arXiv subjects

Wei Gong

Publications and source records attributed to Wei Gong.

At least 19 recordsLinked to original sources

arXiv2026

Exploring the Initial Performance of NB-IoT NTN over GEO: Measurement and Analysis

With the standardization of Non-Terrestrial Networks (NTN) to provide direct satellite connectivity to massive, low-power Internet of Things (IoT) devices, 3GPP IoT-NTN bridges the worlds of cellular and satellite communications. While holding great potential for global connectivity with IoT devices, there exist several concerns about the system performance of IoT-NTN over Geostationary Earth Orbit (GEO), which covers multiple dimensions such as end-to-end delay and energy consumption considering the ultra-long transmission distance from ground IoT terminals to GEO satellite. To answer these concerns, we have conducted the first comprehensive and in depth measurement for NB-IoT NTN over GEO. Based on real NB-IoT NTN testbeds including both Skylo and Tiantong, measurements covering more than six months confirm that the available implementation of NB-IoT NTN remains in the initial stage. Amplified by ultra-long Round-Trip Time (RTT) between ground IoT terminals and GEO satellite, there exists plenty of time and energy consumption during the access process. Interestingly, it also reveals that as an energy-saving mechanism, Power Saving Mode (PSM) fundamentally reshapes NB-IoT NTN traffic into a bursty and access-driven communication pattern and thus has a considerable influence on the end-to-end delay and energy consumption. Finally, we propose corresponding optimization schemes to reduce the delay and energy, which lays a good foundation for the implementation of NB-IoT NTN in the near future.

cs.NI↗

arXiv2026

Chorusing Synchronization Signals for Ambient 5G Backscatter

5G backscatter communication presents an emerging energy-efficient IoT connectivity solution with enhanced availability and data rate advantages over traditional wireless networks. For 5G backscatter, synchronization is crucial as it ensures high-quality transmission. Popular synchronization methods employ autocorrelation and cross-correlation for accurate timing, yet they are constrained by resources. Traditional cross-correlation-based methods for resource utilization optimization also fail in 5G backscatter due to the presence of multiple templates for 5G. A synchronization strategy that supports high accuracy and low power would be highly attractive for wireless backscatter communication. We propose Symmetric Differential (SD)-based Sync, an accurate and resource-efficient synchronization method for 5G backscatter. We have observed that the envelope of the 5G Primary Synchronization Signal (PSS) exhibits a unique mirror symmetry, which enables us to employ differential techniques for low-power PSS detection. We extensively evaluated our design using a testbed of backscatter hardware, SDR gNodeB, and User Equipment (UE). Results show that our SD consumes 3,175 D flip-flops, which is 87x lower than NR fine timing (NFT), 181x lower than symmetry-based semi-template sync (SST), and 30x lower than symmetric autocorrelation (SA)-based sync.

cs.NI↗

arXiv2026

An unfitted finite element method for PDE-constrained shape optimization via shape gradient flow

In this paper, we propose an unfitted finite element method to solve PDE-constrained shape optimization problems via shape gradient flow. The shape gradient flow system consists of the state equation, the adjoint equation, the velocity equation, as well as the flow map that generates the evolution of the boundary driven by the velocity field, which can be viewed as a limit system of the classical shape gradient descent algorithm. In \cite{GongLiRao} the authors proposed an evolving finite element method to solve the shape gradient flow system. Instead, in this paper, we propose an unfitted finite element method in which the evolution of the boundary is realized by cubic splines and the equations are solved by cut finite element methods with ghost penalization. Under reasonable assumptions, we are able to prove some optimal convergence rates that are further validated by numerical experiments.

math.NA↗

arXiv2026

Mie-lithography: self-guiding nonlinear laser printing for deep ultraviolet to near-infrared nano dispersion devices

Nanoscale control of optical dispersion is essential for applications ranging from miniaturized spectrometers to color printing, all of which demand broadband spectral tunability. However, the Kramers-Kronig relations impose a fundamental trade-off between dispersion and loss, strictly limiting the design ability of single-material devices across the deep ultraviolet (DUV) to near-infrared (NIR) regimes. Consequently, the fabrication of miniaturized dispersion devices heavily relies on costly nanofabrication or heterogeneous integration. Here we overcome these limitations by shifting the light-matter interaction from solid structure into air-filled voids. We introduce a fabrication strategy termed "Mie-lithography", in which laser printed seed nanocavities excite Mie resonances in air and the resulting localized field enhancement drives the self-assembly of three-dimensionally tunable void-type optical resonators. Because the resonant modes are primarily confined within air voids, this architecture effectively circumvents material-imposed dispersion-loss constraints, allowing on-demand customization of the broadband spectral response. This approach enables single-step, high-throughput (>= 10^6 pixels/s) printing of dispersion units with a resolution of 63,500 DPI. As a proof of concept, we demonstrate a DUV-NIR nano spectrometer integrated in a single material covering an unprecedented range from 200 nm to 800 nm. Our approach can be extended into a platform for ultra-broadband nano devices fabrication and design, opening avenues for high-pixel-density displays and miniaturized spectrometers.

physics.optics↗

arXiv2026

Analysis of Robin-boundary control for the Boussinesq equations

In this paper, we study an optimal boundary control problem for the Boussinesq equations, which couple the time-dependent Navier-Stokes system with a heat equation, where the control enters through a Robin boundary condition on temperature. We begin by establishing the well-posedness of the optimization problem via a variational framework. We then derive both first- and second-order optimality conditions, including explicit characterizations of the adjoint state and the optimal control. Next, we perform a detailed numerical analysis of a fully discrete scheme: using finite elements in space and a semi-implicit scheme in time, combined with variational discretization for the control. We present rigorous a prior error estimates for the state, adjoint state, and control variables. Numerical experiments are provided to validate our theoretical results.

math.NA↗

arXiv2026

A Penalty Method for Non-Self-Adjoint Topology Optimization

We propose a novel penalty method framework for the non-self-adjoint topology optimization problems, taking compliant mechanism problems as an example, by incorporating a convex nonlocal perimeter approximation scheme. We rigorously analyze the existence of solutions to the optimization problem derived from the penalty method. Furthermore, we establish that the discrete problem \(\Gamma\)-converges to the continuous problem, ensuring consistency across scales. To solve the discrete problem, we develop a projected gradient method that guarantees strict monotonic descent of the objective function. We also extend the framework to the heat dissipation problem and propose a generalized material interpolation function (GMIF), which allows for a targeted control of the topological connectivity in the resulting optimal design. Numerical experiments on the compliant mechanism and heat dissipation problems validate the effectiveness of the proposed method. This framework provides a robust approach to addressing complex optimization challenges in computational mathematics with potential applications in engineering design.

math.OC↗

arXiv2026

Advanced Global Wildfire Activity Modeling with Hierarchical Graph ODE

Wildfires, as an integral component of the Earth system, are governed by a complex interplay of atmospheric, oceanic, and terrestrial processes spanning a vast range of spatiotemporal scales. Modeling their global activity on large timescales is therefore a critical yet challenging task. While deep learning has recently achieved significant breakthroughs in global weather forecasting, its potential for global wildfire behavior prediction remains underexplored. In this work, we reframe this problem and introduce the Hierarchical Graph ODE (HiGO), a novel framework designed to learn the multi-scale, continuous-time dynamics of wildfires. Specifically, we represent the Earth system as a multi-level graph hierarchy and propose an adaptive filtering message passing mechanism for both intra- and inter-level information flow, enabling more effective feature extraction and fusion. Furthermore, we incorporate GNN-parameterized Neural ODE modules at multiple levels to explicitly learn the continuous dynamics inherent to each scale. Through extensive experiments on the SeasFire Cube dataset, we demonstrate that HiGO significantly outperforms state-of-the-art baselines on long-range wildfire forecasting. Moreover, its continuous-time predictions exhibit strong observational consistency, highlighting its potential for real-world applications.

cs.LG↗

arXiv2025

Adaptive Regime-Switching Forecasts with Distribution-Free Uncertainty: Deep Switching State-Space Models Meet Conformal Prediction

Regime transitions routinely break stationarity in time series, making calibrated uncertainty as important as point accuracy. We study distribution-free uncertainty for regime-switching forecasting by coupling Deep Switching State Space Models with Adaptive Conformal Inference (ACI) and its aggregated variant (AgACI). We also introduce a unified conformal wrapper that sits atop strong sequence baselines including S4, MC-Dropout GRU, sparse Gaussian processes, and a change-point local model to produce online predictive bands with finite-sample marginal guarantees under nonstationarity and model misspecification. Across synthetic and real datasets, conformalized forecasters achieve near-nominal coverage with competitive accuracy and generally improved band efficiency.

cs.LG↗

arXiv2025

A Unified Phase-Field Fourier Neural Network Framework for Topology Optimization

We propose Alternating Phase-Field Fourier Neural Networks (APF-FNNs) as a unified and physics-based framework for topology optimization. The approach decouples the design problem by representing the state, adjoint, and topology fields with three separate Fourier neural networks, which are trained via a stable collaborative alternating scheme applicable to both self-adjoint and non-self-adjoint problems. To obtain well-resolved designs, the Ginzburg--Landau energy functional is embedded in the loss of the topology network as an intrinsic regularizer, naturally enforcing smooth and distinct interfaces between the two phases. Phase-field updates are driven by adjoint-based optimality conditions, and design sensitivities are evaluated efficiently using automatic differentiation, ensuring that the gradients correspond to exact total derivatives rather than naive partial derivatives. In contrast to classical phase-field methods, APF-FNNs exploit these physically consistent design gradients directly, avoiding pseudo-time gradient-flow solvers. By formulating physics-driven losses from variational principles or strong-form PDE residuals, the framework is broadly applicable to 2D and 3D benchmark problems, including compliance minimization, eigenvalue maximization, and Stokes/Navier--Stokes flow optimization. Across these examples, APF-FNNs consistently yield competitive performance and well-resolved topologies, establishing a versatile and scalable foundation for physics-driven computational design.

math.OC↗

arXiv2025

Unlocking Out-of-Distribution Generalization in Dynamics through Physics-Guided Augmentation

In dynamical system modeling, traditional numerical methods are limited by high computational costs, while modern data-driven approaches struggle with data scarcity and distribution shifts. To address these fundamental limitations, we first propose SPARK, a physics-guided quantitative augmentation plugin. Specifically, SPARK utilizes a reconstruction autoencoder to integrate physical parameters into a physics-rich discrete state dictionary. This state dictionary then acts as a structured dictionary of physical states, enabling the creation of new, physically-plausible training samples via principled interpolation in the latent space. Further, for downstream prediction, these augmented representations are seamlessly integrated with a Fourier-enhanced Graph ODE, a combination designed to robustly model the enriched data distribution while capturing long-term temporal dependencies. Extensive experiments on diverse benchmarks demonstrate that SPARK significantly outperforms state-of-the-art baselines, particularly in challenging out-of-distribution scenarios and data-scarce regimes, proving the efficacy of our physics-guided augmentation paradigm.

cs.LG↗

arXiv2025

Moving or Predicting? RoleAware-MAPP: A Role-Aware Transformer Framework for Movable Antenna Position Prediction to Secure Wireless Communications

Movable antenna (MA) technology provides a promising avenue for actively shaping wireless channels through dynamic antenna positioning, thereby enabling electromagnetic radiation reconstruction to enhance physical layer security (PLS). However, its practical deployment is hindered by two major challenges: the high computational complexity of real time optimization and a critical temporal mismatch between slow mechanical movement and rapid channel variations. Although data driven methods have been introduced to alleviate online optimization burdens, they are still constrained by suboptimal training labels derived from conventional solvers or high sample complexity in reinforcement learning. More importantly, existing learning based approaches often overlook communication-specific domain knowledge, particularly the asymmetric roles and adversarial interactions between legitimate users and eavesdroppers, which are fundamental to PLS. To address these issues, this paper reformulates the MA positioning problem as a predictive task and introduces RoleAware-MAPP, a novel Transformer based framework that incorporates domain knowledge through three key components: role-aware embeddings that model user specific intentions, physics-informed semantic features that encapsulate channel propagation characteristics, and a composite loss function that strategically prioritizes secrecy performance over mere geometric accuracy. Extensive simulations under 3GPP-compliant scenarios show that RoleAware-MAPP achieves an average secrecy rate of 0.3569 bps/Hz and a strictly positive secrecy capacity of 81.52%, outperforming the strongest baseline by 48.4% and 5.39 percentage points, respectively, while maintaining robust performance across diverse user velocities and noise conditions.

cs.IT↗

arXiv2025

Breaking the Discretization Barrier of Continuous Physics Simulation Learning

The modeling of complicated time-evolving physical dynamics from partial observations is a long-standing challenge. Particularly, observations can be sparsely distributed in a seemingly random or unstructured manner, making it difficult to capture highly nonlinear features in a variety of scientific and engineering problems. However, existing data-driven approaches are often constrained by fixed spatial and temporal discretization. While some researchers attempt to achieve spatio-temporal continuity by designing novel strategies, they either overly rely on traditional numerical methods or fail to truly overcome the limitations imposed by discretization. To address these, we propose CoPS, a purely data-driven methods, to effectively model continuous physics simulation from partial observations. Specifically, we employ multiplicative filter network to fuse and encode spatial information with the corresponding observations. Then we customize geometric grids and use message-passing mechanism to map features from original spatial domain to the customized grids. Subsequently, CoPS models continuous-time dynamics by designing multi-scale graph ODEs, while introducing a Markov-based neural auto-correction module to assist and constrain the continuous extrapolations. Comprehensive experiments demonstrate that CoPS advances the state-of-the-art methods in space-time continuous modeling across various scenarios.

cs.CV↗

arXiv2025

Bioluminescence tomography via a shape optimization method based on a complex-valued model

In this study, we investigate the inverse source problem arising in bioluminescence tomography, the objective of which is to reconstruct both the support and the intensity of an internal light source from boundary measurements governed by an elliptic model. A shape optimization framework is developed in which the source intensity and its support are decoupled through first-order optimality conditions. To enhance the stability of the reconstruction, we incorporate a parameter-dependent coupled complex boundary method together with perimeter and volume regularizations. Source support is represented by a level set function, allowing the algorithm to naturally accommodate topological changes and recover multiple, closely spaced, or nested source regions. Theoretical justifications for the proposed formulation and regularization strategy are established, and extensive numerical experiments are performed to assess the reconstruction accuracy for both noise-free and noisy data. The results demonstrate that our method achieves robust and accurate recovery of source geometry and intensity, and exhibits clear advantages over existing approaches.

math.NA↗

arXiv2025

Towards Understanding the Optimization Mechanisms in Deep Learning

In this paper, we adopt a probability distribution estimation perspective to explore the optimization mechanisms of supervised classification using deep neural networks. We demonstrate that, when employing the Fenchel-Young loss, despite the non-convex nature of the fitting error with respect to the model's parameters, global optimal solutions can be approximated by simultaneously minimizing both the gradient norm and the structural error. The former can be controlled through gradient descent algorithms. For the latter, we prove that it can be managed by increasing the number of parameters and ensuring parameter independence, thereby providing theoretical insights into mechanisms such as over-parameterization and random initialization. Ultimately, the paper validates the key conclusions of the proposed method through empirical results, illustrating its practical effectiveness.

cs.LG↗

arXiv2025

Injecting Imbalance Sensitivity for Multi-Task Learning

Multi-task learning (MTL) has emerged as a promising approach for deploying deep learning models in real-life applications. Recent studies have proposed optimization-based learning paradigms to establish task-shared representations in MTL. However, our paper empirically argues that these studies, specifically gradient-based ones, primarily emphasize the conflict issue while neglecting the potentially more significant impact of imbalance/dominance in MTL. In line with this perspective, we enhance the existing baseline method by injecting imbalance-sensitivity through the imposition of constraints on the projected norms. To demonstrate the effectiveness of our proposed IMbalance-sensitive Gradient (IMGrad) descent method, we evaluate it on multiple mainstream MTL benchmarks, encompassing supervised learning tasks as well as reinforcement learning. The experimental results consistently demonstrate competitive performance.

cs.LG↗

arXiv2024

Identification of Epileptic Spasms (ESES) Phases Using EEG Signals: A Vision Transformer Approach

This work introduces a new approach to the Epileptic Spasms (ESES) detection based on the EEG signals using Vision Transformers (ViT). Classic ESES detection approaches have usually been performed with manual processing or conventional algorithms, suffering from poor sample sizes, single-channel-based analyses, and low generalization abilities. In contrast, the proposed ViT model overcomes these limitations by using the attention mechanism to focus on the important features in multi-channel EEG data, which is contributing to both better accuracy and efficiency. The model processes frequency-domain representations of EEG signals, such as spectrograms, as image data to capture long-range dependencies and complex patterns in the signal. The model demonstrates high performance with an accuracy of 97% without requiring intensive data preprocessing, thus rendering it suitable for real-time clinical applications on a large scale. The method represents a significant development in the advancement of neurological disorders such as ESES in detection and analysis.

q-bio.NC↗

arXiv2024

Revisiting Long-Tailed Learning: Insights from an Architectural Perspective

Long-Tailed (LT) recognition has been widely studied to tackle the challenge of imbalanced data distributions in real-world applications. However, the design of neural architectures for LT settings has received limited attention, despite evidence showing that architecture choices can substantially affect performance. This paper aims to bridge the gap between LT challenges and neural network design by providing an in-depth analysis of how various architectures influence LT performance. Specifically, we systematically examine the effects of key network components on LT handling, such as topology, convolutions, and activation functions. Based on these observations, we propose two convolutional operations optimized for improved performance. Recognizing that operation interactions are also crucial to network effectiveness, we apply Neural Architecture Search (NAS) to facilitate efficient exploration. We propose LT-DARTS, a NAS method with a novel search space and search strategy specifically designed for LT data. Experimental results demonstrate that our approach consistently outperforms existing architectures across multiple LT datasets, achieving parameter-efficient, state-of-the-art results when integrated with current LT methods.

cs.CV↗

arXiv2024

Offline Inverse Constrained Reinforcement Learning for Safe-Critical Decision Making in Healthcare

Reinforcement Learning (RL) applied in healthcare can lead to unsafe medical decisions and treatment, such as excessive dosages or abrupt changes, often due to agents overlooking common-sense constraints. Consequently, Constrained Reinforcement Learning (CRL) is a natural choice for safe decisions. However, specifying the exact cost function is inherently difficult in healthcare. Recent Inverse Constrained Reinforcement Learning (ICRL) is a promising approach that infers constraints from expert demonstrations. ICRL algorithms model Markovian decisions in an interactive environment. These settings do not align with the practical requirement of a decision-making system in healthcare, where decisions rely on historical treatment recorded in an offline dataset. To tackle these issues, we propose the Constraint Transformer (CT). Specifically, 1) we utilize a causal attention mechanism to incorporate historical decisions and observations into the constraint modeling, while employing a Non-Markovian layer for weighted constraints to capture critical states. 2) A generative world model is used to perform exploratory data augmentation, enabling offline RL methods to simulate unsafe decision sequences. In multiple medical scenarios, empirical results demonstrate that CT can capture unsafe states and achieve strategies that approximate lower mortality rates, reducing the occurrence probability of unsafe behaviors.

cs.LG↗