arXiv subjects

Wang Chen

Publications and source records attributed to Wang Chen.

At least 37 records · Page 2Linked to original sources

arXiv2025

Low Rank Support Quaternion Matrix Machine

Input features are conventionally represented as vectors, matrices, or third order tensors in the real field, for color image classification. Inspired by the success of quaternion data modeling for color images in image recovery and denoising tasks, we propose a novel classification method for color image classification, named as the Low-rank Support Quaternion Matrix Machine (LSQMM), in which the RGB channels are treated as pure quaternions to effectively preserve the intrinsic coupling relationships among channels via the quaternion algebra. For the purpose of promoting low-rank structures resulting from strongly correlated color channels, a quaternion nuclear norm regularization term, serving as a natural extension of the conventional matrix nuclear norm to the quaternion domain, is added to the hinge loss in our LSQMM model. An Alternating Direction Method of Multipliers (ADMM)-based iterative algorithm is designed to effectively resolve the proposed quaternion optimization model. Experimental results on multiple color image classification datasets demonstrate that our proposed classification approach exhibits advantages in classification accuracy, robustness and computational efficiency, compared to several state-of-the-art methods using support vector machines, support matrix machines, and support tensor machines.

cs.CV↗

arXiv2025

Unveiling Uniform Shifted Power Law in Stochastic Human and Autonomous Driving Behavior

Accurately simulating rare but safety-critical driving behaviors is essential for the evaluation and certification of autonomous vehicles (AVs). However, current models often fail to reproduce realistic collision rates when calibrated on real-world data, largely due to inadequate representation of long-tailed behavioral distributions. Here, we uncover a simple yet unifying shifted power law that robustly characterizes the stochasticity of both human-driven vehicle (HV) and AV behaviors, especially in the long-tail regime. The model adopts a parsimonious analytical form with only one or two parameters, enabling efficient calibration even under data sparsity. Analyzing large-scale, micro-level trajectory data from global HV and AV datasets, the shifted power law achieves an average R2 of 0.97 and a nearly identical tail distribution, uniformly fits both frequent behaviors and rare safety-critical deviations, significantly outperforming existing Gaussian-based baselines. When integrated into an agent-based traffic simulator, it enables forward-rolling simulations that reproduce realistic crash patterns for both HVs and AVs, achieving rates consistent with real-world statistics and improving the fidelity of safety assessment without post hoc correction. This discovery offers a unified and data-efficient foundation for modeling high-risk behavior and improves the fidelity of simulation-based safety assessments for mixed AV/HV traffic. The shifted power law provides a promising path toward simulation-driven validation and global certification of AV technologies.

eess.SY↗

arXiv2025

SMART: Scalable Multi-Agent Reasoning and Trajectory Planning in Dense Environments

Multi-vehicle trajectory planning is a non-convex problem that becomes increasingly difficult in dense environments due to the rapid growth of collision constraints. Efficient exploration of feasible behaviors and resolution of tight interactions are essential for real-time, large-scale coordination. This paper introduces SMART, Scalable Multi-Agent Reasoning and Trajectory Planning, a hierarchical framework that combines priority-based search with distributed optimization to achieve efficient and feasible multi-vehicle planning. The upper layer explores diverse interaction modes using reinforcement learning-based priority estimation and large-step hybrid A* search, while the lower layer refines solutions via parallelizable convex optimization. By partitioning space among neighboring vehicles and constructing robust feasible corridors, the method decouples the joint non-convex problem into convex subproblems solved efficiently in parallel. This design alleviates the step-size trade-off while ensuring kinematic feasibility and collision avoidance. Experiments show that SMART consistently outperforms baselines. On 50 m x 50 m maps, it sustains over 90% success within 1 s up to 25 vehicles, while baselines often drop below 50%. On 100 m x 100 m maps, SMART achieves above 95% success up to 50 vehicles and remains feasible up to 90 vehicles, with runtimes more than an order of magnitude faster than optimization-only approaches. Built on vehicle-to-everything communication, SMART incorporates vehicle-infrastructure cooperation through roadside sensing and agent coordination, improving scalability and safety. Real-world experiments further validate this design, achieving planning times as low as 0.014 s while preserving cooperative behaviors.

cs.RO↗

arXiv2025

Theory Foundation of Physics-Enhanced Residual Learning

Intensive studies have been conducted in recent years to integrate neural networks with physics models to balance model accuracy and interpretability. One recently proposed approach, named Physics-Enhanced Residual Learning (PERL), is to use learning to estimate the residual between the physics model prediction and the ground truth. Numeral examples suggested that integrating such residual with physics models in PERL has three advantages: (1) a reduction in the number of required neural network parameters; (2) faster convergence rates; and (3) fewer training samples needed for the same computational precision. However, these numerical results lack theoretical justification and cannot be adequately explained. This paper aims to explain these advantages of PERL from a theoretical perspective. We investigate a general class of problems with Lipschitz continuity properties. By examining the relationships between the bounds to the loss function and residual learning structure, this study rigorously proves a set of theorems explaining the three advantages of PERL. Several numerical examples in the context of automated vehicle trajectory prediction are conducted to illustrate the proposed theorems. The results confirm that, even with significantly fewer training samples, PERL consistently achieves higher accuracy than a pure neural network. These results demonstrate the practical value of PERL in real world autonomous driving applications where corner case data are costly or hard to obtain. PERL therefore improves predictive performance while reducing the amount of data required.

cs.LG↗

arXiv2025

Unified Modelling of Infrastructure Asset Performance Deterioration -- a bounded gamma process approach

Infrastructure asset management systems require a flexible deterioration model that can handle various degradation patterns in a unified way. Owing to its appealing monotonic sample paths, independent increments and mathematical tractability, gamma process has been widely employed as an infrastructure performance deterioration model. This model was recently enhanced by introducing an upper bound to satisfy a practical modelling need that many infrastructure performance deterioration processes are constrained by physical or managerial limits. Several bounded transformed gamma process (BTGP) alternatives had been proposed; however, they lacked due flexibility to characterize different deterioration patterns. This paper proposed a new BTGP model that is deeply grounded upon the traditional regression modelling tradition in infrastructure asset management systems. Qualitative and quantitative comparisons were carried out between the proposed BTGP and a bounded nonstationary gamma process (BNGP) model from both deterioration modelling and asset management decision-making perspectives. An empirical study using the real-world historical bridge condition data was performed to examine the flexibility of the BTGP against the BNGP and six other BTGP alternatives. The results confirmed the flexibility and significance of the proposed BTGP model for infrastructure systems.

stat.AP↗

arXiv2025

PAIRS: Parametric-Verified Adaptive Information Retrieval and Selection for Efficient RAG

Retrieval-Augmented Generation (RAG) has become a cornerstone technique for enhancing large language models (LLMs) with external knowledge. However, current RAG systems face two critical limitations: (1) they inefficiently retrieve information for every query, including simple questions that could be resolved using the LLM's parametric knowledge alone, and (2) they risk retrieving irrelevant documents when queries contain sparse information signals. To address these gaps, we introduce Parametric-verified Adaptive Information Retrieval and Selection (PAIRS), a training-free framework that integrates parametric and retrieved knowledge to adaptively determine whether to retrieve and how to select external information. Specifically, PAIRS employs a dual-path generation mechanism: First, the LLM produces both a direct answer and a context-augmented answer using self-generated pseudo-context. When these outputs converge, PAIRS bypasses external retrieval entirely, dramatically improving the RAG system's efficiency. For divergent cases, PAIRS activates a dual-path retrieval (DPR) process guided by both the original query and self-generated contextual signals, followed by an Adaptive Information Selection (AIS) module that filters documents through weighted similarity to both sources. This simple yet effective approach can not only enhance efficiency by eliminating unnecessary retrievals but also improve accuracy through contextually guided retrieval and adaptive information selection. Experimental results on six question-answering (QA) benchmarks show that PAIRS reduces retrieval costs by around 25% (triggering for only 75% of queries) while still improving accuracy-achieving +1.1% EM and +1.0% F1 over prior baselines on average.

cs.CL↗

arXiv2025

HRSim: An agent-based simulation platform for high-capacity ride-sharing services

The rapid growth of ride-sharing services presents a promising solution to urban transportation challenges, such as congestion and carbon emissions. However, developing efficient operational strategies, such as pricing, matching, and fleet management, requires robust simulation tools that can replicate real-world dynamics at scale. Existing platforms often lack the capacity, flexibility, or open-source accessibility needed to support large-scale, high-capacity ride-sharing services. To address these gaps, we introduce HRSim, an open-source, agent-based High-capacity Ride-sharing Simulator. HRSim integrates real-world road networks and demand data to simulate dynamic ride-sharing operations, including pricing, routing, matching, and repositioning. Its module design supports both ride-sharing and solo-hailing service modes. Also, it includes a visualization module for real-time performance analysis. In addition, HRSim incorporates integer linear programming and heuristic algorithms, which can achieve large-scale simulations of high-capacity ride-sharing services. Applications demonstrate HRSim's utility in various perspectives, including quantifying carbon emissions, scaling ride-sharing performance, evaluating new strategies, etc. By bridging the gap between theoretical research and practical implementation, HRSim serves as a versatile testbed for policymakers and transportation network companies to optimize ride-sharing systems for efficiency and sustainability.

eess.SY↗

arXiv2025

SCOPE: Compress Mathematical Reasoning Steps for Efficient Automated Process Annotation

Process Reward Models (PRMs) have demonstrated promising results in mathematical reasoning, but existing process annotation approaches, whether through human annotations or Monte Carlo simulations, remain computationally expensive. In this paper, we introduce Step COmpression for Process Estimation (SCOPE), a novel compression-based approach that significantly reduces annotation costs. We first translate natural language reasoning steps into code and normalize them through Abstract Syntax Tree, then merge equivalent steps to construct a prefix tree. Unlike simulation-based methods that waste numerous samples on estimation, SCOPE leverages a compression-based prefix tree where each root-to-leaf path serves as a training sample, reducing the complexity from $O(NMK)$ to $O(N)$. We construct a large-scale dataset containing 196K samples with only 5% of the computational resources required by previous methods. Empirical results demonstrate that PRMs trained on our dataset consistently outperform existing automated annotation approaches on both Best-of-N strategy and ProcessBench.

cs.AI↗

arXiv2025

QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Video Comprehension

Recent advances in long video understanding typically mitigate visual redundancy through visual token pruning based on attention distribution. However, while existing methods employ post-hoc low-response token pruning in decoder layers, they overlook the input-level semantic correlation between visual tokens and instructions (query). In this paper, we propose QuoTA, an ante-hoc training-free modular that extends existing large video-language models (LVLMs) for visual token assignment based on query-oriented frame-level importance assessment. The query-oriented token selection is crucial as it aligns visual processing with task-specific requirements, optimizing token budget utilization while preserving semantically relevant content. Specifically, (i) QuoTA strategically allocates frame-level importance scores based on query relevance, enabling one-time visual token assignment before cross-modal interactions in decoder layers, (ii) we decouple the query through Chain-of-Thoughts reasoning to facilitate more precise LVLM-based frame importance scoring, and (iii) QuoTA offers a plug-and-play functionality that extends to existing LVLMs. Extensive experimental results demonstrate that implementing QuoTA with LLaVA-Video-7B yields an average performance improvement of 3.2% across six benchmarks (including Video-MME and MLVU) while operating within an identical visual token budget as the baseline. Codes are open-sourced at https://github.com/MAC-AutoML/QuoTA.

cs.CV↗

arXiv2025

Full-Step-DPO: Self-Supervised Preference Optimization with Step-wise Rewards for Mathematical Reasoning

Direct Preference Optimization (DPO) often struggles with long-chain mathematical reasoning. Existing approaches, such as Step-DPO, typically improve this by focusing on the first erroneous step in the reasoning chain. However, they overlook all other steps and rely heavily on humans or GPT-4 to identify erroneous steps. To address these issues, we propose Full-Step-DPO, a novel DPO framework tailored for mathematical reasoning. Instead of optimizing only the first erroneous step, it leverages step-wise rewards from the entire reasoning chain. This is achieved by training a self-supervised process reward model, which automatically scores each step, providing rewards while avoiding reliance on external signals. Furthermore, we introduce a novel step-wise DPO loss, which dynamically updates gradients based on these step-wise rewards. This endows stronger reasoning capabilities to language models. Extensive evaluations on both in-domain and out-of-domain mathematical reasoning benchmarks across various base language models, demonstrate that Full-Step-DPO achieves superior performance compared to state-of-the-art baselines.

cs.CL↗

arXiv2025

Point-PRC: A Prompt Learning Based Regulation Framework for Generalizable Point Cloud Analysis

This paper investigates the 3D domain generalization (3DDG) ability of large 3D models based on prevalent prompt learning. Recent works demonstrate the performances of 3D point cloud recognition can be boosted remarkably by parameter-efficient prompt tuning. However, we observe that the improvement on downstream tasks comes at the expense of a severe drop in 3D domain generalization. To resolve this challenge, we present a comprehensive regulation framework that allows the learnable prompts to actively interact with the well-learned general knowledge in large 3D models to maintain good generalization. Specifically, the proposed framework imposes multiple explicit constraints on the prompt learning trajectory by maximizing the mutual agreement between task-specific predictions and task-agnostic knowledge. We design the regulation framework as a plug-and-play module to embed into existing representative large 3D models. Surprisingly, our method not only realizes consistently increasing generalization ability but also enhances task-specific 3D recognition performances across various 3DDG benchmarks by a clear margin. Considering the lack of study and evaluation on 3DDG, we also create three new benchmarks, namely base-to-new, cross-dataset and few-shot generalization benchmarks, to enrich the field and inspire future research. Code and benchmarks are available at \url{https://github.com/auniquesun/Point-PRC}.

cs.CV↗

arXiv2025

Multi-Task Model Merging via Adaptive Weight Disentanglement

Model merging has recently gained attention as an economical and scalable approach to incorporate task-specific weights from various tasks into a unified multi-task model. For example, in Task Arithmetic (TA), adding the fine-tuned weights of different tasks can enhance the model's performance on those tasks, while subtracting them leads to task forgetting. Although TA is highly effective, interference among task still hampers the performance of the merged model. Existing methods for handling conflicts between task generally rely on empirical selection, resulting in suboptimal performance. In this paper, we introduce an Adaptive Weight Disentanglement method. We begin by theoretically proving that task vectors employed in model merging should be orthogonal to minimize interference among tasks. Guided by this insight, we initialize redundant vectors such that, when subtracted from the original task vectors, the resulting vectors exhibit increased orthogonality. Additionally, we impose an norm constraint on the redundant vectors to preserve the performance of the task-specific models. Experimental results demonstrate the effectiveness of our proposed technique: it successfully extracts redundant vectors, and after their subtraction, the task vectors not only retain robust performance but also achieve superior fusion outcomes. Our code is available at \href{https://github.com/FarisXiong/AWD.git}{https://github.com/FarisXiong/AWD.git}.

cs.LG↗

arXiv2024

Development dilemma of ride-sharing: Revenue or social welfare?

This study investigates the development dilemma of ride-sharing services using real-world mobility datasets from nine cities and calibrated customers' price and detour elasticity. Through massive numerical experiments, this study reveals that while ride-sharing can benefit social welfare, it may also lead to a loss of revenue for transportation network companies (TNCs) or drivers compared with solo-hailing, which limits TNCs' motivation to develop ride-sharing services. Three key factors contributing to this revenue loss are identified: (1) the low successful sharing ratio for customers choosing ride-sharing in some cases, (2) the limited saved trip distance by pooling two customers, and (3) the potential revenue loss when pooling customers with significantly different trip fares. Furthermore, this study finds that the monetary benefits of carbon emission reductions from ride-sharing are not substantial enough to affect customers' choices between solo-hailing and ride-sharing. The findings provide a valuable reference for TNCs and governments. For TNCs, effective pricing strategies, such as dynamic pricing, should be designed to prevent revenue loss when introducing ride-sharing. Governments are suggested to subsidize ride-sharing services to solve the development dilemma and maintain or even increase social welfare benefits from ride-sharing, including reduced carbon emissions and improved vehicle occupancy rates.

eess.SY↗

arXiv2024

As Simple as Fine-tuning: LLM Alignment via Bidirectional Negative Feedback Loss

Direct Preference Optimization (DPO) has emerged as a more computationally efficient alternative to Reinforcement Learning from Human Feedback (RLHF) with Proximal Policy Optimization (PPO), eliminating the need for reward models and online sampling. Despite these benefits, DPO and its variants remain sensitive to hyper-parameters and prone to instability, particularly on mathematical datasets. We argue that these issues arise from the unidirectional likelihood-derivative negative feedback inherent in the log-likelihood loss function. To address this, we propose a novel LLM alignment loss that establishes a stable Bidirectional Negative Feedback (BNF) during optimization. Our proposed BNF loss eliminates the need for pairwise contrastive losses and does not require any extra tunable hyper-parameters or pairwise preference data, streamlining the alignment pipeline to be as simple as supervised fine-tuning. We conduct extensive experiments across two challenging QA benchmarks and four reasoning benchmarks. The experimental results show that BNF achieves comparable performance to the best methods on QA benchmarks, while its performance decrease on the four reasoning benchmarks is significantly lower compared to the best methods, thus striking a better balance between value alignment and reasoning ability. In addition, we further validate the performance of BNF on non-pairwise datasets, and conduct in-depth analysis of log-likelihood and logit shifts across different preference optimization methods.

cs.CL↗

arXiv2024

Generalized conditional gradient methods for multiobjective composite optimization problems with H{ö}lder condition

In this paper, we deal with multiobjective composite optimization problems, where each objective function is a combination of smooth and possibly non-smooth functions. We first propose a parameter-dependent conditional gradient method to solve this problem. The step size in this method requires prior knowledge of the parameters related to the H{ö}lder continuity of the gradient of the smooth function. The convergence properties of this method are then established. Given that these parameters may be unknown or, if known, may not be unique, the first method may encounter implementation challenges or slow convergence. To address this, we further propose a parameter-free conditional gradient method that determines the step size using a local quadratic upper approximation and an adaptive line search strategy, eliminating the need for any problem-specific parameters. The performance of the proposed methods is demonstrated on several test problems involving the indicator function and an uncertainty function.

math.OC↗

arXiv2024

Conjugate gradient methods without line search for multiobjective optimization

This paper addresses unconstrained multiobjective optimization problems where two or more continuously differentiable functions have to be minimized. We delve into the conjugate gradient methods proposed by Lucambio Pérez and Prudente (SIAM J Optim, 28(3): 2690--2720, 2018) for such problems. Instead of the Wolfe-type line search procedure used in their work, we employ a fixed stepsize formula (or no-line-search scheme), which can mitigate the pressure of choosing stepsize caused by multiple inequalities and avoid the computational cost associated with function evaluations in specific applications. The no-line-search scheme is utilized to derive the condition of Zoutendijk's type. Global convergence encompasses the vector extensions of Fletcher--Reeves, conjugate descent, Dai--Yuan, Polak--Ribière--Polyak and Hestenes--Stiefel parameters, subject to certain mild assumptions. Additionally, numerical experiments are conducted to demonstrate the practical performance of the proposed stepsize rule, and comparative analyses are made with the multiobjective steepest descent methods using the Armijo line search and the multiobjective conjugate gradient methods using the Wolfe-type line search.

math.OC↗

arXiv2024

Robust Coulomb Gap and Varied-temperature Study of Epitaxial 1T'-WSe$_2$ Monolayers

The transition metal dichalcogenides (TMDCs) with a 1T' structural phase are predicted to be two-dimensional topological insulators at zero temperature. Although the quantized edge conductance of 1T'-WTe$_2$ has been confirmed to survive up to 100 K, this temperature is still relatively low for industrial applications. Addressing the limited studies on temperature effects in 1T'-TMDCs, our research focuses on the electronic and crystal properties of the epitaxial 1T'-WSe$_2$ monolayers grown on bilayer graphene (BLG) and SrTiO$_3$(100) substrates at various temperatures. For the 1T'-WSe$_2$ grown on BLG, we observed a significant thermal expansion effect on its band structures with a thermal expansion coefficient of $\sim$60$\times$10$^{-6}$ K$^{-1}$. In contrast, the 1T'-WSe$_2$ grown on SrTiO$_3$(100) exhibits minimal changes with varied temperatures due to the enhanced strain exerted by the substrate. Besides, A significant Coulomb gap (CG) was observed pinned at the Fermi level in the angle-resolved photoemission spectroscopy (ARPES) and scanning tunneling spectroscopy (STS). The CG was founded to decrease with increasing temperatures, and can persist up to 200 K for 1T'-WSe$_2$/BLG, consistent with our Monte Carlo simulations. The robustness of the CG and the positive fundamental gap endow the epitaxial 1T'-WSe$_2$ monolayers with huge potential for realizing the quantum spin Hall devices.

cond-mat.mes-hall↗

arXiv2024

Decision algorithms for reversibility of one-dimensional non-linear cellular automata under null boundary conditions

The property of reversibility is quite meaningful for the classic theoretical computer science model, cellular automata. For the reversibility problem for a CA under null boundary conditions, while linear rules have been studied a lot, the non-linear rules remain unexplored at present. The paper investigates the reversibility problem of general one-dimensional CA on a finite field $\mathbb{Z}_p$, and proposes an approach to optimize the Amoroso's infinite CA surjectivity detection algorithm. This paper proposes algorithms for deciding the reversibility of one-dimensional CA under null boundary conditions. We propose a method to decide the strict reversibility of one-dimensional CA under null boundary conditions. We also provide a bucket chain based algorithm for calculating the reversibility function of one-dimensional CA under null boundary conditions. These decision algorithms work for not only linear rules but also non-linear rules. In addition, it has been confirmed that the reversibility function always has a period, and its periodicity is related to the periodicity of the corresponding bucket chain. Some of our experiment results of reversible CA are presented in the paper, complementing and validating the theoretical aspects, and thereby further supporting the research conclusions of this paper.

cs.CC↗