arXiv subjects

Li Wang

Publications and source records attributed to Li Wang.

At least 127 records · Page 7Linked to original sources

arXiv2025

Dynamical feedback control with operator learning for the Vlasov-Poisson system

To meet the demands of instantaneous control of instabilities over long time horizons in plasma fusion, we design a dynamic feedback control strategy for the Vlasov-Poisson system by constructing an operator that maps state perturbations to an external control field. In the first part of the paper, we propose learning such an operator using a neural network. Inspired by optimal control theory for linearized dynamics, we introduce a low-rank neural operator architecture and train it via adjoint state method. The resulting controller is effective at suppressing instabilities well beyond the training time horizon. To generalize control across varying initial data, we further introduce a novel cancellation-based control strategy that removes the destabilizing component of the electric field. This approach naturally defines an operator without requiring any training, ensures perturbation decay over infinite time, and demonstrates strong robustness under noisy feedback. Numerical experiments confirm the effectiveness of the method in both one- and multidimensional settings.

math.NA↗

arXiv2025

LongFly: Long-Horizon UAV Vision-and-Language Navigation with Spatiotemporal Context Integration

Unmanned aerial vehicles (UAVs) are crucial tools for post-disaster search and rescue, facing challenges such as high information density, rapid changes in viewpoint, and dynamic structures, especially in long-horizon navigation. However, current UAV vision-and-language navigation(VLN) methods struggle to model long-horizon spatiotemporal context in complex environments, resulting in inaccurate semantic alignment and unstable path planning. To this end, we propose LongFly, a spatiotemporal context modeling framework for long-horizon UAV VLN. LongFly proposes a history-aware spatiotemporal modeling strategy that transforms fragmented and redundant historical data into structured, compact, and expressive representations. First, we propose the slot-based historical image compression module, which dynamically distills multi-view historical observations into fixed-length contextual representations. Then, the spatiotemporal trajectory encoding module is introduced to capture the temporal dynamics and spatial structure of UAV trajectories. Finally, to integrate existing spatiotemporal context with current observations, we design the prompt-guided multimodal integration module to support time-based reasoning and robust waypoint prediction. Experimental results demonstrate that LongFly outperforms state-of-the-art UAV VLN baselines by 7.89\% in success rate and 6.33\% in success weighted by path length, consistently across both seen and unseen environments.

cs.CV↗

arXiv2025

The Evolution of Pointwise Statistics in Hyperbolic Equations with Random Data

We consider one-dimensional hyperbolic PDEs, linear and nonlinear, with random initial data. Our focus is the {\em pointwise statistics,} i.e., the probability measure of the solution at any fixed point in space and time. For linear hyperbolic equations, the probability density function (PDF) of these statistics satisfies the same linear PDE. For nonlinear hyperbolic PDEs, we derive a linear transport equation for the cumulative distribution function (CDF) and a nonlocal linear PDE for the PDF. Both results are valid only as long as no shocks have formed, a limitation which is inherent to the problem, as demonstrated by a counterexample. For systems of linear hyperbolic equations, we introduce the multi-point statistics and derive their evolution equations. In all of the settings we consider, the resulting PDEs for the statistics are of practical significance: they enable efficient evaluation of the random dynamics, without requiring an ensemble of solutions of the underlying PDE, and their cost is not affected by the dimension of the random parameter space. Additionally, the evolution equations for the statistics lead to a priori statistical error bounds for Monte Carlo methods (in particular, Kernel Density Estimators) when applied to hyperbolic PDEs with random data.

math.AP↗

arXiv2025

Decoupling Understanding from Reasoning via Problem Space Mapping for Small-Scale Model Reasoning

Despite recent advances in the reasoning capabilities of Large Language Models (LLMs), improving the reasoning ability of Small Language Models (SLMs, e.g., up to 1.5B parameters) remains challenging. A key obstacle lies in the complexity and variability of natural language: essentially equivalent problems often appear in diverse surface forms, often obscured by redundant or distracting details. This imposes a dual burden on SLMs: they must first extract the core problem from complex linguistic input, and then perform reasoning based on that understanding. The resulting vast and noisy problem space hinders optimization, particularly for models with limited capacity. To address this, we propose a new framework that decouples understanding from reasoning by mapping natural language problems into a canonical problem space-a semantically simplified yet expressive domain. This enables SLMs to focus on reasoning over standardized inputs, free from linguistic variability. Within this framework, we introduce DURIT (Decoupled Understanding from Reasoning via Iterative Training), a three-step algorithm that iteratively: (1) mapping natural language problems via reinforcement learning, (2) aligns reasoning trajectories through self-distillation, and (3) trains reasoning policies in the problem space. The mapper and reasoner are co-trained in an alternating loop throughout this process. Experiments show that DURIT substantially improves SLMs' performance on both in-domain and out-of-domain mathematical and logical reasoning tasks. Beyond improving reasoning capabilities, DURIT also improves the robustness of reasoning, validating decoupling understanding from reasoning as an effective strategy for strengthening SLMs.

cs.CL↗

arXiv2025

DFALLM: Achieving Generalizable Multitask Deepfake Detection by Optimizing Audio LLM Components

Audio deepfake detection has recently garnered public concern due to its implications for security and reliability. Traditional deep learning methods have been widely applied to this task but often lack generalisability when confronted with newly emerging spoofing techniques and more tasks such as spoof attribution recognition rather than simple binary classification. In principle, Large Language Models (LLMs) are considered to possess the needed generalisation capabilities. However, previous research on Audio LLMs (ALLMs) indicates a generalization bottleneck in audio deepfake detection performance, even when sufficient data is available. Consequently, this study investigates the model architecture and examines the effects of the primary components of ALLMs, namely the audio encoder and the text-based LLM. Our experiments demonstrate that the careful selection and combination of audio encoders and text-based LLMs are crucial for unlocking the deepfake detection potential of ALLMs. We further propose an ALLM structure capable of generalizing deepfake detection abilities to out-of-domain spoofing tests and other deepfake tasks, such as spoof positioning and spoof attribution recognition. Our proposed model architecture achieves state-of-the-art (SOTA) performance across multiple datasets, including ASVSpoof2019, InTheWild, and Demopage, with accuracy reaching up to 95.76% on average, and exhibits competitive capabilities in other deepfake detection tasks such as attribution, and localisation compared to SOTA audio understanding models. Data and codes are provided in supplementary materials.

cs.SD↗

arXiv2025

Monobricks in extriangulated length categories

In this paper, we introduce the notation of monobricks in an extriangulated length category as a generalization of the semibricks. We prove that there is a bijection between monobricks and left Schur subcategories. Then we show that this bijection restricts to bijection between cofinally closed monobricks and torsion-free classes. These extend the results of Enomoto for abelian length categories.

math.CT↗

arXiv2025

Robust low-rank tensor regression via clipping and Huber loss

In this paper, we construct a parameter estimation framework for robust low-rank tensor regression based on a truncation method and Huber loss, specifically focusing on models with random noise having only finite second-order moments. Through a robust gradient descent method, our proposed Huber-type estimator is theoretically optimal in two aspects: (1) its statistical error rate matches the optimal upper bound established for the traditional least squares method under sub-Gaussian error; and (2) the sample complexity for recovering the tensor parameter is also optimal. Extensive numerical experiments demonstrate the robustness of our estimator, indicating that the utilization of truncation and Huber loss significantly enhances stability and statistical effectiveness, outperforming the traditional least squares method. Additionally, the phenomenon of phase transition in the convergence rate of the proposed estimator is confirmed through simulation. Furthermore, applications to image recovery and the Beijing air-quality dataset demonstrate the practical effectiveness of our method.

math.ST↗

arXiv2025

Bayesian Physics-Informed Neural Networks for Inverse Problems (BPINN-IP): Application in Infrared Image Processing

Inverse problems arise across scientific and engineering domains, where the goal is to infer hidden parameters or physical fields from indirect and noisy observations. Classical approaches, such as variational regularization and Bayesian inference, provide well established theoretical foundations for handling ill posedness. However, these methods often become computationally restrictive in high dimensional settings or when the forward model is governed by complex physics. Physics Informed Neural Networks (PINNs) have recently emerged as a promising framework for solving inverse problems by embedding physical laws directly into the training process of neural networks. In this paper, we introduce a new perspective on the Bayesian Physics Informed Neural Network (BPINN) framework, extending classical PINNs by explicitly incorporating training data generation, modeling and measurement uncertainties through Bayesian prior modeling and doing inference with the posterior laws. Also, as we focus on the inverse problems, we call this method BPINN-IP, and we show that the standard PINN formulation naturally appears as its special case corresponding to the Maximum A Posteriori (MAP) estimate. This unified formulation allows simultaneous exploitation of physical constraints, prior knowledge, and data-driven inference, while enabling uncertainty quantification through posterior distributions. To demonstrate the effectiveness of the proposed framework, we consider inverse problems arising in infrared image processing, including deconvolution and super-resolution, and present results on both simulated and real industrial data.

stat.ML↗

arXiv2025

SpeechJudge: Towards Human-Level Judgment for Speech Naturalness

Aligning large generative models with human feedback is a critical challenge. In speech synthesis, this is particularly pronounced due to the lack of a large-scale human preference dataset, which hinders the development of models that truly align with human perception. To address this, we introduce SpeechJudge, a comprehensive suite comprising a dataset, a benchmark, and a reward model centered on naturalness--one of the most fundamental subjective metrics for speech synthesis. First, we present SpeechJudge-Data, a large-scale human feedback corpus of 99K speech pairs. The dataset is constructed using a diverse set of advanced zero-shot text-to-speech (TTS) models across diverse speech styles and multiple languages, with human annotations for both intelligibility and naturalness preference. From this, we establish SpeechJudge-Eval, a challenging benchmark for speech naturalness judgment. Our evaluation reveals that existing metrics and AudioLLMs struggle with this task; the leading model, Gemini-2.5-Flash, achieves less than 70% agreement with human judgment, highlighting a significant gap for improvement. To bridge this gap, we develop SpeechJudge-GRM, a generative reward model (GRM) based on Qwen2.5-Omni-7B. It is trained on SpeechJudge-Data via a two-stage post-training process: Supervised Fine-Tuning (SFT) with Chain-of-Thought rationales followed by Reinforcement Learning (RL) with GRPO on challenging cases. On the SpeechJudge-Eval benchmark, the proposed SpeechJudge-GRM demonstrates superior performance, achieving 77.2% accuracy (and 79.4% after inference-time scaling @10) compared to a classic Bradley-Terry reward model (72.7%). Furthermore, SpeechJudge-GRM can be also employed as a reward function during the post-training of speech generation models to facilitate their alignment with human preferences.

cs.SD↗

arXiv2025

KOM: A Multi-Agent Artificial Intelligence System for Precision Management of Knee Osteoarthritis (KOA)

Knee osteoarthritis (KOA) affects more than 600 million individuals globally and is associated with significant pain, functional impairment, and disability. While personalized multidisciplinary interventions have the potential to slow disease progression and enhance quality of life, they typically require substantial medical resources and expertise, making them difficult to implement in resource-limited settings. To address this challenge, we developed KOM, a multi-agent system designed to automate KOA evaluation, risk prediction, and treatment prescription. This system assists clinicians in performing essential tasks across the KOA care pathway and supports the generation of tailored management plans based on individual patient profiles, disease status, risk factors, and contraindications. In benchmark experiments, KOM demonstrated superior performance compared to several general-purpose large language models in imaging analysis and prescription generation. A randomized three-arm simulation study further revealed that collaboration between KOM and clinicians reduced total diagnostic and planning time by 38.5% and resulted in improved treatment quality compared to each approach used independently. These findings indicate that KOM could help facilitate automated KOA management and, when integrated into clinical workflows, has the potential to enhance care efficiency. The modular architecture of KOM may also offer valuable insights for developing AI-assisted management systems for other chronic conditions.

cs.AI↗

arXiv2025

Sketch2PoseNet: Efficient and Generalized Sketch to 3D Human Pose Prediction

3D human pose estimation from sketches has broad applications in computer animation and film production. Unlike traditional human pose estimation, this task presents unique challenges due to the abstract and disproportionate nature of sketches. Previous sketch-to-pose methods, constrained by the lack of large-scale sketch-3D pose annotations, primarily relied on optimization with heuristic rules-an approach that is both time-consuming and limited in generalizability. To address these challenges, we propose a novel approach leveraging a "learn from synthesis" strategy. First, a diffusion model is trained to synthesize sketch images from 2D poses projected from 3D human poses, mimicking disproportionate human structures in sketches. This process enables the creation of a synthetic dataset, SKEP-120K, consisting of 120k accurate sketch-3D pose annotation pairs across various sketch styles. Building on this synthetic dataset, we introduce an end-to-end data-driven framework for estimating human poses and shapes from diverse sketch styles. Our framework combines existing 2D pose detectors and generative diffusion priors for sketch feature extraction with a feed-forward neural network for efficient 2D pose estimation. Multiple heuristic loss functions are incorporated to guarantee geometric coherence between the derived 3D poses and the detected 2D poses while preserving accurate self-contacts. Qualitative, quantitative, and subjective evaluations collectively show that our model substantially surpasses previous ones in both estimation accuracy and speed for sketch-to-pose tasks.

cs.CV↗

arXiv2025

CrossRay3D: Geometry and Distribution Guidance for Efficient Multimodal 3D Detection

The sparse cross-modality detector offers more advantages than its counterpart, the Bird's-Eye-View (BEV) detector, particularly in terms of adaptability for downstream tasks and computational cost savings. However, existing sparse detectors overlook the quality of token representation, leaving it with a sub-optimal foreground quality and limited performance. In this paper, we identify that the geometric structure preserved and the class distribution are the key to improving the performance of the sparse detector, and propose a Sparse Selector (SS). The core module of SS is Ray-Aware Supervision (RAS), which preserves rich geometric information during the training stage, and Class-Balanced Supervision, which adaptively reweights the salience of class semantics, ensuring that tokens associated with small objects are retained during token sampling. Thereby, outperforming other sparse multi-modal detectors in the representation of tokens. Additionally, we design Ray Positional Encoding (Ray PE) to address the distribution differences between the LiDAR modality and the image. Finally, we integrate the aforementioned module into an end-to-end sparse multi-modality detector, dubbed CrossRay3D. Experiments show that, on the challenging nuScenes benchmark, CrossRay3D achieves state-of-the-art performance with 72.4 mAP and 74.7 NDS, while running 1.84 faster than other leading methods. Moreover, CrossRay3D demonstrates strong robustness even in scenarios where LiDAR or camera data are partially or entirely missing.

cs.CV↗

arXiv2025

Perturbation Function Iteration Method: A New Framework for Solving Periodic Solutions of Non-linear and Non-smooth Systems

Computing accurate periodic responses in strongly nonlinear or even non-smooth vibration systems remains a fundamental challenge in nonlinear dynamics. Existing numerical methods, such as the Harmonic Balance Method (HBM) and the Shooting Method (SM), have achieved notable success but face intrinsic limitations when applied to complex, high-dimensional, or non-smooth systems. A key bottleneck is the construction of Jacobian matrices for the associated algebraic equations; although numerical approximations can avoid explicit analytical derivation, they become unreliable and computationally expensive for large-scale or non-smooth problems. To overcome these challenges, this study proposes the Perturbation Function Iteration Method (PFIM), a novel framework built upon perturbation theory. PFIM transforms nonlinear equations into time-varying linear systems and solves their periodic responses via a piecewise constant approximation scheme. Unlike HBM, PFIM avoids the trade-off between Fourier truncation errors and the Gibbs phenomenon in non-smooth problems by employing a basis-free iterative formulation, while significantly simplifying the Jacobian computation. Extensive numerical studies, including self-excited systems, parameter continuation, systems with varying smoothness, and high-dimensional finite element models, demonstrate that PFIM achieves quadratic convergence in smooth systems and maintains robust linear convergence in highly non-smooth cases. Moreover, comparative analyses show that, for high-dimensional non-smooth systems, PFIM attains solutions of comparable accuracy with computational costs up to two orders of magnitude lower than HBM. These results indicate that PFIM provides a robust and efficient alternative for periodic response analysis in complex nonlinear dynamical systems, with strong potential for practical engineering applications.

math.NA↗

arXiv2025

Existence and multiplicity results for the zero mass Schrödinger-Bopp-Podolsky system with critical growth

In this paper we study the following zero mass Schrödinger-Bopp-Podolsky system with critical growth \[ \begin{cases} -Δu +q^2ϕu=μ|u|^{p-2}u+|u|^4u\\ -Δϕ+a^2Δ^2ϕ=4πu^2, \end{cases} \] where $a>0$, $q\neq0$, $μ>0$ is a parameter and $p\in(3,6)$. By introducing a new functional framework developed by Caponio et al. \cite{Cd}, we first establish the existence of positive ground state solutions for the case of $p\in(3,6)$. Moreover, for the case of $p\in(4,6)$, multiplicity results are obtained by applying an abstract critical point theorem due to Perera \cite{Pe}.

math.AP↗

arXiv2025

Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning

In cooperative Multi-Agent Reinforcement Learning (MARL), it is a common practice to tune hyperparameters in ideal simulated environments to maximize cooperative performance. However, policies tuned for cooperation often fail to maintain robustness and resilience under real-world uncertainties. Building trustworthy MARL systems requires a deep understanding of robustness, which ensures stability under uncertainties, and resilience, the ability to recover from disruptions--a concept extensively studied in control systems but largely overlooked in MARL. In this paper, we present a large-scale empirical study comprising over 82,620 experiments to evaluate cooperation, robustness, and resilience in MARL across 4 real-world environments, 13 uncertainty types, and 15 hyperparameters. Our key findings are: (1) Under mild uncertainty, optimizing cooperation improves robustness and resilience, but this link weakens as perturbations intensify. Robustness and resilience also varies by algorithm and uncertainty type. (2) Robustness and resilience do not generalize across uncertainty modalities or agent scopes: policies robust to action noise for all agents may fail under observation noise on a single agent. (3) Hyperparameter tuning is critical for trustworthy MARL: surprisingly, standard practices like parameter sharing, GAE, and PopArt can hurt robustness, while early stopping, high critic learning rates, and Leaky ReLU consistently help. By optimizing hyperparameters only, we observe substantial improvement in cooperation, robustness and resilience across all MARL backbones, with the phenomenon also generalizing to robust MARL methods across these backbones. Code and results available at https://github.com/BUAA-TrustworthyMARL/adv_marl_benchmark .

cs.MA↗

arXiv2025

Cluster-wise processing in fronthaul-aware cell-free massive MIMO systems

We exploit a general cluster-based network architecture for a fronthaul-limited user-centric cell-free massive multiple-input multiple-output (CF-mMIMO) system under different degrees of cooperation among the access points (APs) to achieve scalable implementation. In particular, we consider a CF-mMIMO system wherein the available APs are grouped into multiple processing clusters (PCs) to share channel state information (CSI), ensuring that they have knowledge of the CSI for all users assigned to the given cluster for the purposes of designing resource allocation and precoding. We utilize the sum pseudo-SE metric, which accounts for intra-cluster interference and intercluster-leakage, providing a close approximation to the true sum achievable SE. For a given PC, we formulate two optimization problems to maximize the cluster-wise weighted sum pseudo-SE under fronthaul constraints, relying solely on local CSI. These optimization problems are associated with different computational complexity requirements. The first optimization problem jointly designs precoding, user association, and power allocation, and is performed at the small-scale fading time scale. The second optimization problem optimizes user association and power allocation at the large-scale fading time scale. Accordingly, we develop a novel application of modified weighted minimum mean square error (WMMSE)-based approach to solve the challenging formulated non-convex mixed-integer problems.

cs.IT↗

arXiv2025

The constraints on the stochastic gravitational wave background from cosmic strings by an electromagnetic resonance system

As one of the primary detection targets for contemporary gravitational wave (GW) observatories, the stochastic gravitational wave background (SGWB) holds significant potential for enhancing our understanding of the early universe's formation and evolution. Studies indicate that the SGWB spectrum from cosmic strings can span an extraordinarily broad frequency range, extending from extremely low frequencies up to the microwave band. This work specifically investigates the detectability of cosmic string SGWB signals in an electromagnetic (EM) resonance system at GHz frequency. We present a systematic analysis encompassing: (1) the response of high frequency gravitational waves (HFGWs) in such EM resonance system. (2) the development and application of fundamental data processing protocols in the EM resonance system. Our results demonstrate that the EM system shows promising sensitivity to detect cosmic string SGWB signals with tension parameters $Gμ\geq 10^{-11}$ (the corresponding dimensionless amplitude $h \geq 10^{-33}$ at 1 GHz), while potentially establishing new constraints for $Gμ\leq 10^{-11}$ in the microwave band. These findings would complement existing multi-band SGWB observations and provide additional constraints on cosmic-string tension parameters in GHz frequency regimes.

gr-qc↗

arXiv2025

Determining nonlinear balance laws in product-type domains by a single local passive boundary observation

This paper introduces an operator-theoretic paradigm for solving inverse problems in nonlinear balance laws, shifting the focus from identifying specific functional forms to recovering the input-output actions of the associated flux and source operators. It is established that a single local passive boundary observation suffices to uniquely determine realizations of these operators for systems posed on product-type domains. This framework, which encompasses dynamical regimes, reveals a holographic-type principle where macroscopic boundary data encodes microscopic dynamical information, with broad implications for fluid dynamics and reaction-diffusion systems.

math.AP↗