arXiv subjects

Yuntian Zhang

Publications and source records attributed to Yuntian Zhang.

7 recordsLinked to original sources

arXiv2026

An End-to-End Learning Approach for Solving Capacitated Location-Routing Problems

The capacitated location-routing problems (CLRPs) are classical problems in combinatorial optimization, which require simultaneously making location and routing decisions. In CLRPs, the complex constraints and the intricate relationships between various decisions make the problem challenging to solve. With the emergence of deep reinforcement learning (DRL), it has been extensively applied to address the vehicle routing problem and its variants, while the research related to CLRPs still needs to be explored. In this paper, we propose the DRL with heterogeneous query (DRLHQ) to solve CLRP and open CLRP (OCLRP), respectively. We are the first to propose an end-to-end learning approach for CLRPs, following the encoder-decoder structure. In particular, we reformulate the CLRPs as a markov decision process tailored to various decisions, a general modeling framework that can be adapted to other DRL-based methods. To better handle the interdependency across location and routing decisions, we also introduce a novel heterogeneous querying attention mechanism designed to adapt dynamically to various decision-making stages. Experimental results on both synthetic and benchmark datasets demonstrate superior solution quality and better generalization performance of our proposed approach over representative traditional and DRL-based baselines in solving both CLRP and OCLRP.

cs.LG↗

arXiv2026

Adversarial Training for Robust Coverage Network under Worst-case Facility Losses

The Maximal Covering Location-Interdiction Problem (MCLIP) is a classic bi-level optimization problem, which is fundamental to resilient infrastructure planning yet remains computationally intractable. Specifically, the upper level determines facility locations to maximize coverage, while the lower level executes worst-case interdiction to minimize the coverage. The strong coupling between the upper and lower levels, combined with their respective high combinatorial complexity, renders traditional methods ineffective. To bridge this gap, we propose a Dual-Agent Deep Reinforcement Learning (DADRL) framework based on adversarial learning, comprising a location agent corresponding to the upper level and an interdiction agent corresponding to the lower level. Our contributions are threefold: (1) The location agent is trained simultaneously against an evolving interdiction agent, making it effectively capture the dynamic competitive interplay between the upper and lower levels; (2) To fully exploit the learned capabilities of the interdiction agent, we propose a Surrogate-based Ensemble Inference Strategy that utilizes the trained interdiction agent as a high-fidelity surrogate to guide the decisions of location agent; (3) Extensive experiments on synthetic and real-world datasets demonstrate that our approach achieves superior computational efficiency while maintaining highly competitive solution quality compared to other baselines. Furthermore, our DADRL framework is model-agnostic to network structures, while its underlying adversarial learning paradigm demonstrates strong potential for solving other bi-level optimization problems.

cs.LG↗

arXiv2026

Towards Generalization-Oriented Models for Vehicle Routing Problems with Mixture-of-Experts

In recent years, Deep Reinforcement Learning (DRL) has achieved substantial progress on Vehicle Routing Problems (VRPs). However, existing DRL-based methods are typically trained on instances generated from a uniform distribution, which limits their performance under real-world distribution shifts. In this paper, we aim to develop a generalization-oriented model that partitions the policy network into multiple modules and adaptively recombines modules to form specific policies during inference. Specifically, we propose Residual Refined Experts with Instance-level Gating (R2E-IG) to improve cross-distribution generalization. Our contributions are threefold: (1) We introduce a Residual Refined Expert (R2E) architecture that enhance expert expressiveness via residual refinement; (2) We design an instance-level gating mechanism that learns distribution-aware instance representations and routes inputs to suitable modules; (3) We propose a mixed-distribution training mechanism equipped with Dynamic Weight Adaption (DWA), which dynamically reweights training data from different distributions to emphasize more informative ones. Extensive experiments show that R2E-IG achieves competitive performance against state-of-the-art baselines on both in-distribution and out-of-distribution instances across synthetic and benchmark datasets. Moreover, R2E-IG is generic and can be easily integrated into existing DRL-based methods to further improve performance.

cs.LG↗

arXiv2026

Uni-Skill: Building Self-Evolving Skill Repository for Generalizable Robotic Manipulation

While skill-centric approaches leverage foundation models to enhance generalization in compositional tasks, they often rely on fixed skill libraries, limiting adaptability to new tasks without manual intervention. To address this, we propose Uni-Skill, a Unified Skill-centric framework that supports skill-aware planning and facilitates automatic skill evolution. Unlike prior methods that restrict planning to predefined skills, Uni-Skill requests for new skill implementations when existing ones are insufficient, ensuring adaptable planning with self-augmented skill library. To support automatic implementation of diverse skills requested by the planning module, we construct SkillFolder, a VerbNet-inspired repository derived from large-scale unstructured robotic videos. SkillFolder introduces a hierarchical skill taxonomy that captures diverse skill descriptions at multiple levels of abstraction. By populating this taxonomy with large-scale, automatically annotated demonstrations, Uni-Skill shifts the paradigm of skill acquisition from inefficient manual annotation to efficient offline structural retrieval. Retrieved examples provide semantic supervision over behavior patterns and fine-grained references for spatial trajectories, enabling few-shot skill inference without deployment-time demonstrations. Comprehensive experiments in both simulation and real-world settings verify the state-of-the-art performance of Uni-Skill over existing VLM-based skill-centric approaches, highlighting its advanced reasoning capabilities and strong zero-shot generalization across a wide range of novel tasks.

cs.RO↗

arXiv2025

A RankNet-Inspired Surrogate-Assisted Hybrid Metaheuristic for Expensive Coverage Optimization

Coverage optimization generally involves deploying a set of facilities to best satisfy the demands of specified points, with broad applications in fields such as location science and sensor networks. Recent applications reveal that the subset site selection coupled with continuous angular parameter optimization can be formulated as Mixed-Variable Optimization Problems (MVOPs). Meanwhile, high-fidelity discretization and visibility analysis significantly increase computational cost and complexity, evolving the MVOP into an Expensive Mixed-Variable Optimization Problem (EMVOP). While canonical Evolutionary Algorithms have yielded promising results, their reliance on numerous fitness evaluations is too costly for our problem. Furthermore, most surrogate-assisted methods face limitations due to their reliance on regression-based models. To address these issues, we propose the RankNet-Inspired Surrogate-assisted Hybrid Metaheuristic (RI-SHM), an extension of our previous work. RI-SHM integrates three key components: (1) a RankNet-based pairwise global surrogate that innovatively predicts rankings between pairs of individuals, bypassing the challenges of fitness estimation in discontinuous solution space; (2) a surrogate-assisted local Estimation of Distribution Algorithm that enhances local exploitation and helps escape from local optima; and (3) a fitness diversity-driven switching strategy that dynamically balances exploration and exploitation. Experiments demonstrate that our algorithm can effectively handle large-scale coverage optimization tasks of up to 300 dimensions and more than 1,800 targets within desirable runtime. Compared to state-of-the-art algorithms for EMVOPs, RI-SHM consistently outperforms them by up to 56.5$\%$ across all tested instances.

cs.NE↗

arXiv2024

A Light-weight Transformer-based Self-supervised Matching Network for Heterogeneous Images

Matching visible and near-infrared (NIR) images remains a significant challenge in remote sensing image fusion. The nonlinear radiometric differences between heterogeneous remote sensing images make the image matching task even more difficult. Deep learning has gained substantial attention in computer vision tasks in recent years. However, many methods rely on supervised learning and necessitate large amounts of annotated data. Nevertheless, annotated data is frequently limited in the field of remote sensing image matching. To address this challenge, this paper proposes a novel keypoint descriptor approach that obtains robust feature descriptors via a self-supervised matching network. A light-weight transformer network, termed as LTFormer, is designed to generate deep-level feature descriptors. Furthermore, we implement an innovative triplet loss function, LT Loss, to enhance the matching performance further. Our approach outperforms conventional hand-crafted local feature descriptors and proves equally competitive compared to state-of-the-art deep learning-based methods, even amidst the shortage of annotated data.

cs.CV↗

arXiv2023

Electromotive force and magnetization process of a superconducting traveling-wave flux pump

Understanding and controlling the motion of superconducting vortices has been a key issue in condensed matter physics and applied superconductivity. Here we present a method for macroscopically manipulating the vortices based on travelling wave flux pump to accurately output industrial-scale DC current into high-temperature superconducting (HTS) magnets. DC magnetic fields are used to adjust the polarity of the vortices and thus modulate the direction of the output current, which demonstrates that the DC current of the flux pump originates from the motional electromotive force ( e.m.f. ) other than the induced e.m.f.. In addition, applying different strengths of DC fields can modulate the magnitude of the output current. Further numerical simulation suggests how the flux inside the superconducting tape is controlled by different applied fields. We build a controlled flux flow model to correctly explain the behavior of vortices controlled by the flux pump, and how the motional e.m.f. is created by manipulating the vortices. Based on the method, we achieve high precision regulation of output current using adaptive control of the DC magnetic field, allowing the flux pump to output DC current just as accurate as a typical commercial power supply. This work advances the technic for macroscopic manipulation of vortices.

cond-mat.supr-con↗