PLA Information Engineering University

Continuous Merging of Buildings Considering Functional Semantics and Global Optimization

ABSTRACT Continuous generalization is a key technique for achieving continuous scale representation of map features, and the continuous merging of buildings is a crucial component of this process. Existing methods for continuous building merging predominantly focus on smooth geom...

RT-ProtoNet: radiative-transfer-guided few-shot prototype networks for cross-region bathymetry in optically clear reef environments

Satellite-derived bathymetry faces two coupled obstacles: labels are scarce, and models transfer poorly across regions. We propose RT-ProtoNet, a radiative-transfer-guided few-shot prototype network, which takes patches from three penetrating Sentinel-2 bands and treats ICESat-2...

An Architecture-Level Framework for Earth–Moon Reference-Clock Modeling, Timing Compensation, and PNT Sensitivity Analysis

Accurate characterization and compensation of Earth–Moon reference-clock differences are important for cislunar positioning, navigation, and timing (PNT) architectures. This study develops an integrated analytical framework that connects modeled Earth–Moon timing differences, com...

Adversarial Attack via Latent Feature Attribution of Diffusion Models

Traditional adversarial attacks are constrained by \({l_p}\) norm limits, resulting in adversarial examples with high-frequency noise that compromise their imperceptibility. In contrast, attacks using diffusion models without \({l_p}\) norm constraints can generate visually more...

An evolutionary framework with adaptive recovery for online reconfiguration of multi-source measurement systems

Multi-source measurement systems are expected to maintain estimation accuracy and operational robustness under abnormal disturbances. Such disturbances can alter source availability, observation quality, and synchronization conditions, causing a previously deployed configuration...

Graph-guided MADQN based handover strategy for LEO satellite networks

In low earth orbit satellite networks, the high orbital velocity of satellites causes frequent communication link handovers, which adversely affects user service quality and the efficiency of network resource management. To maintain communication continuity, an effective handover...

Real-Time Precise Positioning Performance of BDS-3 PPP-B2b: Evaluation and Marine Buoy Application

This study decodes the BDS-3 PPP-B2b binary data broadcast by BDS satellites using a self-developed software decoder, RT-B2b (Real-Time PPP-B2b). The orbit, clock corrections, and differential code biases (DCB)—collectively referred to as State Space Representation (SSR) correcti...

Adaptive multi-format synergistic table understanding framework for large language models

Tables serve as a foundational medium for representing structured information and are widely adopted across diverse domains such as scientific research, financial analysis, public administration, and data-intensive industrial applications. Existing large language models (LLMs)-ba...

Sustainable AI Request Scheduling with Joint Compute, Network, and Power Optimization

The rapid growth in artificial intelligence (AI) demand has significantly increased the electricity consumption and carbon emissions of computing centers. How to schedule AI requests across computing centers to reduce carbon emissions and electricity costs while maintaining low l...

Sub-monthly volumetric evolution of the supraglacial lakes in Northeastern Greenland based on the topographic depression method

Study region Supraglacial lakes on the northeastern Greenland Ice Sheet (GrIS) during the melt seasons (May–September) from 2018 to 2025. Study focus This study develops a multi-parameter inversion framework for supraglacial lakes by integrating multi-source remote sensing data a...

Measurement report: Quantifying the trade-off between station number and spatial layout in sparse GNSS networks for calibrating all-weather FY-4A precipitable water vapor

Abstract. Integrating satellite-derived precipitable water vapor (PWV) provides data with high spatiotemporal resolution, which is crucial for monitoring and forecasting extreme weather. However, current fusion and calibration methods typically relies on dense GNSS networks, hind...

ATAC: Anchor-tail aware context parallelism for LLM training

Large language model training commonly relies on multidimensional parallelism, including data, tensor, pipeline, and context parallelism, to support long-context and large-scale workloads. However, real pretraining corpora consist of highly heterogeneous variable-length samples,...

PassBitNet: low-resource password guessing using 1-Bit quantized transformers

Large language models (LLMs) demonstrate exceptional accuracy in password-guessing tasks, but their massive memory cost, high computational demands, and high duplicate rates severely limit deployment in resource-constrained scenarios. This paper introduces the 1-bit/1.58-bit quan...

SepSpace: payload-free open-set network traffic classification via supervised contrastive representation learning and prototype-radius rejection

Abstract Network traffic classification (NTC) increasingly needs to go beyond predefined categories and identify traffic from previously unseen classes, namely the open-set recognition problem in NTC. This problem remains challenging because encrypted traffic limits the practical...

Frequency response estimation and equalization for Rydberg atom electro-optic conversion systems

Rydberg atomic receivers (RARs) have emerged as a promising candidate for next-generation wireless communication systems due to their broadband tunability, SI traceability, compact configuration, and omnidirectional reception. Currently, the primary challenge hindering the furthe...