quality textured meshes with fine-grained geometric details. It can also be integrated with 2D diffusion models to enable fast single-image-to-3D and text-to-3D tasks. **Videos are available at https://meshformer3d.github.io/**

When it comes to deploying deep vision models, the behavior of these systems must be explicable to ensure confidence in their reliability and fairness. A common approach to evaluate deep learning models is to build a labeled test set with attributes of interest and assess how well it performs. However, creating a balanced test set (i.e., one that is uniformly sampled over all the important traits) is often time-consuming, expensive, and prone to mistakes. The question we try to address is: can we evaluate the sensitivity of deep learning models to arbitrary visual attributes without an annotated test set? This paper argues the case that Zero-shot Model Diagnosis (ZOOM) is possible without the need for a test set nor labeling. To avoid the need for test sets, our system relies on a generative model and CLIP. The key idea is enabling the user to select a set of prompts (relevant to the problem) and our system will automatically search for semantic counterfactual images (i.e., synthesized images that flip the prediction in the case of a binary classifier) using the generative model. We evaluate several visual tasks (classification, key-point detection, and segmentation) in multiple visual domains to demonstrate the viability of our methodology. Extensive experiments demonstrate that our method is capable of producing counterfactual images and offering sensitivity analysis for model diagnosis without the need for a test set.

With the 5G commercial deployments rapidly proceeding, operating mobile networks efficiently has become a great challenge. Self-organizing networks have been proposed to focus on automatically monitoring, analyzing and optimizing networks. Regarding the growing scale and complexity, 5G self-organizing networks confront the challenge to handle the massive data. Therefore, AI models are urgently needed to enable end-to-end network automation. In this demonstration, benefiting from the open data interfaces of the standardized NWDAF within the 5GC network, we implement a containerized network data analytic framework embedding Docker-based AI model containers into 5G networks. Furthermore, we simulate a use case automatically monitoring and optimizing user-level QoE in real time and simulation results are presented.

With AI and big data technologies, telecom operators are looking to change the traditional O&M model from reactive problem handling to proactive prevention and prediction. This paper proposes a model framework trained on multiple data sources for the 5G wireless network to support proactive O&M tasks based on complaint prediction. By grouping user complaints into base station complaint prediction, the model enhanced precision scores while maintaining high recall scores. The model has been integrated into the operator’s work order system to support intelligent operational optimization workflow.

We are going to enter the most intelligent era than ever before. Intelligent electronics network is infiltrating into our life and making it more convenient. Nonetheless, users always want smart home be more intelligent and complete more features. users’ issues are endless. Modular packaging device services and effective choreography algorithms can flexible fit different issues. Many organizations have been proving, implementing and managing business solutions for many specific individual industries. However, when comes to smart home for end users, there are numerous limitations in process, tooling, and skills. In the paper, we provide a lightweight visualized service creating tool and an AI-driven service flow construction model. It helps end users to create services though drag-and-drop, and then deploy new services automatically. And in the end a case study will be introduced.

This paper investigates on the remote interference problem in the TDD network and proposes an intelligent 5G Remote Interference Avoidance and Clustering Scheme (RIAC), on the basis of RIM-RS (remote interference management-reference signal) and clustering algorithm. This paper adopts the GBLA-DBSACN (the grid-based local adaptive DBSCAN) algorithm based on the traditional DBSCAN algorithm (Density—Based Spatial Clustering of Application with Noise) to improve the accuracy of interference base station (BS) clustering, which considers the dispersion of interference sources. This scheme helps to locate interference problems and potential sources through testing in the existing network quickly and effectively. By taking corresponding optimization means for these problems, network operators can effectively reduce the interference level in the target area and improve the quality of network construction.

In the mobile and pervasive computing environment, automatic service composition faces the challenges of the highly dynamic network structure and limited computation resources. Existing approaches create service flows under the assumption that network context changes are slower than the time required to plan the composite service which is no longer set up in the mobile and pervasive computing environment. In this paper, we propose an online automatic service composition approach to dynamically construct service flows and interleave the planning and executing processes. Particularly, it introduces a novel distributed heuristic searching algorithm to determine solutions with limited knowledge bases and execute them in real time. Simulation results show that our proposed online approach reduces the composition time and performs faster composition time and higher composition success rates than state-of-the-art approaches in mobile computing environments.

With the evolution of Web technologies, various services have become available in a pervasive network environment. Combining simple atomic services into sophisticated applications with a quality-of-service (QoS) guarantee has become a widely studied problem. Given the increasing number of QoS attributes to be considered, conventional service composition approaches with manual workflows and massive computational burdens are no longer effective. Therefore, this article first suggests an efficient many-objective (with four or more objectives) automatic service composition approach named MaSC. In particular, this article introduces a temporal goal decomposition mechanism based on a temporal model to divide an unwieldy problem into several fine-grained subproblems. Viewing this model as an individual representation, we employ an evolutionary process with a novel fitness function to explore the composition solution. The experimental results on the benchmarks show that our approach can simultaneously optimize up to six objectives and achieve a better trade-off between the computation cost and the QoS than two recently proposed automatic composition approaches.

The rapid development of mobile internet attracts end-users to creating mobile applications. The traditional development process cannot meet their needs. In this paper, we present a cross-platform mobile development environment, EasyApp. It provides a highly-integrated, UI-friendly and easily-operating environment. The architecture of this environment is based on OSGi framework. Users could create mobile applications with draggable widgets and package applications for multiple platforms. Native APIs could be invoked with native API plugins.

Customizable mobile services are usually expressed with complex services composed of different atomic services. Fine-grained atomic mobile services are not so convenient for end users to reuse. Considering that in identical or similar service domains, a great deal of the business logics and functions are reusable within the scope. So we present a template-based framework to allow reuse of services and to achieve rapid mobile application development. The reusable fine-grained service logics and functions are encapsulated into comparatively coarse-grained templates, from which the designers can create the personalized composite services and edit the templates efficiently.

In this paper, we show an end-user oriented tool suite for mobile application development. The advantages of this tool suite are that the graphical user interface (GUI), as well as the application logic can both be developed in a rapid and simple way, and web-based services on the Internet can be integrated into our platform by end-users. This tool suite involves three sub-systems, namely ServiceAccess, EasyApp and LSCE. ServiceAccess takes charge of the registration and management of heterogeneous services, and can export different form of services according to the requirements of the other sub-systems. EasyApp is responsible for developing GUI in the form of mobile app. LSCE takes charge of creating the application logic that can be invoked by mobile app directly. Finally, a development case is presented to illustrate the development process using this tool suite. The URL of demo video: https://youtu.be/mM2WkU1_k-w

*** The rapid development of mobile internet abstracts many non-professional persons to creating mobile applications. Traditional development process cannot meet their needs. In this paper, we present a cross-platform mobile development environment based on OSGi framework, EasyApp. It provides a highly-integrated, UI-friendly and easily-operating environment. Applications are comprehensively developed with web techniques. Users could create mobile applications with draggable widgets. Native APIs of mobile phone can be invoked with abundant plugins. After designing, users could package and download applications of multiple platforms. ***