arXiv subjects
Publications and source records attributed to Zhiqiang Wei.
Let \[ π_{0}=[\underbrace{2,\ldots,2}_{2s-1}],\quad π_{\infty}=[\underbrace{3,\ldots,3}_{s},\underbrace{1,\ldots,1}_{s-2}],\quad π_{1}=[γ_{1},γ_{2},γ_{3}] \] be three nontrivial partitions of the integer \(d=4s-2\), where \(s\ge 3\). We establish a necessary and sufficient condition for the candidate datum \(\{π_{0},π_{\infty},π_{1}\}\) to be realizable by a rational map.
This paper investigates the sensing potential of affine frequency division multiplexing (AFDM) in high-mobility integrated sensing and communication (ISAC) from the perspective of radar waveforms. We introduce an innovative parameter selection criterion that establishes a precise mathematical equivalence between AFDM subcarriers and Nyquist-sampled frequency-modulated continuous-wave (FMCW). This connection not only provides a clear physical insight into AFDM's sensing mechanism but also enables a direct mapping from the DAFT index to delay-Doppler (DD) parameters of wireless channels. Building on this, we develop a novel input-output model in a DD-parameterized DAFT (DD-DAFT) domain for AFDM, which explicitly reveals the inherent DD coupling effect arising from the chirp-channel interaction. Subsequently, we design two matched-filtering sensing algorithms. The first is performed in the time-frequency domain with low complexity, while the second is operated in the DD-DAFT domain to precisely resolve the DD coupling. Simulations show that our algorithms achieve effective pilot-free sensing and demonstrate a fundamental trade-off between sensing performance, communication overhead, and computational complexity. The proposed AFDM outperforms classical AFDM and other variants in most scenarios.
The Low-Altitude Economy (LAE) is rapidly expanding, giving rise to low-altitude wireless networks (LAWNs), where large-scale cellular-connected unmanned aerial vehicle (UAV) deployments support heterogeneous mission-critical applications over multi-cell ground base station (GBS) infrastructures. To ensure mission success, each UAV must jointly optimize communication throughput and mission completion efficiency. In fifth-generation (5G) new radio (NR) systems, the equal resource block (RB) allocation policy induces strong strategic coupling among UAV trajectories: when a UAV enters a GBS cell, it reduces the RB share available to all co-served UAVs, thereby altering their achievable rates and trajectory incentives through shared wireless resources. Existing studies either ignore this coupling or focus on single-cell infrastructure, leaving the multi-cell, congestion-aware UAV trajectory planning problem insufficiently addressed. To fill this gap, we formulate the problem as a cooperative stochastic congestion game with a communication-and-mission-aware utility function, and propose a centralized-training decentralized-execution multi-agent proximal policy optimization (CTDE-MAPPO) algorithm to maximize social welfare under multi-cell RB congestion. Simulation results show that the proposed method outperforms QMIX, independent Q-learning, and random baselines in terms of aggregate utility and mission success rate, while achieving stable convergence within practical training budgets.
We establish a structure theorem for rational maps $f:\overline{\mathbb{C}}\to\overline{\mathbb{C}}$: the pullback metric $f^{*}{\rm d}s_{0}^{2}$ of the standard metric ${\rm d}s_{0}^{2}$ admits a canonical decomposition into finitely many footballs -- Riemann spheres with two antipodal conical singularities of equal angle -- by cutting along a finite set of geodesics. This geometric decomposition provides a new framework for the Hurwitz existence problem. As an application, we prove that a collection $\mathcal{D}$ of $k$ nontrivial partitions of a positive integer $d$ satisfying the Riemann--Hurwitz condition is realizable as the branch datum of a rational map whenever $k>l+1$, where $l$ is the minimum partition length. This unifies the classical results of Thom ($l = 1$), Pakovich ($l = 2$) and Barański ($k\geq d$), and confirms a conjecture of Zheng in an important special case.
High-mobility scenarios will be a critical part of 6G systems. Since the widely deployed orthogonal frequency division multiplexing (OFDM) waveform suffers from subcarrier orthogonality loss under severe Doppler spread, delay-Doppler domain multi-carrier (DDMC) modulation systems, such as orthogonal time frequency space (OTFS), have been extensively studied. While OTFS can exploit time-frequency (TF) domain channel diversity, it faces challenges including high receiver complexity and inflexible TF resource allocation, making OFDM still the most promising waveform for 6G. In this article, we propose a DD domain signal processing-aided OFDM (DD-a-OFDM) scheme to enhance OFDM performance based on DDMC research insights. First, we design a DD-a-OFDM system structure, retaining the classical OFDM transceiver while incorporating DD domain channel estimation and TF domain equalization. Second, we detail DD domain channel estimation using discrete TF pilots and prove that TF domain inter-carrier interference (ICI) could be transformed into DD domain Gaussian interference. Third, we derive closed-form Cramér-Rao lower bounds (CRLBs) for DD domain channel estimation. Fourth, we develop maximum likelihood (ML) and peak detection-based channel estimators, along with a corresponding TF domain equalizer. Numerical results verify the proposed design, showing that DD-a-OFDM reduces the bit-error rate (BER) compared to classical OFDM and outperforms OTFS in channel estimation accuracy with lower pilot overhead.
This paper investigates the design of orthogonal frequency-division multiplexing (OFDM) waveforms for bistatic integrated sensing and communication (ISAC) systems. In the considered framework, an ISAC transmitter jointly optimizes subcarrier assignment and power allocation for a single OFDM waveform that simultaneously supports communication and sensing functionalities. Meanwhile, an ISAC receiver decodes information on communication subcarriers and estimates per-path propagation delays via exploiting pilot symbols on sensing subcarriers. We propose a joint path coefficient and delay estimation (JPCDE) scheme, revealing that the achievable communication data rate (CDR) is determined by the number of communication subcarriers, whereas the delay sensing accuracy is governed by the index distribution of sensing subcarriers. Building on this insight, we formulate an OFDM waveform optimization problem to maximize the CDR subject to sensing-accuracy and power-budget constraints. To solve this problem, we employ a quadratic transform and Lagrangian dual decomposition, which iteratively updates the subcarrier assignment and power allocation variables in closed-form. Our results reveal that a subcarrier is allocated for sensing if and only if its Fisher information gain exceeds the corresponding communication rate loss, while the power allocation for communication subcarriers exhibits a bounded water-filling structure. Simulation results demonstrate that the proposed frameworks substantially outperform existing baselines in both delay estimation accuracy and CDR.
Speech Emotion Recognition models typically use single categorical labels, overlooking the inherent ambiguity of human emotions. Ambiguous Emotion Recognition addresses this by representing emotions as probability distributions, but progress is limited by unreliable ground-truth distributions inferred from sparse human annotations. This paper explores whether Large Audio-Language Models (ALMs) can mitigate the annotation bottleneck by generating high-quality synthetic annotations. We introduce a framework leveraging ALMs to create Synthetic Perceptual Proxies, augmenting human annotations to improve ground-truth distribution reliability. We validate these proxies through statistical analysis of their alignment with human distributions and evaluate their impact by fine-tuning ALMs with the augmented emotion distributions. Furthermore, to address class imbalance and enable unbiased evaluation, we propose DiME-Aug, a Distribution-aware Multimodal Emotion Augmentation strategy. Experiments on IEMOCAP and MSP-Podcast show that synthetic annotations enhance emotion distribution, especially in low-ambiguity regions where annotation agreement is high. However, benefits diminish for highly ambiguous emotions with greater human disagreement. This work provides the first evidence that ALMs could address annotation scarcity in ambiguous emotion recognition, but highlights the need for more advanced prompting or generation strategies to handle highly ambiguous cases.
This paper introduces a novel channel knowledge map (CKM)-assisted dual-domain tracking and predictive beamforming scheme for high-mobility wireless networks. The central premise is that the CKM integrates both the coordinate and beam domains, thereby enabling tracking in one domain via treating the other domain's input as priors or measurements. In the coordinate domain (C-Domain), an extended Kalman filter (EKF) is employed to predict and track the state (i.e., location and velocity) of a moving communication receiver across time slots under both line-of-sight (LoS)-present and LoS-absent conditions, where the CKM provides a prior mapping from multipath channel parameters to potential target locations. In the beam domain (B-Domain), the updated location of the receiver is fed back to CKM to offer a priori information of angle of arrival (AoA) variations, which are incorporated to establish beam transition models for effective beam tracking, depending on the angular variation situation of each path. Then, we analyze the Cramér-Rao Bound (CRB) for AoA estimation for each path in the considered system and propose a jointly predictive beamforming and power allocation design to minimize AoA estimation errors, directly enhancing multipath beam tracking accuracy and indirectly improving target tracking performance. Simulation results demonstrate that the proposed scheme achieves significant improvements in both target and beam tracking performance compared to the state-of-the-art approaches, particularly in AoA tracking of non-line-of-sight (NLoS) paths, highlighting the potential gain of CKM in facilitating both target and beam tracking in high-mobility communications.
Orthogonal time frequency space (OTFS) modulation has emerged as a robust solution for high-mobility wireless communications. However, conventional detection algorithms, such as linear equalizers and message passing (MP) methods, either suffer from noise enhancement or fail under complex doubly-selective channels, especially in the presence of fractional delay and Doppler shifts. In this paper, we propose a hybrid low-complexity iterative detection framework that combines linear minimum mean square error (L-MMSE) estimation with MP-based probabilistic inference. The key idea is to apply a new delay-Doppler (DD) commutation precoder (DDCP) to the DD domain signal vector, such that the resulting effective channel matrix exhibits a structured form with several locally dense blocks that are sparsely inter-connected. This precoding structure enables a hybrid iterative detection strategy, where a low-dimensional L-MMSE estimation is applied to the dense blocks, while MP is utilized to exploit the sparse inter-block connections. Furthermore, we provide a detailed complexity analysis, which shows that the proposed scheme incurs lower computational cost compared to the full-size L-MMSE detection. The simulation results of convergence performance confirm that the proposed hybrid MP detection achieves fast and reliable convergence with controlled complexity. In terms of error performance, simulation results demonstrate that our scheme achieves significantly better bit error rate (BER) under various channel conditions. Particularly in multipath scenarios, the BER performance of the proposed method closely approaches the matched filter bound (MFB), indicating its near-optimal error performance.
Introduction: The blood-brain barrier (BBB) protects the central nervous system but prevents most neurotherapeutics from reaching effective concentrations in the brain. BBB-penetrating peptides (BBBPs) offer a promising strategy for brain drug delivery; however, the scarcity of positive samples and severe class imbalance hinder the reliable identification of BBBPs. Objectives: Our goal is to alleviate class imbalance in BBBP prediction and to develop an accurate, interpretable classifier for BBBP prediction. Methods: We propose DREAM-B3P, which couples a feedback diffusion model (FB-Diffusion) for data augmentation with a dual-stream Transformer for classification. FB-Diffusion learns the BBBP distribution via iterative denoising and uses an external analyzer to provide feedback, generating high-quality pseudo-BBBPs. The classifier contains a sequence stream that extracts structural features from peptide sequences and a physicochemical stream that captures physicochemical features such as hydrophobic surface area, molecular charge, number of rotatable bonds, and polarizability. Combining the two features leads to superior BBBP predictive performance. Results: On a benchmark test set containing equal numbers of BBBPs and non-BBBPs, DREAM-B3P surpasses baseline methods (Deep-B3P, B3Pred, BBPpredict and Augur), improving AUC/ACC/MCC by 4.3\%/17.8\%/14.9\%, respectively, over the second-best method. Conclusion: By integrating feedback diffusion with a dual-stream Transformer classifier, DREAM-B3P effectively mitigates data scarcity and imbalance and achieves state-of-the-art performance.
We investigate the Hurwitz existence problem from a computational viewpoint. Leveraging the symmetric-group algorithm by Zheng and building upon implementations originally developed by Baroni, we achieve a complete and non-redundant enumeration of all non-realizable partition triples for positive integers up to $31$. These results are further categorized into four types according to their underlying mathematical structure; it is observed that nearly nine-tenths of them can be explained by known theoretical results. As an application, we verify the prime-degree conjecture for all primes less than $32$. In light of the exponential memory growth inherent in existing computational approaches -- which limits their feasibility at higher degrees -- we propose a novel software architecture designed to stabilize memory usage, thereby facilitating further detection of exceptional cases in the Hurwitz existence problem. The complete dataset of non-realizable partition triples, along with our implementation, will been made public on GitHub.
Accurate 3D semantic occupancy perception is essential for autonomous driving in complex environments with diverse and irregular objects. While vision-centric methods suffer from geometric inaccuracies, LiDAR-based approaches often lack rich semantic information. To address these limitations, MS-Occ, a novel multi-stage LiDAR-camera fusion framework which includes middle-stage fusion and late-stage fusion, is proposed, integrating LiDAR's geometric fidelity with camera-based semantic richness via hierarchical cross-modal fusion. The framework introduces innovations at two critical stages: (1) In the middle-stage feature fusion, the Gaussian-Geo module leverages Gaussian kernel rendering on sparse LiDAR depth maps to enhance 2D image features with dense geometric priors, and the Semantic-Aware module enriches LiDAR voxels with semantic context via deformable cross-attention; (2) In the late-stage voxel fusion, the Adaptive Fusion (AF) module dynamically balances voxel features across modalities, while the High Classification Confidence Voxel Fusion (HCCVF) module resolves semantic inconsistencies using self-attention-based refinement. Experiments on two large-scale benchmarks demonstrate state-of-the-art performance. On nuScenes-OpenOccupancy, MS-Occ achieves an Intersection over Union (IoU) of 32.1% and a mean IoU (mIoU) of 25.3%, surpassing the state-of-the-art by +0.7% IoU and +2.4% mIoU. Furthermore, on the SemanticKITTI benchmark, our method achieves a new state-of-the-art mIoU of 24.08%, robustly validating its generalization capabilities.Ablation studies further confirm the effectiveness of each individual module, highlighting substantial improvements in the perception of small objects and reinforcing the practical value of MS-Occ for safety-critical autonomous driving scenarios.
The self-supervised contrastive learning strategy has attracted considerable attention due to its exceptional ability in representation learning. However, current contrastive learning tends to learn global coarse-grained representations of the image that benefit generic object recognition, whereas such coarse-grained features are insufficient for fine-grained visual recognition. In this paper, we incorporate subtle local fine-grained feature learning into global self-supervised contrastive learning through a pure self-supervised global-local fine-grained contrastive learning framework. Specifically, a novel pretext task called local discrimination (LoDisc) is proposed to explicitly supervise the self-supervised model's focus toward local pivotal regions, which are captured by a simple but effective location-wise mask sampling strategy. We show that the LoDisc pretext task can effectively enhance fine-grained clues in important local regions and that the global-local framework further refines the fine-grained feature representations of images. Extensive experimental results on different fine-grained object recognition tasks demonstrate that the proposed method can lead to a decent improvement in different evaluation settings. The proposed method is also effective for general object recognition tasks.
The effective utilization of observational data is frequently hindered by insufficient resolution. To address this problem, we present a new spatio-temporal super-resolution (STSR) model, called InWaveSR. It is built on a deep learning framework with physical restrictions and can efficiently generate high-resolution data from low-resolution input, especially for data featuring internal solitary waves (ISWs). To increase generality and interpretation, the model InWaveSR uses the primitive Navier-Stokes equations as the constraint, ensuring that the output results are physically consistent. In addition, the proposed model incorporates an HF-ResBlock component that combines the attention mechanism and the Fast Fourier Transform (FFT) method to improve the performance of the model in capturing high-frequency characteristics. Simultaneously, in order to enhance the adaptability of the model to complicated bottom topography, an edge sampling and numerical pre-processing method are carried out to optimize the training process. On evaluations using the in-situ observational ISW data, the proposed InWaveSR achieved a peak signal-to-noise ratio (PSNR) score of 36.2, higher than those of the traditional interpolation method and the previous neural network. This highlights its significant superiority over traditional methods, demonstrating its excellent performance and reliability in high-resolution ISW reconstruction.
Affine Frequency Division Multiplexing (AFDM) has attracted considerable attention for its robustness to Doppler effects. However, its high receiver-side computational complexity remains a major barrier to practical deployment. To address this, we propose a novel symbol-level precoding (SLP)-based AFDM transmission framework, which shifts the signal processing burden in downlink communications from user side to the base station (BS), enabling direct symbol detection without requiring channel estimation or equalization at the receiver. Specifically, in the uplink phase, we propose a Sparse Bayesian Learning (SBL) based channel estimation algorithm by exploiting the inherent sparsity of affine frequency (AF) domain channels. In particular, the sparse prior is modeled via a hierarchical Laplace distribution, and parameters are iteratively updated using the Expectation-Maximization (EM) algorithm. We also derive the Bayesian Cramer-Rao Bound (BCRB) to characterize the theoretical performance limit. In the downlink phase, the BS employs the SLP technology to design the transmitted waveform based on the estimated uplink channel state information (CSI) and channel reciprocity. The resulting optimization problem is formulated as a second-order cone programming (SOCP) problem, and its dual problem is investigated by Lagrangian function and Karush-Kuhn-Tucker conditions. Simulation results demonstrate that the proposed SBL estimator outperforms traditional orthogonal matching pursuit (OMP) in accuracy and robustness to off-grid effects, while the SLP-based waveform design scheme achieves performance comparable to conventional AFDM receivers while significantly reducing the computational complexity at receiver, validating the practicality of our approach.
Integrated sensing and communication (ISAC) is pivotal for next-generation wireless networks, rendering the computation of rate-distortion trade-off in ISAC systems critically important. In this paper, we propose the extended Arimoto-Blahut (AB) algorithms to calculate the rate-distortion trade-off in bistatic ISAC systems, which overcome the limitation of existing AB algorithms in handling non-convex constraints. Specifically, we introduce auxiliary variables to transform non-convex distortion constraints into linear constraints, prove that the reformulated linearly-constrained optimization problem maintains the same optimal solution as the original problem, and develop extended AB algorithms for both squared error and logarithmic loss distortion metrics based on the framework of AB algorithm. Numerical results validate the effectiveness of the proposed algorithm.
While combining large language models (LLMs) with evolutionary algorithms (EAs) shows promise for solving complex optimization problems, current approaches typically evolve individual solutions, often incurring high LLM call costs. We introduce \(X\)-evolve, a paradigm-shifting method that instead evolves solution spaces \(X\) (sets of individual solutions) - subsets of the overall search space \(S\). In \(X\)-evolve, LLMs generate tunable programs wherein certain code snippets, designated as parameters, define a tunable solution space. A score-based search algorithm then efficiently explores this parametrically defined space, guided by feedback from objective function scores. This strategy enables broader and more efficient exploration, which can potentially accelerate convergence at a much lower search cost, requiring up to two orders of magnitude fewer LLM calls than prior leading methods. We demonstrate \(X\)-evolve's efficacy across three distinct hard optimization problems. For the cap set problem, we discover a larger partial admissible set, establishing a new tighter asymptotic lower bound for the cap set constant (\(C \ge 2.2203\)). In information theory, we uncover a larger independent set for the 15-vertex cycle graph (\(\mathcal{C}_{15}^{\boxtimes 5}\), size 19,946), thereby raising the known lower bound on its Shannon capacity. Furthermore, for the NP-hard online bin packing problem, we generate heuristics that consistently outperform standard strategies across established benchmarks. By evolving solution spaces, our method considerably improves search effectiveness, making it possible to tackle high-dimensional problems that were previously computationally prohibitive.
Model routing allocates queries to the suitable model, improving system performance while reducing costs. However, existing routing methods face practical limitations that hinder scalability in large-scale applications and struggle to keep up with the rapid growth of the large language model (LLM) ecosystem. To tackle these challenges, we propose TagRouter, a training-free model routing method designed to optimize the synergy among multiple LLMs for open-domain text generation tasks. Experimental results demonstrate that TagRouter outperforms 13 baseline methods, increasing the accept rate of system by 6.15% and reducing costs by 17.20%, achieving optimal cost-efficiency. Our findings provides the LLM community with an efficient and scalable solution for model ensembling, offering users an evolvable "super model."