China Mobile (China)

Federated learning (FL) has garnered significant attention as an emerging distributed learning paradigm due to its inherent privacy protection features. Cell-free massive MIMO (CF-mMIMO) is a key enabler for future wireless communication systems, offering high reliability, energy efficiency, low latency, and seamless coverage to meet the demands of FL. This paper investigates an FL realization in a CF-mMIMO system with multi-antenna access points and user equipments, employing multi-datastream transmission to leverage the advantages of multi-antenna transmission. The results of FL convergence analysis under two typical cooperative reception scenarios in the CF-mMIMO system—fully-centralized processing (FCP) and large-scale fading decoding (LSFD)—are presented without predefining the transmission and reception strategies. Based on the analysis, the optimization of FL convergence performance was carried out. Through decoupling, the FL convergence performance optimization problem is ultimately transformed into a series of weighted sum-MSE minimization problems. The alternative optimization approach is employed to design iterative optimization algorithms for both cooperative reception scenarios, thereby achieving optimal convergence performance. Simulation experiments validate the effectiveness of the convergence analysis and demonstrate the advantages of multi-antenna multi-datastream transmission. Moreover, the proposed alternating iterative algorithms improve the convergence performance of FL under most experimental setups.

To address the high cost of separate operation and maintenance of traditional IP and optical layers, as well as the challenges of increasing types of information network services and surging traffic, this paper takes the "IP +optical" converged network as the research object, aiming to improve network resource utilization and efficiency. By adopting Software-Defined Networking (SDN) technology, a mechanism for separating physical and logical devices is designed, and a network slicing generation algorithm based on multi-user requirements is proposed. Virtualization of the IP layer and optical network layer is realized through the shortest path algorithm, while a resource allocation method based on this algorithm is constructed, and a port queue bandwidth adjustment method is designed to ensure Quality of Service(QoS). The results show that this technology can achieve bandwidth isolation and efficient resource utilization between the IP and optical network layers, improve physical link utilization, and meet the QoS requirements of virtual machine service traffic.

We propose Contextual History for Adaptive and Simple Exploitation (CHASE), a novel multi-turn method for Large Language Model (LLM) jailbreaking. Rather than directly attack an LLM that may be difficult to jailbreak, CHASE first collects jailbroken histories from an easy-to-jailbreak LLM and then transfers them to the target LLM. Through this history transfer process, CHASE misleads the target LLM into thinking that it is responsible for producing the jailbroken histories and increases the chances of successful jailbreaking by prompting it to continue the conversation. Extensive evaluations on mainstream LLMs show that CHASE consistently achieves higher attack success rates and demands fewer computational resources compared to existing methods.

Spatio-temporal data generation aims to synthesize realistic urban data across graph nodes by learning spatial and temporal dependencies. This task plays a crucial role in urban planning by enabling the simulation of unobserved nodes. However, existing approaches face critical limitations that time series generation methods fail to generalize to unseen nodes, while spatio-temporal generative models are either restricted to the trajectory generation task or dependent on auxiliary data inputs. To bridge these gaps, we propose a Knowledge Graph Guided Heterogeneity-Informed Diffusion Model (KGDiff) in this paper through the following key innovations. First, we design a geometry-aware mixture of experts integrating Euclidean, hyperbolic, and hyperspherical representations to comprehensively encode urban structural knowledge. Next, we present a learnable meta spatio-temporal pattern module that normalizes node-specific heterogeneity before the generation process, and a conditional denoising process that progressively transforms random noise into realistic samples under structural guidance. Finally, extensive experiments across real-world urban datasets demonstrate that KGDiff achieves the state-of-art performance in generating realistic urban spatio-temporal data.

In object detection, annotation cost and computational efficiency are important factors in iterative model improvement under standard benchmark settings. Active learning (AL) addresses this challenge by selecting informative samples for labeling; however, many detection-oriented AL methods incur substantial overhead due to repeated inference (e.g., augmentation-based consistency). This paper introduces Uncertainty3D, a lightweight uncertainty proxy designed for standard CNN-based object detectors. It leverages native pre-NMS predictions to estimate sample informativeness using a single forward pass. We propose a tri-dimensional formulation that captures inconsistencies in position, scale, and category across proposal-consistent predictions. Experiments on PASCAL VOC and MS COCO using representative CNN-based detectors (Faster R-CNN and RetinaNet) show competitive mAP versus representative baselines and about 3–4× faster uncertainty estimation than augmentation-based baselines.

Introduction High-precision radio wave propagation over maritime environments is of great importance for ensuring reliable maritime wireless communications. Methods To support the development of maritime transmission services, this work employs genetic algorithms to extract features from measured maritime data, thereby constructing a data-model-driven propagation model. The proposed model is established using measurement datasets collected in the South China Sea, covering the frequency range of 99 MHz to 1000 MHz over transmission distances up to 60 km. By integrating the strengths of both data-driven and model-driven approaches, a high-precision empirical model for maritime VHF and UHF propagation loss is developed. Specifically, we first analyze the propagation mechanisms of radio waves in the study region based on the measured data, and then combine them with the ITU-R P.2001 model to define a driving model with undetermined coefficients. These coefficients are subsequently determined using genetic algorithms through feature extraction from the measurement data. Finally, the proposed model is validated against the measurement dataset. Results Results demonstrate that the model achieves an average root-mean-square error of 2.13 dB, representing a 72.73% improvement compared with the ITU-R P.2001 model. Discussion The study of high-precision radio wave propagation over maritime environments is of great importance for ensuring reliable maritime wireless communications.

Multi-key homomorphic encryption (MKHE) is crucial for secure collaborative computing, yet it suffers from high multiplicative depth and computational overhead during Look-Up Table (LUT) evaluations, particularly for large input domains. To address these challenges, this paper proposes an optimized LUT evaluation method based on multivariate polynomial approximation. Specifically, we partition the high-dimensional input space into several lower-dimensional variables to design low-depth multivariate polynomials. By integrating blockwise encoding and tensor-based transformations, we construct a parallelizable evaluation framework that maps multivariate functions into a high-dimensional polynomial-coefficient space. This approach allows for efficient parallel processing and effective noise management. Theoretical analysis demonstrates that our method significantly reduces the multiplicative depth from O(l) to O(l/α), indicating its robustness and efficiency in large-scale LUT scenarios.