Shi Jin

Weijie Yuan, Yuanhao Cui, Jiacheng Wang et al.

In this article, we introduce a novel low-altitude wireless network (LAWN), which is a reconfigurable, three-dimensional (3D) layered architecture. In particular, the LAWN integrates connectivity, sensing, control, and computing across aerial and terrestrial nodes that enable seamless operation in complex, dynamic, and mission-critical environments. Different from the conventional aerial communication systems, LAWN's distinctive feature is its tight integration of functional planes in which multiple functionalities continually reshape themselves to operate safely and efficiently in the low-altitude sky. With the LAWN, we discuss several enabling technologies, such as integrated sensing and communication (ISAC), semantic communication, and fully-actuated control systems. Finally, we identify potential applications and key cross-layer challenges. This article offers a comprehensive roadmap for future research and development in the low-altitude airspace.

Jiajia Guo, Chao-Kai Wen, Shi Jin et al.

Many performance gains achieved by massive multiple-input and multiple-output depend on the accuracy of the downlink channel state information (CSI) at the transmitter (base station), which is usually obtained by estimating at the receiver (user terminal) and feeding back to the transmitter. The overhead of CSI feedback occupies substantial uplink bandwidth resources, especially when the number of the transmit antennas is large. Deep learning (DL)-based CSI feedback refers to CSI compression and reconstruction by a DL-based autoencoder and can greatly reduce feedback overhead. In this paper, a comprehensive overview of state-of-the-art research on this topic is provided, beginning with basic DL concepts widely used in CSI feedback and then categorizing and describing some existing DL-based feedback works. The focus is on novel neural network architectures and utilization of communication expert knowledge to improve CSI feedback accuracy. Works on bit-level CSI feedback and joint design of CSI feedback with other communication modules are also introduced, and some practical issues, including training dataset collection, online training, complexity, generalization, and standardization effect, are discussed. At the end of the paper, some challenges and potential research directions associated with DL-based CSI feedback in future wireless communication systems are identified.

Ziling Liang, Xinping Yi, Qingsong Wen et al.

Whilst the vulnerability of graph neural networks (GNNs) to adversarial attacks poses a critical threat to graph representation learning, the understanding of the robust generalization behavior remains a fundamental challenge in the adversarial setting. Recently, PAC-Bayesian margin-based generalization analysis substantially advances this line of research by providing a flexible and data-dependent analytical framework. However, existing robust analyses often rely on isotropic Gaussian posteriors and control weight perturbations in the full parameter space, which limits the ability to capture heterogeneous parameter sensitivity yet hinges on hidden-width-dependent complexity terms, resulting in not-tight-enough generalization bounds. In this paper, we extend a recently proposed sensitivity-aware PAC-Bayesian framework from deep neural networks to message passing GNNs (MPGNNs) and derive a tighter robust generalization bound in the adversarial setting. Specifically, we first quantify how sensitive the perturbations across different parameter blocks are to the network outputs by deriving the output Jacobians with respect to the weight parameters. Exploiting the fact that these Jacobian matrices have rank at most $K$ in $K$-class graph classification, we then construct Jacobian-aligned sensitivity matrices and use anisotropic Gaussian posteriors with optimized covariances to upper bound the KL divergence in a tight way. Notably, by refining the spectral-norm dependence on the learned weights and reducing the leading dimension factor from hidden-width-dependent terms to the number of classes $K$, our analysis yields much tighter robust generalization guarantees for MPGNNs, thereby guiding their designs to enhance adversarial robustness.

Siqi Chen, Shi Jin, Lei Zhang

We study quantum algorithms for nonlinear and stochastic homogenization via a Young-measure based linear programming (LP) formulation, which lifts the nonlinear problem to a linear one in higher dimensions by treating the microscale, the gradient, and possible random variables as independent variables, thereby capturing effective macroscopic quantities without directly resolving fine-scale oscillations. The resulting LP is large but structured, and its high-dimensional nature creates regimes in which quantum LP solvers outperform direct classical solvers: in the deterministic setting, polynomial quantum speedup arises when moderate homogenized accuracy suffices; in the stochastic setting, encoding all random realizations simultaneously in a single LP yields a quantum square-root reduction in stochastic sampling cost that grows with the number of random variables. Regularity or sparsity of the Young measure may further extend these advantages to fine-scale accuracy. Numerical experiments on one- and two-dimensional benchmarks confirm the correctness of the Young-measure LP formulation.

Jianwei Zhao, Feifei Gao, Qihui Wu et al.

Unmanned aerial vehicle (UAV)-satellite communication has drawn dramatic attention for its potential to build the integrated space-air-ground network and the seamless wide-area coverage. The key challenge to UAV-satellite communication is its unstable beam pointing due to the UAV navigation, which is a typical SatCom on-the-move scenario. In this paper, we propose a blind beam tracking approach for Ka-band UAVsatellite communication system, where UAV is equipped with a large-scale antenna array. The effects of UAV navigation are firstly released through the mechanical adjustment, which could approximately point the beam towards the target satellite through beam stabilization and dynamic isolation. Specially, the attitude information can be realtimely derived from data fusion of lowcost sensors. Then, the precision of the beam pointing is blindly refined through electrically adjusting the weight of the massive antennas, where an array structure based simultaneous perturbation algorithm is designed. Simulation results are provided to demonstrate the superiority of the proposed method over the existing ones.

Yuelin Wang, Kai Yi, Xinliang Liu et al.

Neural message passing is a basic feature extraction unit for graph-structured data considering neighboring node features in network propagation from one layer to the next. We model such process by an interacting particle system with attractive and repulsive forces and the Allen-Cahn force arising in the modeling of phase transition. The dynamics of the system is a reaction-diffusion process which can separate particles without blowing up. This induces an Allen-Cahn message passing (ACMP) for graph neural networks where the numerical iteration for the particle system solution constitutes the message passing propagation. ACMP which has a simple implementation with a neural ODE solver can propel the network depth up to one hundred of layers with theoretically proven strictly positive lower bound of the Dirichlet energy. It thus provides a deep model of GNNs circumventing the common GNN problem of oversmoothing. GNNs with ACMP achieve state of the art performance for real-world node classification tasks on both homophilic and heterophilic datasets. Codes are available at https://github.com/ykiiiiii/ACMP.

Jiajia Guo, Chao-Kai Wen, Shi Jin et al.

The 3rd Generation Partnership Project started the study of Release 18 in 2021. Artificial intelligence (AI)-native air interface is one of the key features of Release 18, where AI for channel state information (CSI) feedback enhancement is selected as the representative use case. This article provides an overview of AI for CSI feedback enhancement in 5G-Advanced. Several representative non-AI and AI-enabled CSI feedback frameworks are first introduced and compared. Then, the standardization of AI for CSI feedback enhancement in 5G-advanced is presented in detail. First, the scope of the AI for CSI feedback enhancement in 5G-Advanced is presented and discussed. Then, the main challenges and open problems in the standardization of AI for CSI feedback enhancement, especially focusing on performance evaluation and the design of new protocols for AI-enabled CSI feedback, are identified and discussed. This article provides a guideline for the standardization study of AI-based CSI feedback enhancement.

Zhongyi Huang, Shi Jin, Peter Markowich et al.

We present a time-splitting spectral scheme for the Maxwell-Dirac system and similar time-splitting methods for the corresponding asymptotic problems in the semi-classical and the non-relativistic regimes. The scheme for the Maxwell-Dirac system conserves the Lorentz gauge condition, is unconditionally stable and highly efficient as our numerical examples show. In particular we focus in our examples on the creation of positronic modes in the semi-classical regime and on the electron-positron interaction in the non-relativistic regime. Furthermore, in the non-relativistic regime, our numerical method exhibits uniform convergence in the small parameter $\dt$, which is the ratio of the characteristic speed and the speed of light.

Francis Filbet, Shi Jin

In this paper, we study a time discrete scheme for the initial value problem of the ES-BGK kinetic equation. Numerically solving these equations are challenging due to the nonlinear stiff collision (source) terms induced by small mean free or relaxation time. We study an implicit-explicit (IMEX) time discretization in which the convection is explicit while the relaxation term is implicit to overcome the stiffness. We first show how the implicit relaxation can be solved explicitly, and then prove asymptotically that this time discretization drives the density distribution toward the local Maxwellian when the mean free time goes to zero while the numerical time step is held fixed. This naturally imposes an asymptotic-preserving scheme in the Euler limit. The scheme so designed does not need any nonlinear iterative solver for the implicit relaxation term. Moreover, it can capture the macroscopic fluid dynamic (Euler) limit even if the small scale determined by the Knudsen number is not numerically resolved. We also show that it is consistent to the compressible Navier-Stokes equations if the viscosity and heat conductivity are numerically resolved. Several numerical examples, in both one and two space dimensions, are used to demonstrate the desired behavior of this scheme.

Liu Liu, Shi Jin

In this paper, we provide a general framework to study general class of linear and nonlinear kinetic equations with random uncertainties from the initial data or collision kernels, and their stochastic Galerkin approximations, in both incompressible Navier-Stokes and Euler (acoustic) regimes. First, we show that the general framework put forth in [C. Mouhot and L. Neumann, Nonlinearity, 19, 969-998, 2006, M. Briant, J. Diff. Eqn., 259, 6072-6141, 2005] based on hypocoercivity for the deterministic kinetic equations can be easily adopted for sensitivity analysis for random kinetic equations, which gives rise to an exponential convergence of the random solution toward the (deterministic) global equilibrium, under suitable conditions on the collision kernel. Then we use such theory to study the stochastic Galerkin (SG) methods for the equations, establish hypocoercivity of the SG system and regularity of its solution, and spectral accuracy and exponential decay of the numerical error of the method in a weighted Sobolev norm.

Shi Jin, Yuhua Zhu

We study the Vlasov-Poisson-Fokker-Planck system with uncertainty and multiple scales. Here the uncertainty, modeled by random variables, enters the solution through initial data, while the multiple scales lead the system to its high-field or parabolic regimes. With the help of proper Lyapunov-type inequalities, under some mild conditions on the initial data, the regularity of the solution in the random space, as well as exponential decay of the solution to the global Maxwellian, are established under Sobolev norms, which are ${\it uniform}$ in terms of the scaling parameters. These are the first hypocoercivity results for a nonlinear kinetic system with random input, which are important for the understanding of the sensitivity of the system under random perturbations, and for the establishment of spectral convergence of popular numerical methods for uncertainty quantification based on (spectrally accurate) polynomial chaos expansions.

Jie Zhang, Jun Li, Yijin Zhang et al.

Intelligent reflecting surface (IRS) is envisioned to be widely applied in future wireless networks. In this paper, we investigate a multi-user communication system assisted by cooperative IRS devices with the capability of energy harvesting. Aiming to maximize the long-term average achievable system rate, an optimization problem is formulated by jointly designing the transmit beamforming at the base station (BS) and discrete phase shift beamforming at the IRSs, with the constraints on transmit power, user data rate requirement and IRS energy buffer size. Considering time-varying channels and stochastic arrivals of energy harvested by the IRSs, we first formulate the problem as a Markov decision process (MDP) and then develop a novel multi-agent Q-mix (MAQ) framework with two layers to decouple the optimization parameters. The higher layer is for optimizing phase shift resolutions, and the lower one is for phase shift beamforming and power allocation. Since the phase shift optimization is an integer programming problem with a large-scale action space, we improve MAQ by incorporating the Wolpertinger method, namely, MAQ-WP algorithm to achieve a sub-optimality with reduced dimensions of action space. In addition, as MAQ-WP is still of high complexity to achieve good performance, we propose a policy gradient-based MAQ algorithm, namely, MAQ-PG, by mapping the discrete phase shift actions into a continuous space at the cost of a slight performance loss. Simulation results demonstrate that the proposed MAQ-WP and MAQ-PG algorithms can converge faster and achieve data rate improvements of 10.7% and 8.8% over the conventional multi-agent DDPG, respectively.

Zhongyi Huang, Shi Jin, Peter Markowich et al.

We present a new numerical method for accurate computations of solutions to (linear) one dimensional Schrödinger equations with periodic potentials. This is a prominent model in solid state physics where we also allow for perturbations by non-periodic potentials describing external electric fields. Our approach is based on the classical Bloch decomposition method which allows to diagonalize the periodic part of the Hamiltonian operator. Hence, the dominant effects from dispersion and periodic lattice potential are computed together, while the non-periodic potential acts only as a perturbation. Because the split-step communicator error between the periodic and non-periodic parts is relatively small, the step size can be chosen substantially larger than for the traditional splitting of the dispersion and potential operators. Indeed it is shown by the given examples, that our method is unconditionally stable and more efficient than the traditional split-step pseudo spectral schemes. To this end a particular focus is on the semiclassical regime, where the new algorithm naturally incorporates the adiabatic splitting of slow and fast degrees of freedom.

Hao Wu, Zhongyi Huang, Shi Jin et al.

The Dirac equation is an important model in relativistic quantum mechanics. In the semi-classical regime $ε\ll1$, even a spatially spectrally accurate time splitting method \cite{HuJi:05} requires the mesh size to be $O(ε)$, which makes the direct simulation extremely expensive. In this paper, we present the Gaussian beam method for the Dirac equation. With the help of an eigenvalue decomposition, the Gaussian beams can be independently evolved along each eigenspace and summed to construct an approximate solution of the Dirac equation. Moreover, the proposed Eulerian Gaussian beam keeps the advantages of constructing the Hessian matrices by simply using level set functions' derivatives. Finally, several numerical examples show the efficiency and accuracy of the method.

Irene M. Gamba, Shi Jin, Liu Liu

In this paper, we first extend the micro-macro decomposition method for multiscale kinetic equations from the BGK model to general collisional kinetic equations, including the Boltzmann and the Fokker-Planck Landau equations. The main idea is to use a relation between the (numerically stiff) linearized collision operator with the nonlinear quadratic ones, the later's stiffness can be overcome using the BGK penalization method of Filbet and Jin for the Boltzmann, or the linear Fokker-Planck penalization method of Jin and Yan for the Fokker-Planck Landau equations. Such a scheme allows the computation of multiscale collisional kinetic equations efficiently in all regimes, including the fluid regime in which the fluid dynamic behavior can be correctly computed even without resolving the small Knudsen number. A distinguished feature of these schemes is that although they contain implicit terms, they can be implemented explicitly. These schemes preserve the moments (mass, momentum and energy) exactly thanks to the use of the macroscopic system which is naturally in a conservative form. We further utilize this conservation property for more general kinetic systems, using the Vlasov-Ampére and Vlasov-Ampére-Boltzmann systems as examples. The main idea is to evolve both the kinetic equation for the probability density distribution and the moment system, the later naturally induces a scheme that conserves exactly the moments numerically if they are physically conserved.

Shi Jin, Hanqing Lu, Lorenzo Pareschi

For linear transport and radiative heat transfer equations with random inputs, we develop new generalized polynomial chaos based Asymptotic-Preserving stochastic Galerkin schemes that allow efficient computation for the problems that contain both uncertainties and multiple scales. Compared with previous methods for these problems, our new method use the implicit-explicit (IMEX) time discretization to gain higher order accuracy, and by using a modified diffusion operator based penalty method, a more relaxed stability condition--a hyperbolic, rather than parabolic, CFL stability condition, is achieved in the case of small mean free path in the diffusive regime. The stochastic Asymptotic-Preserving property of these methods will be shown asymptotically, and demonstrated numerically, along with computational cost comparison with previous methods.

Kerstin Küpper, Martin Frank, Shi Jin

We propose a two-dimensional asymptotic preserving scheme for linear transport equations with diffusive scalings. It is an extension of the time splitting developed by Jin, Pareschi and Toscani [SINUM,2000], but uses spatial discretizations on staggered grids, which preserves the discrete diffusion limit with a more compact stencil. The first novelty of this paper is that we propose a staggering in two dimensions that requires fewer unknowns than one could have naively expected. The second contribution of this paper is that we rigorously analyze the scheme of Jin, Pareschi, and Toscani [SINUM,2000] We show that the scheme is AP and obtain an explicit CFL condition, which couples a hyperbolic and a parabolic condition. This type of condition is common for asymptotic preserving schemes and guarantees uniform stability with respect to the mean free path. In addition, we obtain an upper bound on the relaxation parameter, which is the crucial parameter of the used time discretization. Several numerical examples are provided to verify the accuracy and asymptotic property of the scheme.

Francis Filbet, Jingwei Hu, Shi Jin

Numerically solving the Boltzmann kinetic equations with the small Knudsen number is challenging due to the stiff nonlinear collision term. A class of asymptotic preserving schemes was introduced in [6] to handle this kind of problems. The idea is to penalize the stiff collision term by a BGK type operator. This method, however, encounters its own difficulty when applied to the quantum Boltzmann equation. To define the quantum Maxwellian (Bose-Einstein or Fermi- Dirac distribution) at each time step and every mesh point, one has to invert a nonlinear equation that connects the macroscopic quantity fugacity with density and internal energy. Setting a good initial guess for the iterative method is troublesome in most cases because of the complexity of the quantum functions (Bose-Einstein or Fermi-Dirac function). In this paper, we propose to penalize the quantum collision term by a 'classical' BGK operator instead of the quantum one. This is based on the observation that the classical Maxwellian, with the temperature replaced by the internal energy, has the same first five moments as the quantum Maxwellian. The scheme so designed avoids the aforementioned difficulty, and one can show that the density distribution is still driven toward the quantum equilibrium. Numerical results are present to illustrate the efficiency of the new scheme in both the hydrodynamic and kinetic regimes. We also develop a spectral method for the quantum collision operator.

Ziyan Yin, Zhe Wang, Jun Li et al.

The explosive growth of dynamic and heterogeneous data traffic brings great challenges for 5G and beyond mobile networks. To enhance the network capacity and reliability, we propose a learning-based dynamic time-frequency division duplexing (D-TFDD) scheme that adaptively allocates the uplink and downlink time-frequency resources of base stations (BSs) to meet the asymmetric and heterogeneous traffic demands while alleviating the inter-cell interference. We formulate the problem as a decentralized partially observable Markov decision process (Dec-POMDP) that maximizes the long-term expected sum rate under the users' packet dropping ratio constraints. In order to jointly optimize the global resources in a decentralized manner, we propose a federated reinforcement learning (RL) algorithm named federated Wolpertinger deep deterministic policy gradient (FWDDPG) algorithm. The BSs decide their local time-frequency configurations through RL algorithms and achieve global training via exchanging local RL models with their neighbors under a decentralized federated learning framework. Specifically, to deal with the large-scale discrete action space of each BS, we adopt a DDPG-based algorithm to generate actions in a continuous space, and then utilize Wolpertinger policy to reduce the mapping errors from continuous action space back to discrete action space. Simulation results demonstrate the superiority of our proposed algorithm to benchmark algorithms with respect to system sum rate.

Nicolas Crouseilles, Shi Jin, Mohammed Lemou

We introduce a new numerical strategy to solve a class of oscillatory transport PDE models which is able to captureaccurately the solutions without numerically resolving the high frequency oscillations {\em in both space and time}.Such PDE models arise in semiclassical modeling of quantum dynamics with band-crossings, and otherhighly oscillatory waves. Our first main idea is to use the nonlinear geometric optics ansatz, which builds theoscillatory phase into an independent variable. We then choose suitable initial data, based on the Chapman-Enskog expansion, for the new model. For a scalar model, we prove that so constructed model will have certain smoothness, and consequently, for a first order approximation scheme we prove uniform error estimates independent of the (possibly small) wave length. The method is extended to systems arising from a semiclassical model for surface hopping, a non-adiabatic quantum dynamic phenomenon. Numerous numerical examples demonstrate that the method has the desired properties.

Keke Wu, Xiong-bin Yan, Shi Jin et al.

In this paper, we introduce two types of novel Asymptotic-Preserving Convolutional Deep Operator Networks (APCONs) designed to address the multiscale time-dependent linear transport problem. We observe that the vanilla physics-informed DeepONets with modified MLP may exhibit instability in maintaining the desired limiting macroscopic behavior. Therefore, this necessitates the utilization of an asymptotic-preserving loss function. Drawing inspiration from the heat kernel in the diffusion equation, we propose a new architecture called Convolutional Deep Operator Networks, which employ multiple local convolution operations instead of a global heat kernel, along with pooling and activation operations in each filter layer. Our APCON methods possess a parameter count that is independent of the grid size and are capable of capturing the diffusive behavior of the linear transport problem. Finally, we validate the effectiveness of our methods through several numerical examples.

Shi Jin, Zheng Ma

We develop a general polynomial chaos (gPC) based stochastic Galerkin (SG) for hyperbolic equations with random and singular coefficients. Due to the singu- lar nature of the solution, the standard gPC-SG methods may suffer from a poor or even non convergence. Taking advantage of the fact that the discrete solution, by the central type finite difference or finite volume approximations in space and time for example, is smoother, we first discretize the equation by a smooth finite difference or finite volume scheme, and then use the gPC-SG approximation to the discrete system. The jump condition at the interface is treated using the immersed upwind methods introduced in [8, 12]. This yields a method that converges with the spectral accuracy for finite mesh size and time step. We use a linear hyperbolic equation with discontinuous and random coefficient, and the Liouville equation with discontinuous and random potential, to illustrate our idea, with both one and second order spatial discretizations. Spectral convergence is established for the first equation, and numerical examples for both equations show the desired accu- racy of the method.

Xiangyi Li, Jiajia Guo, Chao-Kai Wen et al.

Deep learning has revolutionized the design of the channel state information (CSI) feedback module in wireless communications. However, designing the optimal neural network (NN) architecture for CSI feedback can be a laborious and time-consuming process. Manual design can be prohibitively expensive for customizing NNs to different scenarios. This paper proposes using neural architecture search (NAS) to automate the generation of scenario-customized CSI feedback NN architectures, thereby maximizing the potential of deep learning in exclusive environments. By employing automated machine learning and gradient-descent-based NAS, an efficient and cost-effective architecture design process is achieved. The proposed approach leverages implicit scene knowledge, integrating it into the scenario customization process in a data-driven manner, and fully exploits the potential of deep learning for each specific scenario. To address the issue of excessive search, early stopping and elastic selection mechanisms are employed, enhancing the efficiency of the proposed scheme. The experimental results demonstrate that the automatically generated architecture, known as Auto-CsiNet, outperforms manually-designed models in both reconstruction performance (achieving approximately a 14% improvement) and complexity (reducing it by approximately 50%). Furthermore, the paper analyzes the impact of the scenario on the NN architecture and its capacity.

Nicolas Crouseilles, Shi Jin, Mohammed Lemou et al.

We develop generalized polynomial chaos (gPC) based stochastic Galerkin (SG) methods for a class of highly oscillatory transport equations that arise in semiclassical modeling of non-adiabatic quantum dynamics. These models contain uncertainties, particularly in coefficients that correspond to the potentials of the molecular system. We first focus on a highly oscillatory scalar model with random uncertainty. Our method is built upon the nonlinear geometrical optics (NGO) based method, developed in \cite{NGO} for numerical approximations of deterministic equations, which can obtain accurate pointwise solution even without numerically resolving spatially and temporally the oscillations. With the random uncertainty, we show that such a method has oscillatory higher order derivatives in the random space, thus requires a frequency dependent discretization in the random space. We modify this method by introducing a new "time" variable based on the phase, which is shown to be non-oscillatory in the random space, based on which we develop a gPC-SG method that can capture oscillations with the frequency-independent time step, mesh size as well as the degree of polynomial chaos. A similar approach is then extended to a semiclassical surface hopping model system with a similar numerical conclusion. Various numerical examples attest that these methods indeed capture accurately the solution statistics {\em pointwisely} even though none of the numerical parameters resolve the high frequencies of the solution.

Xinjie Li, Xingyu Zhou, Jing Zhang et al.

Superimposed pilot (SIP) transmission improves spectral efficiency by eliminating the dedicated pilot overhead required in orthogonal pilot (OP)-based schemes. However, SIP suffers from severe pilot-data coupling, which leads to a critical performance-complexity bottleneck at the receiver. To address this issue, this paper proposes a low-overhead transmission framework that revitalizes data-dependent superimposed training (DDST) with enhanced interference mitigation strategies. First, for quasi-static block-fading channels, an enhanced DDST receiver is developed to achieve non-iterative pilot-data decoupling by exploiting data-dependent algebraic structures. Second, to overcome the sensitivity of conventional DDST to channel variations and symbol misidentification in fast time-varying environments, a mix transmission scheme is developed. By strategically applying DDST to a subset of resource elements, the proposed scheme combines the interference-free transmission property of OP with the zero-pilot-overhead advantage of SIP, thereby improving demapping reliability and interference suppression. Furthermore, under the proposed mix scheme, a Vision Transformer-based neural receiver is designed to capture the orthogonal structure between pilots and perturbation-bearing data, as well as the underlying channel correlations, thereby relaxing the stringent quasi-static assumption required for interference disentanglement. Simulation results demonstrate that the proposed framework achieves significant performance gains in the low-to-medium SNR regime under time-varying channels while providing superior computational efficiency compared with state-of-the-art SIP receivers.

Qitong Hu, Xiaoyang He, Shi Jin et al.

In this paper, we present a quantum implicit-explicit (IMEX) scheme for multiscale ordinary and partial differential equations whose discretization parameters are independent of the scaling parameter $\varepsilon$. A key ingredient of our approach is a continuous-time formulation of classical IMEX schemes, which decouples the evolution time of the quantum algorithm from the physical time of the differential equation and is therefore particularly useful in multiscale settings. Building on this idea, we employ the Schrödingerization framework [Phys. Rev. Lett. 133 (2024), 230602] to implement IMEX schemes on quantum computers. Compared to previous HHL type quantum AP scheme [J. Comput. Phys. 471 (2022), 111641], this new method requires narrower -- an extra logarithmic factor -- auxiliary register numerical examples on linear heat and multiscale telegraph equations demonstrate the independence in $\varepsilon$ of the method.

Shi Jin, Hanqing Lu, Lorenzo Pareschi

In this paper, we develop a stochastic Asymptotic-Preserving (sAP) scheme for the kinetic chemotaxis system with random inputs, which will converge to the modified Keller-Segel model with random inputs in the diffusive regime. Based on the generalized Polynomial Chaos (gPC) approach, we design a high order stochastic Galerkin method using implicit-explicit (IMEX) Runge-Kutta (RK) time discretization with a macroscopic penalty term. The new schemes improve the parabolic CFL condition to a hyperbolic type when the mean free path is small, which shows significant efficiency especially in uncertainty quantification (UQ) with multi-scale problems. The stochastic Asymptotic-Preserving property will be shown asymptotically and verified numerically in several tests. Many other numerical tests are conducted to explore the effect of the randomness in the kinetic system, in the aim of providing more intuitions for the theoretic study of the chemotaxis models.

Haiquan Lu, Yong Zeng, Shaodan Ma et al.

Unmanned aerial vehicle (UAV) is regarded as a key enabling platform for low-altitude economy, due to its advantages such as 3D maneuverability, flexible deployment, and LoS air-to-air/ground communication links. In particular, the intrinsic high mobility renders UAV especially suitable for operating as a movable antenna (MA) from the sky. In this paper, by exploiting the flexible mobility of UAV swarm and antenna position adjustment of MA, we propose a novel UAV swarm enabled two-level MA system, where UAVs not only individually deploy a local MA array, but also form a larger-scale MA system with their individual MA arrays via swarm coordination. We formulate a general optimization problem to maximize the minimum achievable rate over all ground user equipments (UEs), by jointly optimizing the 3D UAV swarm placement positions, their individual MAs' positions, and receive beamforming for different UEs. To gain useful insights, we first consider the special case where each UAV has only one antenna, under different scenarios of one single UE, two UEs, and arbitrary number of UEs. In particular, for the two-UE case, we derive the optimal UAV swarm placement positions in closed-form that achieves IUI-free communication when the uniform plane wave (UPW) model holds, where the UAV swarm forms a uniform sparse array (USA) satisfying minimum safe distance constraint. While for the general case with arbitrary number of UEs, we propose an efficient alternating optimization algorithm to solve the formulated non-convex optimization problem. Then, we extend the results to the case where each UAV is equipped with multiple antennas. Numerical results verify that the proposed low-altitude UAV swarm enabled MA system significantly outperforms various benchmark schemes, thanks to the exploitation of two-level mobility to create more favorable channel conditions for multi-UE communications.

Yucheng Sheng, Kai Huang, Le Liang et al.

In this letter, we use large language models (LLMs) to develop a high-performing and robust beam prediction method. We formulate the millimeter wave (mmWave) beam prediction problem as a time series forecasting task, where the historical observations are aggregated through cross-variable attention and then transformed into text-based representations using a trainable tokenizer. By leveraging the prompt-as-prefix (PaP) technique for contextual enrichment, our method harnesses the power of LLMs to predict future optimal beams. Simulation results demonstrate that our LLM-based approach outperforms traditional learning-based models in prediction accuracy as well as robustness, highlighting the significant potential of LLMs in enhancing wireless communication systems.

Fuwang Dong, Fan Liu, Yifeng Xiong et al.

In the low-altitude wireless networks, the simultaneous sensing data acquisition and sharing (SDAS) through an ISAC signaling strategy becomes a typical application scenario. In this paper, we mainly investigate three primary aspects of the SDAS system, namely, the information-theoretic framework, the optimal distribution of channel input, and the optimal waveform design for Gaussian signaling. First, we establish the information-theoretic framework and develop a modified source-channel separation theorem (MSST) tailored for the SDAS systems. The proposed MSST elucidates the relationship between achievable distortion, coding rate, and communication channel capacity in cases where the distortion metric is separable for sensing and communication (S\&C) processes. Second, we present an optimal channel input design for dual-functional signaling, which aims to minimize SDAS distortion under the constraints of the MSST and resource budget. We then conceive a two-step Blahut-Arimoto (BA)-based optimal search algorithm to numerically solve the functional optimization problem. Third, to provide practical design insights, we further propose an optimal waveform design for Gaussian signaling in multi-input multi-output (MIMO) SDAS systems. The associated covariance matrix optimization problem is addressed using a successive convex approximation (SCA)-based waveform design algorithm. Finally, we provide numerical simulation results to demonstrate the effectiveness of the proposed algorithms, which characterize the unique performance tradeoff between S&C processes.

Zijian Kuang, Lihang Ying, Shi Jin et al.

Pixel-aligned Implicit Function (PIFu) effectively captures subtle variations in body shape within a low-dimensional space through extensive training with human 3D scans, its application to live animals presents formidable challenges due to the difficulty of obtaining animal cooperation for 3D scanning. To address this challenge, we propose the combination of two-stage supervised and self-supervised training to address the challenge of obtaining animal cooperation for 3D scanning. In the first stage, we leverage synthetic animal models for supervised learning. This allows the model to learn from a diverse set of virtual animal instances. In the second stage, we use 2D multi-view consistency as a self-supervised training method. This further enhances the model's ability to reconstruct accurate and realistic 3D shape and texture from largely available single-view images of real animals. The results of our study demonstrate that our approach outperforms state-of-the-art methods in both quantitative and qualitative aspects of bird 3D digitization. The source code is available at https://github.com/kuangzijian/drifu-for-animals.

Yucheng Sheng, Le Liang, Hao Ye et al.

Cooperative perception, offering a wider field of view than standalone perception, is becoming increasingly crucial in autonomous driving. This perception is enabled through vehicle-to-vehicle (V2V) communication, allowing connected automated vehicles (CAVs) to exchange sensor data, such as light detection and ranging (LiDAR) point clouds, thereby enhancing the collective understanding of the environment. In this paper, we leverage an importance map to distill critical semantic information, introducing a cooperative perception semantic communication framework that employs intermediate fusion. To counter the challenges posed by time-varying multipath fading, our approach incorporates the use of orthogonal frequency-division multiplexing (OFDM) along with channel estimation and equalization strategies. Furthermore, recognizing the necessity for reliable transmission, especially in the low SNR scenarios, we introduce a novel semantic error detection method that is integrated with our semantic communication framework in the spirit of hybrid automatic repeated request (HARQ). Simulation results show that our model surpasses the traditional separate source-channel coding methods in perception performance, both with and without HARQ. Additionally, in terms of throughput, our proposed HARQ schemes demonstrate superior efficiency to the conventional coding approaches.

Yueshan Lin, Wei Feng, Yunfei Chen et al.

This paper investigates latency-constrained resource synergization for mission-oriented non-terrestrial networks (NTNs) in post-disaster emergency scenarios. When terrestrial infrastructures are damaged, unmanned aerial vehicles (UAVs) equipped with edge information hubs (EIHs) are deployed to provide temporary coverage and synergize communication and computing resources for rapid situation awareness. We formulate a joint resource configuration and location optimization problem to minimize overall resource costs while guaranteeing stringent latency requirements. Through analytical derivations, we obtain closed-form optimal solutions that reveal the fundamental tradeoff between communication and computing resources, and develop a successive convex approximation method for EIH location optimization. Simulation results demonstrate that the proposed scheme achieves approximately 20% cost reduction compared with benchmark approaches, validating its optimality and effectiveness for mission-critical emergency response applications in the sixth-generation (6G) era.

Shunfeng Chu, Jun Li, Jianxin Wang et al.

As an emerging technology, digital twin (DT) can provide real-time status and dynamic topology mapping for Internet of Things (IoT) devices. However, DT and its implementation within industrial IoT networks necessitates substantial, distributed data support, which often leads to ``data silos'' and raises privacy concerns. To address these issues, we develop a dynamic resource scheduling algorithm tailored for the asynchronous federated learning (FL)-based lightweight DT empowered IoT network. Specifically, our approach aims to minimize a multi-objective function that encompasses both energy consumption and latency by optimizing IoT device selection and transmit power control, subject to FL model performance constraints. We utilize the Lyapunov method to decouple the formulated problem into a series of one-slot optimization problems and develop a two-stage optimization algorithm to achieve the optimal transmission power control and IoT device scheduling strategies. In the first stage, we derive closed-form solutions for optimal transmit power on the IoT device side. In the second stage, since partial state information is unknown, e.g., the transmitting power and computational frequency of IoT device, the edge server employs a multi-armed bandit (MAB) framework to model the IoT device selection problem and utilizes an efficient online algorithm, namely the client utility-based upper confidence bound (CU-UCB), to address it. Numerical results validate our algorithm's superiority over benchmark schemes, and simulations demonstrate that our algorithm achieves faster training speeds on the Fashion-MNIST and CIFAR-10 datasets within the same training duration.

Xinran Fang, Wei Feng, Yanmin Wang et al.

In hazardous environments, sensors and actuators can be deployed to see and operate on behalf of humans, enabling safe and efficient task execution. Functioning as a neural center, the edge information hub (EIH), which integrates communication and computing capabilities, coordinates these sensors and actuators into sensing-communication-computing-control (SC3) closed loops to enable autonomous operations. From a system-level optimization perspective, this paper addresses the problem of joint sensor-actuator pairing and resource allocation across multiple SC3 closed loops. To tackle the resulting mixed-integer nonlinear programming problem, we develop a learning-optimization-integrated actor-critic (LOAC) framework. In this framework, a deep neural network-based actor generates pairing candidates, while an optimization-based critic subsequently allocates communication and computing resources. The actor is then iteratively refined through feedback from the critic. Simulation results demonstrate that the LOAC framework achieves near-optimal solutions with low computational complexity, offering significant performance gains in reducing control cost.

Chen Chen, Weijie Jin, Hengtao He et al.

Deep learning (DL) has been widely used in future 6G physical layer communications, but task-specific DL models are difficult to generalize across different physical layer tasks. Recently emerging wireless foundation models demonstrate strong generalization capability. However, existing methods mainly adapt pretrained language/vision models or rely on CSI reconstruction objectives for pretraining, with limited use of channel knowledge, and thus have limited performance. To address this limitation, we propose SPA-MAE, a physics-guided wireless foundation model by exploiting the adapted MAE backbone and channel knowledge. A physical prior module is developed to provide two complementary guidance signals in the pretraining stage. Specifically, the parameter-aware guidance branch extracts features from explicit multipath parameters and encourages the encoder output to align them, while the structure-aware guidance branch encourages the encoder to capture the sparse transformed-domain CSI structure obtained after a 2D FFT. After end-to-end learning, the MAE encoder will be retained for downstream tasks. Experiments on four wireless tasks show that SPA-MAE outperforms state-of-the-art CSI foundation models with smaller number of parameters, especially under low-SNR and limited-data conditions.

Xingyu Zhou, Le Liang, Hao Ye et al.

Accurate channel state information (CSI) acquisition is essential for modern wireless systems, which becomes increasingly difficult under large antenna arrays, strict pilot overhead constraints, and diverse deployment environments. Existing artificial intelligence-based solutions often lack robustness and fail to generalize across scenarios. To address this limitation, this paper introduces a predictive-foundation-model-based channel estimation framework that enables accurate, low-overhead, and generalizable CSI acquisition. The proposed framework employs a predictive foundation model trained on large-scale cross-domain CSI data to extract universal channel representations and provide predictive priors with strong cross-scenario transferability. A pilot processing network based on a vision transformer architecture is further designed to capture spatial, temporal, and frequency correlations from pilot observations. An efficient fusion mechanism integrates predictive priors with real-time measurements, enabling reliable CSI reconstruction even under sparse or noisy conditions. Extensive evaluations across diverse configurations demonstrate that the proposed estimator significantly outperforms both classical and data-driven baselines in accuracy, robustness, and generalization capability.

Ahmad Bazzi, Florian Gast, Fan Liu et al.

Future 6G systems are expected to exploit upper midband spectrum in frequency range 3 (FR3) not only for high throughput communications, but also for sensing services such as localization, detection, and situational awareness. The following paper develops a concrete path from today's coverage-oriented deployments to FR3 networks that treat sensing as a native function. We first show how existing FR2 radars can be time-multiplexed and coordinated under a $6$G medium access control as radar-as-a-service, forming a bridge between legacy sensing and network-managed integrated sensing and communications (ISAC). We then propose a hierarchical FR3 beam-alignment strategy in which coarse access occurs at lower frequencies and refinement occurs at upper FR3, and quantify the resulting sensing and communication capabilities via range-angle Cram{é}r-Rao bounds in the near field. We identify intra- and inter-beam squint phenomena specific to wideband FR3 arrays, and discuss design approaches to mitigate them. On the signal-processing side, we argue that FR3 sensing cannot rely solely on pilot resources and discuss how much sensing information can be extracted from payload resource elements. We further highlight the role of calibrated FR3 channel simulators and real-time models as the core of wireless digital twins for training and evaluating ISAC algorithms, and discuss how massive MIMO and dense or distributed deployments at FR3 naturally act as large reconfigurable sensor arrays.

Zhiwei Shan, Xinping Yi, Le Liang et al.

Device-to-device (D2D) spectrum sharing in wireless communications is a challenging non-convex combinatorial optimization problem, involving entangled link scheduling and power control in a large-scale network. The state-of-the-art methods, either from a model-based or a data-driven perspective, exhibit certain limitations such as the critical need for channel state information (CSI) and/or a large number of (solved) instances (e.g., network layouts) as training samples. To advance this line of research, we propose a novel hybrid model/datadriven spectrum sharing mechanism with graph reinforcement learning for link scheduling (GRLinQ), injecting information theoretical insights into machine learning models, in such a way that link scheduling and power control can be solved in an intelligent yet explainable manner. Through an extensive set of experiments, GRLinQ demonstrates superior performance to the existing model-based and data-driven link scheduling and/or power control methods, with a relaxed requirement for CSI, a substantially reduced number of unsolved instances as training samples, a possible distributed deployment, reduced online/offline computational complexity, and more remarkably excellent scalability and generalizability over different network scenarios and system configurations.

Xinping Yi, Gaojie Jin, Xiaowei Huang et al.

Understanding the generalization behavior of deep neural networks remains a fundamental challenge in modern statistical learning theory. Among existing approaches, PAC-Bayesian norm-based bounds have demonstrated particular promise due to their data-dependent nature and their ability to capture algorithmic and geometric properties of learned models. However, most existing results rely on isotropic Gaussian posteriors, heavy use of spectral-norm concentration for weight perturbations, and largely architecture-agnostic analyses, which together limit both the tightness and practical relevance of the resulting bounds. To address these limitations, in this work, we propose a unified framework for PAC-Bayesian norm-based generalization by reformulating the derivation of generalization bounds as a stochastic optimization problem over anisotropic Gaussian posteriors. The key to our approach is a sensitivity matrix that quantifies the network outputs with respect to structured weight perturbations, enabling the explicit incorporation of heterogeneous parameter sensitivities and architectural structures. By imposing different structural assumptions on this sensitivity matrix, we derive a family of generalization bounds that recover several existing PAC-Bayesian results as special cases, while yielding bounds that are comparable to or tighter than state-of-the-art approaches. Such a unified framework provides a principled and flexible way for geometry-/structure-aware and interpretable generalization analysis in deep learning.

Yucheng Sheng, Jiacheng Wang, Le Liang et al.

The aggressive densification of modern wireless networks necessitates judicious resource allocation to mitigate severe mutual interference. However, classical iterative algorithms remain computationally prohibitive for real-time applications requiring rapid responsiveness. While recent deep learning-based methods show promise, they typically function as task-specific solvers lacking the flexibility to adapt to different objectives and scenarios without expensive retraining. To address these limitations, we propose a graph foundation model for resource allocation (GFM-RA) based on a pre-training and fine-tuning paradigm to extract unified representations, thereby enabling rapid adaptation to different objectives and scenarios. Specifically, we introduce an interference-aware Transformer architecture with a bias projector that injects interference topologies into global attention mechanisms. Furthermore, we develop a hybrid self-supervised pre-training strategy that synergizes masked edge prediction with negative-free Teacher-Student contrastive learning, enabling the model to capture transferable structural representations from massive unlabeled datasets. Extensive experiments demonstrate that the proposed framework achieves state-of-the-art performance and scales effectively with increased model capacity. Crucially, leveraging its unified representations, the foundation model exhibits exceptional sample efficiency, enabling robust few-shot adaptation to diverse and unsupervised downstream objectives in out-of-distribution (OOD) scenarios. These results demonstrate the promise of pre-trained foundation models for adaptable wireless resource allocation and provide a strong foundation for future research on generalizable learning-based wireless optimization.

Fan Liu, Yifeng Xiong, Ya-Feng Liu et al.

The inherent randomness of communication symbols creates a fundamental tension in Integrated Sensing and Communications (ISAC). On the one hand, they enable data transmission while allowing sensing to fully reuse communication resources. On the other hand, their randomness induces waveform-dependent fluctuations that directly affect sensing accuracy. This paper investigates a foundational question arising from this tradeoff: \textit{How does the modulation waveform affect the ranging Cramér--Rao Bound (CRB) when sensing reuses random data symbols?} We address this question by revealing a structural factorization of the Fisher information matrix (FIM) for joint delay-amplitude estimation, which separates the deterministic Jacobian of the target geometry from the random frequency-domain signal power induced by the data symbols. This structure yields a Jensen-type universal lower bound on the CRB, which is exactly attained by CP-OFDM under PSK constellations. For QAM and broader sub-Gaussian constellations, we develop an asymptotic perturbation analysis of the inverse FIM and prove that, when the number of transmitted symbols $N$ grows large, CP-OFDM achieves a lower ranging CRB than any frequency-spread orthogonal waveform over the almost-sure event where the random FIM is invertible. This superiority is further extended to amplitude estimation and full joint delay-amplitude estimation. We also characterize the local geometry of the stochastic CRB minimization problem over the unitary group. The analysis reveals that CP-OFDM is a stationary point for finite $N$, and its Riemannian Hessian is positive semidefinite for sufficiently large $N$, establishing its asymptotic local optimality. Numerical results confirm that OFDM outperforms representative waveforms including SC, OTFS, and AFDM.

Mengyuan Li, Qianfan Lu, Jiachen Tian et al.

In near-field extremely large-scale multiple-input multiple-output (XL-MIMO) systems, spherical wavefront propagation expands the traditional beam codebook into the joint angular-distance domain, rendering conventional beam training prohibitively inefficient, especially in complex 3-dimensional (3D) low-altitude environments. Furthermore, since near-field beam variations are deeply coupled not only with user positions but also with the physical surroundings, precise beam alignment demands profound environmental understanding capabilities. To address this, we propose a large language model (LLM)-driven multimodal framework that fuses historical GPS data, RGB image, LiDAR data, and strategically designed task-specific textual prompts. By utilizing the powerful emergent reasoning and generalization capabilities of the LLM, our approach learns complex spatial dynamics to achieve superior environmental comprehension...

José A. Carrillo, Shi Jin, Haoyu Zhang et al.

This paper presents a particle-based optimization method designed for addressing minimization problems with equality constraints, particularly in cases where the loss function exhibits non-differentiability or non-convexity. The proposed method combines components from consensus-based optimization algorithm with a newly introduced forcing term directed at the constraint set. A rigorous mean-field limit of the particle system is derived, and the convergence of the mean-field limit to the constrained minimizer is established. Additionally, we introduce a stable discretized algorithm and conduct various numerical experiments to demonstrate the performance of the proposed method.

Yongwei Yi, Xinping Yi, Wenjin Wang et al.

In practical Multiuser Multiple-Input Multiple-Output (MU-MIMO) systems, symbol detection remains challenging due to severe inter-user interference and sensitivity to Channel State Information (CSI) uncertainty. In contrast to the mostly studied belief propagation-type model-driven methods, which incur high computational complexity, Soft Interference Cancellation (SIC) strikes a good balance between performance and complexity. To further address CSI mismatch and nonlinear effects, the recently proposed data-driven deep neural receivers, such as DeepSIC, leverage the advantages of deep neural networks for interference cancellation and symbol detection, demonstrating strong empirical performance. However, there is still a lack of theoretical underpinning for why and to what extent DeepSIC could generalize with the number of training samples. This paper proposes inspecting the fully data-driven DeepSIC detection within a Network-of-MLPs architecture, which is composed of multiple interconnected MLPs via outer and inner Directed Acyclic Graphs (DAGs). Within such an architecture, DeepSIC can be upgraded as a graph-based message-passing process using Graph Neural Networks (GNNs), termed GNNSIC, with shared model parameters across users and iterations. Notably, GNNSIC achieves excellent expressivity comparable to DeepSIC with substantially fewer trainable parameters, resulting in improved sample efficiency and enhanced user generalization. By conducting a norm-based generalization analysis using Rademacher complexity, we reveal that an exponential dependence on the number of iterations for DeepSIC can be eliminated in GNNSIC due to parameter sharing. Simulation results demonstrate that GNNSIC attains comparable or improved Symbol Error Rate (SER) performance to DeepSIC with significantly fewer parameters and training samples.

Xiaotian Fan, Xingyu Zhou, Le Liang et al.

Deep generative models offer a powerful alternative to conventional channel estimation by learning complex channel distributions. By integrating the rich environmental information available in modern sensing-aided networks, this paper proposes MultiCE-Flow, a multimodal channel estimation framework based on flow matching and diffusion transformer (DiT). We design a specialized multimodal perception module that fuses LiDAR, camera, and location data into a semantic condition, while treating sparse pilots as a structural condition. These conditions guide a DiT backbone to reconstruct high-fidelity channels. Unlike standard diffusion models, we employ flow matching to learn a linear trajectory from noise to data, enabling efficient one-step sampling. By leveraging environmental semantics, our method mitigates the ill-posed nature of estimation with sparse pilots. Extensive experiments demonstrate that MultiCE-Flow consistently outperforms traditional baselines and existing generative models. Notably, it exhibits superior robustness to out-of-distribution scenarios and varying pilot densities, making it suitable for environment-aware communication systems.

Chunhui Chen, Jing Chen, Baojia Luo et al.

Numerically solving multi-marginal optimal transport (MMOT) problems is computationally prohibitive, even for moderate-scale instances involving $l\ge4$ marginals with support sizes of $N\ge1000$. The cost in MMOT is represented as a tensor with $N^l$ elements. Even accessing each element once incurs a significant computational burden. In fact, many algorithms require direct computation of tensor-vector products, leading to a computational complexity of $O(N^l)$ or beyond. In this paper, inspired by our previous work [$Comm. \ Math. \ Sci.$, 20 (2022), pp. 2053 - 2057], we observe that the costly tensor-vector products in the Sinkhorn Algorithm can be computed with a recursive process by separating summations and dynamic programming. Based on this idea, we propose a fast tensor-vector product algorithm to solve the MMOT problem with $L^1$ cost, achieving a miraculous reduction in the computational cost of the entropy regularized solution to $O(N)$. Numerical experiment results confirm such high performance of this novel method which can be several orders of magnitude faster than the original Sinkhorn algorithm.

Haoning Dang, Shi Jin, Fei Wang

This paper proposes an Adaptive-Growth Randomized Neural Network (AG-RaNN) method for computing multivalued solutions of nonlinear first-order PDEs with hyperbolic characteristics, including quasilinear hyperbolic balance laws and Hamilton--Jacobi equations. Such solutions arise in geometric optics, seismic waves, semiclassical limit of quantum dynamics and high frequency limit of linear waves, and differ markedly from the viscosity or entropic solutions. The main computational challenges lie in that the solutions are no longer functions, and become union of multiple branches, after the formation of singularities. Level-set formulations offer a systematic alternative by embedding the nonlinear dynamics into linear transport equations posed in an augmented phase space, at the price of substantially increased dimensionality. To alleviate this computational burden, we combine AG-RaNN with an adaptive collocation strategy that concentrates samples in a tubular neighborhood of the zero level set, together with a layer-growth mechanism that progressively enriches the randomized feature space. Under standard regularity assumptions on the transport field and the characteristic flow, we establish a convergence result for the AG-RaNN approximation of the level-set equations. Numerical experiments demonstrate that the proposed method can efficiently recover multivalued structures and resolve nonsmooth features in high-dimensional settings.

Tianhao Mao, Le Liang, Jie Yang et al.

Accurate beam prediction is a key enabler for next-generation wireless communication systems. In this paper, we propose a multimodal large language model (LLM)-based beam prediction framework that effectively utilizes contextual information, provided by sensory data including RGB camera images and LiDAR point clouds. To effectively fuse heterogeneous modalities, we design specialized modality encoders together with a beam-guided attention masking mechanism and a high-frequency temporal alignment strategy, enabling robust cross-modal feature integration under dynamic environments. Furthermore, we construct a large-scale multimodal dataset for communication, named Multimodal-Wireless, which covers diverse weather and traffic conditions with high-fidelity ray-tracing labels. Extensive simulation results demonstrate that the proposed approach significantly reduces the reliance on oracle angle-of-departure knowledge and consistently outperforms state-of-the-art multimodal LLM-based beam prediction methods in terms of beam accuracy and communication performance, improving the average Top-1 accuracy to 80.8% and the average normalized gain to 89.1%.

Jiayang Wan, Ke He, Yafei Wang et al.

Due to the significant variations in unmanned aerial vehicle (UAV) altitude and horizontal mobility, it becomes difficult for any single network to ensure continuous and reliable threedimensional coverage. Towards that end, the space-air-ground integrated network (SAGIN) has emerged as an essential architecture for enabling ubiquitous UAV connectivity. To address the pronounced disparities in coverage and signal characteristics across heterogeneous networks, this paper formulates UAV mobility management in SAGIN as a constrained multi-objective joint optimization problem. The formulation couples discrete link selection with continuous trajectory optimization. Building on this, we propose a two-level multi-agent hierarchical deep reinforcement learning (HDRL) framework that decomposes the problem into two alternately solvable subproblems. To map complex link selection decisions into a compact discrete action space, we conceive a double deep Q-network (DDQN) algorithm in the top-level, which achieves stable and high-quality policy learning through double Q-value estimation. To handle the continuous trajectory action space while satisfying quality of service (QoS) constraints, we integrate the maximum-entropy mechanism of the soft actor-critic (SAC) and employ a Lagrangian-based constrained SAC (CSAC) algorithm in the lower-level that dynamically adjusts the Lagrange multipliers to balance constraint satisfaction and policy optimization. Moreover, the proposed algorithm can be extended to multi-UAV scenarios under the centralized training and decentralized execution (CTDE) paradigm, which enables more generalizable policies. Simulation results demonstrate that the proposed scheme substantially outperforms existing benchmarks in throughput, link switching frequency and QoS satisfaction.