arXiv subjects

Yongheng Wang

Publications and source records attributed to Yongheng Wang.

At least 19 recordsLinked to original sources

arXiv2026

Life-Cycle Planning of Collector System for Deep-Sea Multi-Spatial Wind-PV-Tidal Farm

This paper develops a life-cycle optimization model for the collector system (CS) of deep-sea co-located energy farms (CEFs), where co-located energy turbines (CETs) integrate wind, photovoltaic (PV), and tidal current resources across sea-area layers. The model captures multi-layer marine-space complementarity, wake effects, and output variability, while accommodating diverse dynamic submarine cable configurations. To improve computational efficiency, the adaptive piecewise linearization (A-PWL) method based on the outputs of CETs is proposed to transform the original mixed-integer quadratic programming (MIQP) problem into a mixed-integer linear programming (MILP) form to approximate quadratic operation costs and simplify absolute power flow modeling. Case studies demonstrate that incorporating multi-energy complementarity significantly enhances the economic performance of deep-sea CEFs. When external physical risks are negligible, the fully-suspended cable configuration proves more cost-effective than the lazy-wave design. The proposed linearization method achieves high accuracy while significantly reducing solution time. Overall, this work provides a practical and scalable framework for efficient CS planning in offshore renewable energy systems.

eess.SY↗

arXiv2026

MatrAIx: Simulating the World with 8.3 Billion Persona Agents

Human evaluation of AI systems and digital products is costly, slow, and difficult to scale. Offline evaluations are more scalable but often abstract away human diversity and interactive behavior. We therefore introduce MatrAIx, a population-scale simulated-user evaluation infrastructure for testing AI systems and digital products with heterogeneous users. MatrAIx has three core components: First, Persona 8B contains 8.3 billion persona records represented by 1,290 categorical dimensions. Records are either sampled from a dependency graph that preserves correlated attributes or derived from human-authored profiles. We release a quality-filtered coreset of approximately 1 million personas, comprising 599,847 human-grounded and 400,000 synthetic records. Second, the MatrAIx Playground provides four environments in which diverse users evaluate and interact with digital products: Survey, AI Chatbot, Web, and App. Third, MatrAIx provides 1,010 application tasks spanning more than 25 domains, including Commerce, Software, Finance, and Healthcare. We conducted 18,189 evaluation trials across eight representative tasks. Persona agents were powered by three LLMs: Claude Opus 4.8, GPT 5.5, and Claude Haiku 4.5. The resulting feedback captures how decisions and preferences vary across persona backgrounds, including hesitation after a price increase, willingness to continue after an AI assistant fails, and latency tolerance. We conducted two main validation studies: First, a 400-trial controlled study evaluated persona adherence across ten behavioral attributes and all four environments. The declared behavior was expressed or correctly suppressed in 366 trials (91.5%). Second, human and LLM judges evaluated the extraction quality of human-grounded personas. Overall, MatrAIx provides an end-to-end infrastructure for evaluating AI systems and digital products with diverse simulated human users.

cs.AI↗

arXiv2026

DiffLens: A Visualization System to Explore Local Differences in Graph Sampling

Graph sampling techniques have been widely used to simplify network computation and visualization, which also results in inevitable differences between the sampled networks and the original networks in terms of nodes, edges and structures. Investigating such differences can inform graph sampling technique users of the pros and cons of different techniques and select the appropriate one, and can also help graph sampling developers evaluate their own technique. However, there are still no systematic ways to achieve such a goal. This paper fills this research gap by first proposing systematic and generic quantitative measures to quantify three categories of graph differences (i.e., neighbor-based, path-based, and structure-based). Built upon this, we further propose DiffLens, a novel visualization system to help graph sampling developers and users intuitively explore local differences at different regions of their interest within a sampled graph, where three new lens-based visual designs are presented to display the neighbor-based, path-based, and structure-based differences respectively. We conducted two case studies and a user study using real-world network datasets to evaluate DiffLens. The results confirmed its effectiveness and usability in helping users explore local differences and compare different graph sampling strategies.

cs.HC↗

arXiv2026

A Survey of AI-Generated Video Evaluation

The growing capabilities of AI in generating video content have brought forward significant challenges in effectively evaluating these videos. Unlike static images or text, video content involves complex spatial and temporal dynamics which may require a more comprehensive and systematic evaluation of its contents in aspects like video presentation quality, semantic information delivery, alignment with human intentions, and the virtual-reality consistency with our physical world. This survey identifies the emerging field of AI-Generated Video Evaluation (AIGVE), highlighting the importance of assessing how well AI-generated videos align with human perception and meet specific instructions. We provide a structured analysis of existing methodologies that could be potentially used to evaluate AI-generated videos. By outlining the strengths and gaps in current approaches, we advocate for the development of more robust and nuanced evaluation frameworks that can handle the complexities of video content, which include not only the conventional metric-based evaluations, but also the current human-involved evaluations, and the future model-centered evaluations. This survey aims to establish a foundational knowledge base for both researchers from academia and practitioners from the industry, facilitating the future advancement of evaluation methods for AI-generated video content.

cs.CV↗

arXiv2026

DomainCQA: Crafting Knowledge-Intensive QA from Domain-Specific Charts

Chart Question Answering (CQA) evaluates Multimodal Large Language Models (MLLMs) on visual understanding and reasoning over chart data. However, existing benchmarks mostly test surface-level parsing, such as reading labels and legends, while overlooking deeper scientific reasoning. We propose DomainCQA, a framework for constructing domain-specific CQA benchmarks that emphasize both visual comprehension and knowledge-intensive reasoning. It integrates complexity-aware chart selection, multitier QA generation, and expert validation. Applied to astronomy, DomainCQA yields AstroChart, a benchmark of 1,690 QA pairs over 482 charts, exposing persistent weaknesses in fine-grained perception, numerical reasoning, and domain knowledge integration across 21 MLLMs. Fine-tuning on AstroChart improves performance across fundamental and advanced tasks. Pilot QA sets in biochemistry, economics, medicine, and social science further demonstrate DomainCQA's generality. Together, our results establish DomainCQA as a unified pipeline for constructing and augmenting domain-specific chart reasoning benchmarks.

cs.CL↗

arXiv2025

Large Language Models for Robotics: A Survey

The human ability to learn, generalize, and control complex manipulation tasks through multi-modality feedback suggests a unique capability, which we refer to as dexterity intelligence. Understanding and assessing this intelligence is a complex task. Amidst the swift progress and extensive proliferation of large language models (LLMs), their applications in the field of robotics have garnered increasing attention. LLMs possess the ability to process and generate natural language, facilitating efficient interaction and collaboration with robots. Researchers and engineers in the field of robotics have recognized the immense potential of LLMs in enhancing robot intelligence, human-robot interaction, and autonomy. Therefore, this comprehensive review aims to summarize the applications of LLMs in robotics, delving into their impact and contributions to key areas such as robot control, perception, decision-making, and planning. This survey first provides an overview of the background and development of LLMs for robotics, followed by a discussion of their benefits and recent advancements in LLM-based robotic models. It then explores various techniques, employed in perception, decision-making, control, and interaction, as well as cross-module coordination in practical tasks. Finally, we review current applications of LLMs in robotics and outline potential challenges they may face in the near future. Embodied intelligence represents the future of intelligent systems, and LLM-based robotics is one of the most promising yet challenging paths toward achieving it.

cs.RO↗

arXiv2025

Tri-Level Stochastic-Robust Co-Planning of Distribution Networks and Renewable Charging Stations With an Adaptive iC&CG Algorithm

Renewable charging stations (RCSs) that co-locate electric-vehicle (EV) charging with distributed generation (DG) can raise renewable utilization and improve distribution-network (DN) efficiency, yet their variability and the siting-dependent charging demand can overload feeders if placed poorly. This paper proposes a tri-level, two-stage stochastic-robust optimization (SRO) co-planning framework that jointly determines RCS siting and DN expansion while accounting for transportation flows and population density. The model distinguishes two uncertainty classes: (i) decision-dependent uncertainty (DDU), under which EV charging loads vary with RCS siting; and (ii) decision-independent uncertainty (DIU), under which load fluctuations and renewable-generation variability do not depend on the RCS locations or the DN topology. At the upper level, the framework selects RCS sites and DN expansions. At the middle level, EV routing and charging are dispatched given the RCS siting to produce charging loads DDU. At the lower level, DN operation minimizes annualized loss costs under the worst-case DIU, reformulated via Karush-Kuhn-Tucker (KKT) conditions. To solve the resulting problem efficiently, we develop an adaptive inexact column-and-constraint generation (A-iC&CG) algorithm and prove finite-iteration convergence. Case studies on a 47-node DN coupled with a 68-hub transportation network in Shenzhen, China, show that A-iC&CG outperforms benchmark algorithms and that PV-EV hybrid stations are cost-optimal, with RCS siting concentrated near substations and high-flow hubs.

eess.SY↗

arXiv2025

Distributionally Robust Joint Planning of Coastal Distribution Network and PV-Storage-EV Stations

The rapid integration of renewable energy resources, such as tidal and photovoltaic (PV) power, coupled with the growing deployment of electric vehicle (EV) charging infrastructure, necessitates coordinated planning for coastal urban distribution networks (DN). This paper presents a tri-layer distributionally robust optimization framework to jointly optimize the sitting of PV-storage-EV stations (PSES) and the configuration of coastal DNs, addressing uncertainties related to power load, PV generation, and EV charging demands. At the upper layer, optimal PSES siting and network topology decisions are made to minimize total investment and operational costs. The middle-layer formulation tackles worst case uncertainty scenarios via the optimal power flow model, utilizing ambiguity sets to capture correlated uncertainties. To handle non-convexities introduced by binary variables for energy storage systems, we propose and rigorously prove the exactness of a novel relaxation approach. At the lower layer, considering the dynamic pricing driven by tidal energy fluctuations, operational decisions-including electricity procurement and carbon emissions are optimized. An inexact column-and-constraint generation (i-CCG) algorithm is developed for efficient problem-solving. Numerical results from a realistic 47-node coastal DN in China illustrate that the proposed method effectively reduces costs and ensures robust, low-carbon planning under substantial uncertainties.

math.OC↗

arXiv2025

A Unified Framework for Interactive Visual Graph Matching via Attribute-Structure Synchronization

In traditional graph retrieval tools, graph matching is commonly used to retrieve desired graphs from extensive graph datasets according to their structural similarities. However, in real applications, graph nodes have numerous attributes which also contain valuable information for evaluating similarities between graphs. Thus, to achieve superior graph matching results, it is crucial for graph retrieval tools to make full use of the attribute information in addition to structural information. We propose a novel framework for interactive visual graph matching. In the proposed framework, an attribute-structure synchronization method is developed for representing structural and attribute features in a unified embedding space based on Canonical Correlation Analysis (CCA). To support fast and interactive matching, \revise{our method} provides users with intuitive visual query interfaces for traversing, filtering and searching for the target graph in the embedding space conveniently. With the designed interfaces, the users can also specify a new target graph with desired structural and semantic features. Besides, evaluation views are designed for easy validation and interpretation of the matching results. Case studies and quantitative comparisons on real-world datasets have demonstrated the superiorities of our proposed framework in graph matching and large graph exploration.

cs.IR↗

arXiv2025

A Highly Efficient Cross-matching Scheme using Learned Index Structure

Spatial data fusion is a bottleneck when it meets the scale of 10 billion records. Cross-matching celestial catalogs is just one example of this. To challenge this, we present a framework that enables efficient cross-matching using Learned Index Structures. Our approach involves a data transformation method to map multi-dimensional data into easily learnable distributions, coupled with a novel search algorithm that leverages the advantages of model pairs, significantly enhancing the efficiency of nearest-neighbor search. In this study, we utilized celestial catalog data derived from astronomical surveys to construct the index and evaluated the speed of the cross-matching process. Using the HEALPix segmentation scheme, we built an independent model object for each tile and developed an end-to-end pipeline to construct a framework with semantic guarantees for record retrieval in query and range search. Our results show that the proposed method improves cross-matching speed by more than four times compared to KD-trees for a radius range between 1 milli-arcseconds and 100 arcseconds.

astro-ph.IM↗

arXiv2024

ChartKG: A Knowledge-Graph-Based Representation for Chart Images

Chart images, such as bar charts, pie charts, and line charts, are explosively produced due to the wide usage of data visualizations. Accordingly, knowledge mining from chart images is becoming increasingly important, which can benefit downstream tasks like chart retrieval and knowledge graph completion. However, existing methods for chart knowledge mining mainly focus on converting chart images into raw data and often ignore their visual encodings and semantic meanings, which can result in information loss for many downstream tasks. In this paper, we propose ChartKG, a novel knowledge graph (KG) based representation for chart images, which can model the visual elements in a chart image and semantic relations among them including visual encodings and visual insights in a unified manner. Further, we develop a general framework to convert chart images to the proposed KG-based representation. It integrates a series of image processing techniques to identify visual elements and relations, e.g., CNNs to classify charts, yolov5 and optical character recognition to parse charts, and rule-based methods to construct graphs. We present four cases to illustrate how our knowledge-graph-based representation can model the detailed visual elements and semantic relations in charts, and further demonstrate how our approach can benefit downstream applications such as semantic-aware chart retrieval and chart question answering. We also conduct quantitative evaluations to assess the two fundamental building blocks of our chart-to-KG framework, i.e., object recognition and optical character recognition. The results provide support for the usefulness and effectiveness of ChartKG.

cs.AI↗

arXiv2024

Continual Multimodal Knowledge Graph Construction

Current Multimodal Knowledge Graph Construction (MKGC) models struggle with the real-world dynamism of continuously emerging entities and relations, often succumbing to catastrophic forgetting-loss of previously acquired knowledge. This study introduces benchmarks aimed at fostering the development of the continual MKGC domain. We further introduce MSPT framework, designed to surmount the shortcomings of existing MKGC approaches during multimedia data processing. MSPT harmonizes the retention of learned knowledge (stability) and the integration of new data (plasticity), outperforming current continual learning and multimodal methods. Our results confirm MSPT's superior performance in evolving knowledge environments, showcasing its capacity to navigate balance between stability and plasticity.

cs.CL↗

arXiv2024

Can We Edit Multimodal Large Language Models?

In this paper, we focus on editing Multimodal Large Language Models (MLLMs). Compared to editing single-modal LLMs, multimodal model editing is more challenging, which demands a higher level of scrutiny and careful consideration in the editing process. To facilitate research in this area, we construct a new benchmark, dubbed MMEdit, for editing multimodal LLMs and establishing a suite of innovative metrics for evaluation. We conduct comprehensive experiments involving various model editing baselines and analyze the impact of editing different components for multimodal LLMs. Empirically, we notice that previous baselines can implement editing multimodal LLMs to some extent, but the effect is still barely satisfactory, indicating the potential difficulty of this task. We hope that our work can provide the NLP community with insights. Code and dataset are available in https://github.com/zjunlp/EasyEdit.

cs.CL↗

arXiv2024

ConceptThread: Visualizing Threaded Concepts in MOOC Videos

Massive Open Online Courses (MOOCs) platforms are becoming increasingly popular in recent years. Online learners need to watch the whole course video on MOOC platforms to learn the underlying new knowledge, which is often tedious and time-consuming due to the lack of a quick overview of the covered knowledge and their structures. In this paper, we propose ConceptThread, a visual analytics approach to effectively show the concepts and the relations among them to facilitate effective online learning. Specifically, given that the majority of MOOC videos contain slides, we first leverage video processing and speech analysis techniques, including shot recognition, speech recognition and topic modeling, to extract core knowledge concepts and construct the hierarchical and temporal relations among them. Then, by using a metaphor of thread, we present a novel visualization to intuitively display the concepts based on video sequential flow, and enable learners to perform interactive visual exploration of concepts. We conducted a quantitative study, two case studies, and a user study to extensively evaluate ConceptThread. The results demonstrate the effectiveness and usability of ConceptThread in providing online learners with a quick understanding of the knowledge content of MOOC videos.

cs.HC↗

arXiv2023

Joint Planning of Active Distribution Network and EV Charging Stations Considering Vehicle-to-Grid Functionality and Reactive Power Support

This paper proposes a collaborative planning model for the active distribution network (ADN) and electric vehicle (EV) charging stations that fully considers the vehicle-to-grid (V2G) function and reactive power support of EVs in different regions. This paper employs a sequential decomposition method based on the physical characteristics of the problem, breaking down the holistic problem into two sub-problems for solution. Subproblem I optimizes the charging and discharging behavior of the autopilot electric vehicles (AEVs) using a mixed-integer linear programming (MILP) model. Subproblem II uses a mixed-integer second-order cone programming (MISOCP) model to plan the ADN and retrofit or construct V2G charging stations (V2GCS), as well as multiple distributed generation resources (DGRs). The paper also analyzes the impact of the bi-directional active-reactive power interaction of V2GCS on ADN planning. The presented model was tested in the 47 nodes ADN in Longgang District, Shenzhen, China, and the IEEE 33 nodes ADN, demonstrating that decomposition can significantly improve the speed of solving large-scale problems while maintaining accuracy with low AEV penetration.

eess.SY↗

arXiv2023

Improving Knowledge Distillation via Regularizing Feature Norm and Direction

Knowledge distillation (KD) exploits a large well-trained model (i.e., teacher) to train a small student model on the same dataset for the same task. Treating teacher features as knowledge, prevailing methods of knowledge distillation train student by aligning its features with the teacher's, e.g., by minimizing the KL-divergence between their logits or L2 distance between their intermediate features. While it is natural to believe that better alignment of student features to the teacher better distills teacher knowledge, simply forcing this alignment does not directly contribute to the student's performance, e.g., classification accuracy. In this work, we propose to align student features with class-mean of teacher features, where class-mean naturally serves as a strong classifier. To this end, we explore baseline techniques such as adopting the cosine distance based loss to encourage the similarity between student features and their corresponding class-means of the teacher. Moreover, we train the student to produce large-norm features, inspired by other lines of work (e.g., model pruning and domain adaptation), which find the large-norm features to be more significant. Finally, we propose a rather simple loss term (dubbed ND loss) to simultaneously (1) encourage student to produce large-\emph{norm} features, and (2) align the \emph{direction} of student features and teacher class-means. Experiments on standard benchmarks demonstrate that our explored techniques help existing KD methods achieve better performance, i.e., higher classification accuracy on ImageNet and CIFAR100 datasets, and higher detection precision on COCO dataset. Importantly, our proposed ND loss helps the most, leading to the state-of-the-art performance on these benchmarks. The source code is available at \url{https://github.com/WangYZ1608/Knowledge-Distillation-via-ND}.

cs.CV↗

arXiv2023

Ensemble Clustering via Co-association Matrix Self-enhancement

Ensemble clustering integrates a set of base clustering results to generate a stronger one. Existing methods usually rely on a co-association (CA) matrix that measures how many times two samples are grouped into the same cluster according to the base clusterings to achieve ensemble clustering. However, when the constructed CA matrix is of low quality, the performance will degrade. In this paper, we propose a simple yet effective CA matrix self-enhancement framework that can improve the CA matrix to achieve better clustering performance. Specifically, we first extract the high-confidence (HC) information from the base clusterings to form a sparse HC matrix. By propagating the highly-reliable information of the HC matrix to the CA matrix and complementing the HC matrix according to the CA matrix simultaneously, the proposed method generates an enhanced CA matrix for better clustering. Technically, the proposed model is formulated as a symmetric constrained convex optimization problem, which is efficiently solved by an alternating iterative algorithm with convergence and global optimum theoretically guaranteed. Extensive experimental comparisons with twelve state-of-the-art methods on eight benchmark datasets substantiate the effectiveness, flexibility and efficiency of the proposed model in ensemble clustering. The codes and datasets can be downloaded at https://github.com/Siritao/EC-CMS.

cs.LG↗

arXiv2023

SimCGNN: Simple Contrastive Graph Neural Network for Session-based Recommendation

Session-based recommendation (SBR) problem, which focuses on next-item prediction for anonymous users, has received increasingly more attention from researchers. Existing graph-based SBR methods all lack the ability to differentiate between sessions with the same last item, and suffer from severe popularity bias. Inspired by nowadays emerging contrastive learning methods, this paper presents a Simple Contrastive Graph Neural Network for Session-based Recommendation (SimCGNN). In SimCGNN, we first obtain normalized session embeddings on constructed session graphs. We next construct positive and negative samples of the sessions by two forward propagation and a novel negative sample selection strategy, and then calculate the constructive loss. Finally, session embeddings are used to give prediction. Extensive experiments conducted on two real-word datasets show our SimCGNN achieves a significant improvement over state-of-the-art methods.

cs.IR↗