arXiv subjects

Wei Ma

Publications and source records attributed to Wei Ma.

At least 55 records · Page 3Linked to original sources

arXiv2025

SPO-VCS: An End-to-End Smart Predict-then-Optimize Framework with Alternating Differentiation Method for Relocation Problems in Large-Scale Vehicle Crowd Sensing

Ubiquitous mobile devices have catalyzed the development of vehicle crowd sensing (VCS). In particular, vehicle sensing systems show great potential in the flexible acquisition of spatio-temporal urban data through built-in sensors under diverse sensing scenarios. However, vehicle systems often exhibit biased coverage due to the heterogeneous nature of trip requests and routes. To achieve a high sensing coverage, a critical challenge lies in optimally relocating vehicles to minimize the divergence between vehicle distributions and target sensing distributions. Conventional approaches typically employ a two-stage predict-then-optimize (PTO) process: first predicting real-time vehicle distributions and subsequently generating an optimal relocation strategy based on the predictions. However, this approach can lead to suboptimal decision-making due to the propagation of errors from upstream prediction. To this end, we develop an end-to-end Smart Predict-then-Optimize (SPO) framework by integrating optimization into prediction within the deep learning architecture, and the entire framework is trained by minimizing the task-specific matching divergence rather than the upstream prediction error. Methodologically, we formulate the vehicle relocation problem by quadratic programming (QP) and incorporate a novel unrolling approach based on the Alternating Direction Method of Multipliers (ADMM) within the SPO framework to compute gradients of the QP layer, facilitating backpropagation and gradient-based optimization for end-to-end learning. The effectiveness of the proposed framework is validated by real-world taxi datasets in Hong Kong. Utilizing the alternating differentiation method, the general SPO framework presents a novel concept of addressing decision-making problems with uncertainty, demonstrating significant potential for advancing applications in intelligent transportation systems.

cs.LG↗

arXiv2025

Collaborating Unmanned Aerial Vehicle and Ground Sensors for Urban Signalized Network Traffic Monitoring

Reliable estimation of network-wide traffic states is essential for urban traffic management. Unmanned Aerial Vehicles (UAVs), with their airborne full-sample continuous trajectory observation, bring new opportunities for traffic state estimation. In this study, we will explore the optimal UAV deployment problem in road networks in conjunction with ground sensors, including connected vehicle (CV) and loop detectors, to achieve more reliable estimation of vehicle path reconstruction as well as movement-based arrival rates and queue lengths. Oriented towards reliable estimation of traffic states, we propose an index, feasible domain size, as the uncertainty measurement, and transform the optimal UAV deployment problem into minimizing the observation uncertainty of network-wide traffic states. Given the large-scale and nonlinear nature of the problem, an improved quantum genetic algorithm (IQGA) that integrates two customized operators is proposed to enhance neighbor searching and solution refinement, thereby improving the observability of UAV pairs. Evaluation was conducted on an empirical network with 18 intersections. Results demonstrated that a UAV fleet size of 7 is sufficient for traffic monitoring, with more than 60\% of network-wide observation uncertainty reduced. Through horizontal comparison with three baselines, the optimal UAV location scheme obtained by the proposed method can reach an improvement of up to 7.23\% and 5.02\% in the estimation accuracy of arrival rate and queue length, respectively. The proposed IQGA is also shown to be faster in solution convergence than the classic QGA by about 9.22\% with better exploration ability in optimum searching.

math.OC↗

arXiv2025

Estimating Real Demand Using a Flipped Queueing Model: A Case of Shared Micro-Mobility Services

The spatial-temporal imbalance between supply and demand in shared micro-mobility services often leads to observed demand being censored, resulting in incomplete records of the underlying real demand. This phenomenon undermines the reliability of the collected demand data and hampers downstream applications such as demand forecasting, fleet management, and micro-mobility planning. How to accurately estimate the real demand is challenging and has not been well explored in existing studies. In view of this, we contribute to real demand estimation for shared micro-mobility services by proposing an analytical method that rigorously derives the real demand under appropriate assumptions. Rather than directly modeling the intractable relationship between observed demand and real demand, we propose a novel random variable, Generalized Vehicle Survival Time (GVST), which is observable from trip records. The relationship between GVST and real demand is characterized by introducing a flipped queueing model (FQM) that captures the operational dynamics of shared micro-mobility services. Specifically, the distribution of GVST is derived within the FQM, which allows the real demand estimation problem to be transformed into an inverse queueing problem. We analytically derive the real demand in closed form using a one-sided estimation method, and solve the problem by a system of equations in a two-sided estimation method. We validate the proposed methods using synthetic data and conduct empirical analyses using real-world datasets from bike-sharing and shared e-scooter systems. The experimental results show that both the two-sided and one-sided methods outperform benchmark models. In particular, the one-sided approach provides a closed-form solution that delivers acceptable accuracy, constituting a practical rule of thumb for demand-related analytics and decision-making processes.

stat.AP↗

arXiv2025

Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Spatial Reasoning

Vision language models (VLMs) perform well on many tasks but often fail at spatial reasoning, which is essential for navigation and interaction with physical environments. Many spatial reasoning tasks depend on fundamental two-dimensional (2D) skills, yet our evaluation shows that state-of-the-art VLMs give implausible or incorrect answers to composite spatial problems, including simple pathfinding tasks that humans solve effortlessly. To address this, we enhance 2D spatial reasoning in VLMs by training them only on basic spatial capabilities. We first disentangle 2D spatial reasoning into three core components: direction comprehension, distance estimation, and localization. We hypothesize that mastering these skills substantially improves performance on complex spatial tasks that require advanced reasoning and combinatorial problem solving, while also generalizing to real-world scenarios. To test this, we introduce Sparkle, a framework that generates synthetic data to provide targeted supervision across these three capabilities and yields an instruction dataset for each. Experiments show that VLMs fine-tuned with \emph{Sparkle} improve not only on basic tasks but also on composite and out-of-distribution real-world spatial reasoning tasks. These results indicate that enhancing basic spatial skills through synthetic generalization effectively advances complex spatial reasoning and offers a systematic strategy for boosting the spatial understanding of VLMs. Source codes of Sparkle are available at https://github.com/YihongT/Sparkle.

cs.CV↗

arXiv2025

Multi-level Dynamic Style Transfer for NeRFs

As the application of neural radiance fields (NeRFs) in various 3D vision tasks continues to expand, numerous NeRF-based style transfer techniques have been developed. However, existing methods typically integrate style statistics into the original NeRF pipeline, often leading to suboptimal results in both content preservation and artistic stylization. In this paper, we present multi-level dynamic style transfer for NeRFs (MDS-NeRF), a novel approach that reengineers the NeRF pipeline specifically for stylization and incorporates an innovative dynamic style injection module. Particularly, we propose a multi-level feature adaptor that helps generate a multi-level feature grid representation from the content radiance field, effectively capturing the multi-scale spatial structure of the scene. In addition, we present a dynamic style injection module that learns to extract relevant style features and adaptively integrates them into the content patterns. The stylized multi-level features are then transformed into the final stylized view through our proposed multi-level cascade decoder. Furthermore, we extend our 3D style transfer method to support omni-view style transfer using 3D style references. Extensive experiments demonstrate that MDS-NeRF achieves outstanding performance for 3D style transfer, preserving multi-scale spatial structures while effectively transferring stylistic characteristics.

cs.CV↗

arXiv2025

Enhancing Crash Frequency Modeling Based on Augmented Multi-Type Data by Hybrid VAE-Diffusion-Based Generative Neural Networks

Crash frequency modelling analyzes the impact of factors like traffic volume, road geometry, and environmental conditions on crash occurrences. Inaccurate predictions can distort our understanding of these factors, leading to misguided policies and wasted resources, which jeopardize traffic safety. A key challenge in crash frequency modelling is the prevalence of excessive zero observations, caused by underreporting, the low probability of crashes, and high data collection costs. These zero observations often reduce model accuracy and introduce bias, complicating safety decision making. While existing approaches, such as statistical methods, data aggregation, and resampling, attempt to address this issue, they either rely on restrictive assumptions or result in significant information loss, distorting crash data. To overcome these limitations, we propose a hybrid VAE-Diffusion neural network, designed to reduce zero observations and handle the complexities of multi-type tabular crash data (count, ordinal, nominal, and real-valued variables). We assess the synthetic data quality generated by this model through metrics like similarity, accuracy, diversity, and structural consistency, and compare its predictive performance against traditional statistical models. Our findings demonstrate that the hybrid VAE-Diffusion model outperforms baseline models across all metrics, offering a more effective approach to augmenting crash data and improving the accuracy of crash frequency predictions. This study highlights the potential of synthetic data to enhance traffic safety by improving crash frequency modelling and informing better policy decisions.

cs.AI↗

arXiv2025

TrueMoE: Dual-Routing Mixture of Discriminative Experts for Synthetic Image Detection

The rapid progress of generative models has made synthetic image detection an increasingly critical task. Most existing approaches attempt to construct a single, universal discriminative space to separate real from fake content. However, such unified spaces tend to be complex and brittle, often struggling to generalize to unseen generative patterns. In this work, we propose TrueMoE, a novel dual-routing Mixture-of-Discriminative-Experts framework that reformulates the detection task as a collaborative inference across multiple specialized and lightweight discriminative subspaces. At the core of TrueMoE is a Discriminative Expert Array (DEA) organized along complementary axes of manifold structure and perceptual granularity, enabling diverse forgery cues to be captured across subspaces. A dual-routing mechanism, comprising a granularity-aware sparse router and a manifold-aware dense router, adaptively assigns input images to the most relevant experts. Extensive experiments across a wide spectrum of generative models demonstrate that TrueMoE achieves superior generalization and robustness.

cs.CV↗

arXiv2025

Prompt Stability in Code LLMs: Measuring Sensitivity across Emotion- and Personality-Driven Variations

Code generation models are widely used in software development, yet their sensitivity to prompt phrasing remains under-examined. Identical requirements expressed with different emotions or communication styles can yield divergent outputs, while most benchmarks emphasize only peak performance. We present PromptSE (Prompt Sensitivity Evaluation), a framework that creates semantically equivalent prompt variants with emotion and personality templates, and that evaluates stability using probability aware continuous scoring or using binary pass rates when logits are unavailable. The results are aggregated into a proposed area under curve metric (AUC-E) for cross model comparison. Across 14 models from three families (Llama, Qwen, and DeepSeek), our study shows that performance and stability behave as largely decoupled optimization objectives, and it reveals architectural and scale related patterns that challenge common assumptions about model robustness. The framework supports rapid screening for closed-source models as well as detailed stability analysis in research settings. PromptSE enables practitioners to quantify performance stability trade offs for deployment and model selection, positioning prompt stability as a complementary evaluation dimension alongside performance and fairness, and contributing to more trustworthy AI-assisted software development tools.

cs.SE↗

arXiv2025

VulnRepairEval: An Exploit-Based Evaluation Framework for Assessing Large Language Model Vulnerability Repair Capabilities

The adoption of Large Language Models (LLMs) for automated software vulnerability patching has shown promising outcomes on carefully curated evaluation sets. Nevertheless, existing datasets predominantly rely on superficial validation methods rather than exploit-based verification, leading to overestimated performance in security-sensitive applications. This paper introduces VulnRepairEval, an evaluation framework anchored in functional Proof-of-Concept (PoC) exploits. Our framework delivers a comprehensive, containerized evaluation pipeline that enables reproducible differential assessment, where repair success requires the original exploit to fail execution against the modified code. The benchmark construction involved extensive data curation: we processed over 400 CVEs and approximately 2,500 potential sources to extract a collection of authentic vulnerability instances (23 Python CVEs) amenable to automated testing with working PoCs. Through VulnRepairEval, we conduct a comprehensive evaluation of 12 popular LLMs and observe a significant performance deficit: even the top-performing model successfully addresses merely 5/23 instances (about 21.7%), exposing critical weaknesses in security-focused applications. Our failure analysis reveals that most unsuccessful attempts stem from imprecise vulnerability identification and patches containing syntactic or semantic errors. Enhanced prompting strategies and multi-agent approaches yield minimal improvements, with overall effectiveness remaining largely unaffected. This work contributes a stringent, practical evaluation framework for LLM-driven vulnerability remediation and underscores the necessity for assessment protocols that authentically reflect real-world exploitation scenarios.

cs.SE↗

arXiv2025

CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter Physics

We introduce CMPhysBench, designed to assess the proficiency of Large Language Models (LLMs) in Condensed Matter Physics, as a novel Benchmark. CMPhysBench is composed of more than 520 graduate-level meticulously curated questions covering both representative subfields and foundational theoretical frameworks of condensed matter physics, such as magnetism, superconductivity, strongly correlated systems, etc. To ensure a deep understanding of the problem-solving process,we focus exclusively on calculation problems, requiring LLMs to independently generate comprehensive solutions. Meanwhile, leveraging tree-based representations of expressions, we introduce the Scalable Expression Edit Distance (SEED) score, which provides fine-grained (non-binary) partial credit and yields a more accurate assessment of similarity between prediction and ground-truth. Our results show that even the best models, Grok-4, reach only 36 average SEED score and 28% accuracy on CMPhysBench, underscoring a significant capability gap, especially for this practical and frontier domain relative to traditional physics. The code anddataset are publicly available at https://github.com/CMPhysBench/CMPhysBench.

cs.LG↗

arXiv2025

Rethinking Testing for LLM Applications: Characteristics, Challenges, and a Lightweight Interaction Protocol

Applications of Large Language Models~(LLMs) have evolved from simple text generators into complex software systems that integrate retrieval augmentation, tool invocation, and multi-turn interactions. Their inherent non-determinism, dynamism, and context dependence pose fundamental challenges for quality assurance. This paper decomposes LLM applications into a three-layer architecture: \textbf{\textit{System Shell Layer}}, \textbf{\textit{Prompt Orchestration Layer}}, and \textbf{\textit{LLM Inference Core}}. We then assess the applicability of traditional software testing methods in each layer: directly applicable at the shell layer, requiring semantic reinterpretation at the orchestration layer, and necessitating paradigm shifts at the inference core. A comparative analysis of Testing AI methods from the software engineering community and safety analysis techniques from the AI community reveals structural disconnects in testing unit abstraction, evaluation metrics, and lifecycle management. We identify four fundamental differences that underlie 6 core challenges. To address these, we propose four types of collaborative strategies (\emph{Retain}, \emph{Translate}, \emph{Integrate}, and \emph{Runtime}) and explore a closed-loop, trustworthy quality assurance framework that combines pre-deployment validation with runtime monitoring. Based on these strategies, we offer practical guidance and a protocol proposal to support the standardization and tooling of LLM application testing. We propose a protocol \textbf{\textit{Agent Interaction Communication Language}} (AICL) that is used to communicate between AI agents. AICL has the test-oriented features and is easily integrated in the current agent framework.

cs.SE↗

arXiv2025

Random Discounting and Assessment of Intertemporal Projects: a Non-expected Utility Approach

This paper assumes each individual in society has a random discount factor and assesses an intertemporal project using rank-dependent expected utility theory. We consider both the ex ante and the ex post approaches. For the former, we show the social planner's discount factor is a convex combination of those of the individuals under the standard Pareto condition. For the latter, we propose a method for determining the social planner's discount factor distribution from the individuals' distributions, which are possibly heterogenous. We demonstrate that relative to expected utility, overweighing of small probabilities can substantially accelerate the decline of the social discount rate.

econ.TH↗

arXiv2025

Optimal Brain Connection: Towards Efficient Structural Pruning

Structural pruning has been widely studied for its effectiveness in compressing neural networks. However, existing methods often neglect the interconnections among parameters. To address this limitation, this paper proposes a structural pruning framework termed Optimal Brain Connection. First, we introduce the Jacobian Criterion, a first-order metric for evaluating the saliency of structural parameters. Unlike existing first-order methods that assess parameters in isolation, our criterion explicitly captures both intra-component interactions and inter-layer dependencies. Second, we propose the Equivalent Pruning mechanism, which utilizes autoencoders to retain the contributions of all original connection--including pruned ones--during fine-tuning. Experimental results demonstrate that the Jacobian Criterion outperforms several popular metrics in preserving model performance, while the Equivalent Pruning mechanism effectively mitigates performance degradation after fine-tuning. Code: https://github.com/ShaowuChen/Optimal_Brain_Connection

cs.CV↗

arXiv2025

Importance Sampling is All You Need: Predict LLM's performance on new benchmark by reusing existing benchmark

With the rapid advancement of large language models , code generation has become a key benchmark for evaluating LLM capabilities. However, existing benchmarks face two major challenges: (1) the escalating cost of constructing high-quality test suites and reference solutions, and (2) the increasing risk of data contamination, which undermines the reliability of benchmark-based evaluations. In this paper, we propose BIS, a prompt-centric evaluation framework that enables ground-truth-free prediction of LLM performance on code generation tasks. Rather than executing generated code, BIS estimates performance metrics by analyzing the prompt distribution alone. Built on importance sampling theory and implemented using Importance Weighted Autoencoders, our method reweights samples from existing annotated benchmarks to estimate performance on new, unseen benchmarks. To stabilize the estimation, we introduce weight truncation strategies and compute marginal expectations across the fitted distributions. BIS serves as a complementary tool that supports benchmark development and validation under constrained resources, offering actionable and quick feedback for prompt selection and contamination assessment. We conduct extensive experiments involving 8,000 evaluation points across 4 CodeLlama models and 9 diverse benchmarks. Our framework achieves an average absolute prediction error of 1.1% for code correctness scores, with best- and worst-case errors of 0.3% and 1.9%, respectively. It also generalizes well to other metrics, attaining average absolute errors of 2.15% for pass@1. These results demonstrate the reliability and broad applicability of BIS, which can significantly reduce the cost and effort of benchmarking LLMs in code-related tasks.

cs.AI↗

arXiv2025

Predicting Large-scale Urban Network Dynamics with Energy-informed Graph Neural Diffusion

Networked urban systems facilitate the flow of people, resources, and services, and are essential for economic and social interactions. These systems often involve complex processes with unknown governing rules, observed by sensor-based time series. To aid decision-making in industrial and engineering contexts, data-driven predictive models are used to forecast spatiotemporal dynamics of urban systems. Current models such as graph neural networks have shown promise but face a trade-off between efficacy and efficiency due to computational demands. Hence, their applications in large-scale networks still require further efforts. This paper addresses this trade-off challenge by drawing inspiration from physical laws to inform essential model designs that align with fundamental principles and avoid architectural redundancy. By understanding both micro- and macro-processes, we present a principled interpretable neural diffusion scheme based on Transformer-like structures whose attention layers are induced by low-dimensional embeddings. The proposed scalable spatiotemporal Transformer (ScaleSTF), with linear complexity, is validated on large-scale urban systems including traffic flow, solar power, and smart meters, showing state-of-the-art performance and remarkable scalability. Our results constitute a fresh perspective on the dynamics prediction in large-scale urban networks.

cs.LG↗

arXiv2025

Hot-Swap MarkBoard: An Efficient Black-box Watermarking Approach for Large-scale Model Distribution

Recently, Deep Learning (DL) models have been increasingly deployed on end-user devices as On-Device AI, offering improved efficiency and privacy. However, this deployment trend poses more serious Intellectual Property (IP) risks, as models are distributed on numerous local devices, making them vulnerable to theft and redistribution. Most existing ownership protection solutions (e.g., backdoor-based watermarking) are designed for cloud-based AI-as-a-Service (AIaaS) and are not directly applicable to large-scale distribution scenarios, where each user-specific model instance must carry a unique watermark. These methods typically embed a fixed watermark, and modifying the embedded watermark requires retraining the model. To address these challenges, we propose Hot-Swap MarkBoard, an efficient watermarking method. It encodes user-specific $n$-bit binary signatures by independently embedding multiple watermarks into a multi-branch Low-Rank Adaptation (LoRA) module, enabling efficient watermark customization without retraining through branch swapping. A parameter obfuscation mechanism further entangles the watermark weights with those of the base model, preventing removal without degrading model performance. The method supports black-box verification and is compatible with various model architectures and DL tasks, including classification, image generation, and text generation. Extensive experiments across three types of tasks and six backbone models demonstrate our method's superior efficiency and adaptability compared to existing approaches, achieving 100\% verification accuracy.

cs.CR↗

arXiv2025

Lossless, Non-Volatile Post-Fabrication Trimming of PICs via On-Chip High-Temperature Annealing of Undercut Waveguides

Limited by equipment precision, manufacturing deviations in waveguide width, etch depth, and layer thickness inevitably occur in photonic integrated circuits (PICs). These variations cause initial phase errors, compromising the reliability of phase-sensitive devices such as Mach-Zehnder Interferometers (MZI) and microring resonators. To overcome this, we report a nonvolatile, near-lossless post-trimming method utilizing sufficient high-temperature thermal treatment for undercut waveguides, reported here for the first time to the best of our knowledge. This CMOS-compatible approach requires no additional processes or equipment, enables simple electrical heating for trimming, and retains long-term stability after high-temperature removal, ensuring high energy efficiency. Transmission electron microscopy indicates that high-temperature thermal treatment induces irreversible lattice expansion in silicon waveguides, leading to a reduction in the real refractive index and enabling compensation for process errors. Experimental results using MZIs confirm a permanent refractive index reduction of 0.0173 and high-resolution tuning up to 5.25 bits, effective across a broadband spectrum and stable for over 218 days after final trimming. Furthermore, 15 MZIs on a single wafer are precisely calibrated to BAR, CROSS, or orthogonal states, demonstrating the method universality. This practical and scalable technique enables reliable post-fabrication trimming for next-generation low-cost, energy-efficient PIC applications such as optical switches and optical computing.

physics.optics↗

arXiv2025

Relativistic quantum mechanics of charged vortex particles accelerated in a uniform electric field

The relativistic quantum-mechanical description of a charged Laguerre-Gauss beam accelerated in a uniform electric field has been fulfilled. Stationary wave eigenfunctions are rigorously derived. The evolution of the beam parameters during acceleration is considered in detail. The practically important effect of extraordinary suppression of transverse spreading of the beam is discovered, carefully analyzed, and properly explained. Our results provide direct evidence that vortex particle beams can be accelerated without destroying their intrinsic vortex properties, paving the way for high-energy vortex beam applications.

physics.acc-ph↗