Searcharxiv⌕ Search

arXiv subjects

Wenli Yang

Publications and source records attributed to Wenli Yang.

18 recordsLinked to original sources
arXiv2026

$\text{VG}^2$GT: Voxel-Gaussian Splatting Visual Geometry Grounded Transformer

Gaussian splatting has shown strong potential for 3D reconstruction and novel view synthesis. However, most existing methods require accurate camera parameters and per-scene optimization, while feed-forward methods with pixel-aligned Gaussian primitives often suffer from artifacts and non-uniform primitives. In this paper, we propose $\text{VG}^2$GT, a Voxel-Gaussian Splatting Visual Geometry-Grounded Transformer. $\text{VG}^2$GT leverages a frozen pretrained visual foundation model (VFM), incorporates a multi-scale differentiable voxel module to enhance geometric understanding, and directly splits and regresses Gaussian primitive parameters from voxel features. During training, depth maps are supervised through stochastic solid volume rendering, enabling geometrically accurate Gaussian scene reconstruction while keeping the visual foundation model fully frozen. This design enables $\text{VG}^2$GT to be seamlessly plugged into any patch-feature-based VFM, while substantially reducing the required training cost. $\text{VG}^2$GT outperforms current state-of-the-art methods on widely used DTU, Replica, TAT, and ScanNet datasets.

cs.CV↗
arXiv2025

Trustworthy Orchestration Artificial Intelligence by the Ten Criteria with Control-Plane Governance

As Artificial Intelligence (AI) systems increasingly assume consequential decision-making roles, a widening gap has emerged between technical capabilities and institutional accountability. Ethical guidance alone is insufficient to counter this challenge; it demands architectures that embed governance into the execution fabric of the ecosystem. This paper presents the Ten Criteria for Trustworthy Orchestration AI, a comprehensive assurance framework that integrates human input, semantic coherence, audit and provenance integrity into a unified Control-Panel architecture. Unlike conventional agentic AI initiatives that primarily focus on AI-to-AI coordination, the proposed framework provides an umbrella of governance to the entire AI components, their consumers and human participants. By taking aspiration from international standards and Australia's National Framework for AI Assurance initiative, this work demonstrates that trustworthiness can be systematically incorporated (by engineering) into AI systems, ensuring the execution fabric remains verifiable, transparent, reproducible and under meaningful human control.

cs.AI↗
arXiv2025

Robust Variational Model Based Tailored UNet: Leveraging Edge Detector and Mean Curvature for Improved Image Segmentation

To address the challenge of segmenting noisy images with blurred or fragmented boundaries, this paper presents a robust version of Variational Model Based Tailored UNet (VM_TUNet), a hybrid framework that integrates variational methods with deep learning. The proposed approach incorporates physical priors, an edge detector and a mean curvature term, into a modified Cahn-Hilliard equation, aiming to combine the interpretability and boundary-smoothing advantages of variational partial differential equations (PDEs) with the strong representational ability of deep neural networks. The architecture consists of two collaborative modules: an F module, which conducts efficient frequency domain preprocessing to alleviate poor local minima, and a T module, which ensures accurate and stable local computations, backed by a stability estimate. Extensive experiments on three benchmark datasets indicate that the proposed method achieves a balanced trade-off between performance and computational efficiency, which yields competitive quantitative results and improved visual quality compared to pure convolutional neural network (CNN) based models, while achieving performance close to that of transformer-based method with reasonable computational expense.

cs.CV↗
arXiv2025

Beyond Black-Box AI: Interpretable Hybrid Systems for Dementia Care

The recent boom of large language models (LLMs) has re-ignited the hope that artificial intelligence (AI) systems could aid medical diagnosis. Yet despite dazzling benchmark scores, LLM assistants have yet to deliver measurable improvements at the bedside. This scoping review aims to highlight the areas where AI is limited to make practical contributions in the clinical setting, specifically in dementia diagnosis and care. Standalone machine-learning models excel at pattern recognition but seldom provide actionable, interpretable guidance, eroding clinician trust. Adjacent use of LLMs by physicians did not result in better diagnostic accuracy or speed. Key limitations trace to the data-driven paradigm: black-box outputs which lack transparency, vulnerability to hallucinations, and weak causal reasoning. Hybrid approaches that combine statistical learning with expert rule-based knowledge, and involve clinicians throughout the process help bring back interpretability. They also fit better with existing clinical workflows, as seen in examples like PEIRS and ATHENA-CDS. Future decision-support should prioritise explanatory coherence by linking predictions to clinically meaningful causes. This can be done through neuro-symbolic or hybrid AI that combines the language ability of LLMs with human causal expertise. AI researchers have addressed this direction, with explainable AI and neuro-symbolic AI being the next logical steps in further advancement in AI. However, they are still based on data-driven knowledge integration instead of human-in-the-loop approaches. Future research should measure success not only by accuracy but by improvements in clinician understanding, workflow fit, and patient outcomes. A better understanding of what helps improve human-computer interactions is greatly needed for AI systems to become part of clinical practice.

cs.AI↗
arXiv2025

Image Segmentation via Variational Model Based Tailored UNet: A Deep Variational Framework

Traditional image segmentation methods, such as variational models based on partial differential equations (PDEs), offer strong mathematical interpretability and precise boundary modeling, but often suffer from sensitivity to parameter settings and high computational costs. In contrast, deep learning models such as UNet, which are relatively lightweight in parameters, excel in automatic feature extraction but lack theoretical interpretability and require extensive labeled data. To harness the complementary strengths of both paradigms, we propose Variational Model Based Tailored UNet (VM_TUNet), a novel hybrid framework that integrates the fourth-order modified Cahn-Hilliard equation with the deep learning backbone of UNet, which combines the interpretability and edge-preserving properties of variational methods with the adaptive feature learning of neural networks. Specifically, a data-driven operator is introduced to replace manual parameter tuning, and we incorporate the tailored finite point method (TFPM) to enforce high-precision boundary preservation. Experimental results on benchmark datasets demonstrate that VM_TUNet achieves superior segmentation performance compared to existing approaches, especially for fine boundary delineation.

cs.CV↗
arXiv2025

Enhancing tutoring systems by leveraging tailored promptings and domain knowledge with Large Language Models

Recent advancements in artificial intelligence (AI) and machine learning have reignited interest in their impact on Computer-based Learning (CBL). AI-driven tools like ChatGPT and Intelligent Tutoring Systems (ITS) have enhanced learning experiences through personalisation and flexibility. ITSs can adapt to individual learning needs and provide customised feedback based on a student's performance, cognitive state, and learning path. Despite these advances, challenges remain in accommodating diverse learning styles and delivering real-time, context-aware feedback. Our research aims to address these gaps by integrating skill-aligned feedback via Retrieval Augmented Generation (RAG) into prompt engineering for Large Language Models (LLMs) and developing an application to enhance learning through personalised tutoring in a computer science programming context. The pilot study evaluated a proposed system using three quantitative metrics: readability score, response time, and feedback depth, across three programming tasks of varying complexity. The system successfully sorted simulated students into three skill-level categories and provided context-aware feedback. This targeted approach demonstrated better effectiveness and adaptability compared to general methods.

cs.CY↗
arXiv2025

Influence of molecular rotation on the generation of N$_2^+$ air lasing

N$_2^+$ air lasing has attracted considerable attention due to its promising applications in remote sensing and the debates surrounding its generation mechanisms. Here, we present a comprehensive theoretical investigation of the role of molecular rotation in N$_2^+$ lasing at 391 nm ($B^2 \Sigma _u^+(v''=0)\rightarrow X^2 \Sigma _g^+ (v=0)$). By solving the open-system density matrix and Maxwell-Bloch equations in a rovibronic-state basis, we examine both the formation of the N$_2^+$ gain medium induced by a femtosecond pump pulse and the subsequent spatial propagation of the seed pulse. During the pump stage, rotational dynamics are found to significantly modify the angle-dependent populations of ionic vibrational-electronic states within tens of femtoseconds. Furthermore, ionization-produced rotational coherences substantially enhance the population inversion between the $X^2 \Sigma _g^+ (v=0)$ and $B^2 \Sigma _u^+(v''=0)$ states. In the seed propagation stage, both population inversion and rotational coherence are found to contribute to the lasing process, with the latter playing a dominant role in amplifying the lasing signals. These findings reveal the crucial role of molecular rotation in N$_2^+$ air lasing and highlight its potential as a tunable parameter for controlling lasing dynamics.

physics.optics↗
arXiv2025

Image Restoration Models with Optimal Transport and Total Variation Regularization

In this paper, we propose image restoration models using optimal transport (OT) and total variation regularization. We present theoretical results of the proposed models based on the relations between the dual Lipschitz norm from OT and the G-norm introduced by Yves Meyer. We design a numerical method based on the Primal-Dual Hybrid Gradient (PDHG) algorithm for the Wasserstain distance and the augmented Lagrangian method (ALM) for the total variation, and the convergence analysis of the proposed numerical method is established. We also consider replacing the total variation in our model by one of its modifications developed in \cite{zhu}, with the aim of suppressing the stair-casing effect and preserving image contrasts. Numerical experiments demonstrate the features of the proposed models.

math.NA↗
arXiv2025

The Impact of Modern AI in Metadata Management

Metadata management plays a critical role in data governance, resource discovery, and decision-making in the data-driven era. While traditional metadata approaches have primarily focused on organization, classification, and resource reuse, the integration of modern artificial intelligence (AI) technologies has significantly transformed these processes. This paper investigates both traditional and AI-driven metadata approaches by examining open-source solutions, commercial tools, and research initiatives. A comparative analysis of traditional and AI-driven metadata management methods is provided, highlighting existing challenges and their impact on next-generation datasets. The paper also presents an innovative AI-assisted metadata management framework designed to address these challenges. This framework leverages more advanced modern AI technologies to automate metadata generation, enhance governance, and improve the accessibility and usability of modern datasets. Finally, the paper outlines future directions for research and development, proposing opportunities to further advance metadata management in the context of AI-driven innovation and complex datasets.

cs.DB↗
arXiv2025

Advancing Oyster Phenotype Segmentation with Multi-Network Ensemble and Multi-Scale mechanism

Phenotype segmentation is pivotal in analysing visual features of living organisms, enhancing our understanding of their characteristics. In the context of oysters, meat quality assessment is paramount, focusing on shell, meat, gonad, and muscle components. Traditional manual inspection methods are time-consuming and subjective, prompting the adoption of machine vision technology for efficient and objective evaluation. We explore machine vision's capacity for segmenting oyster components, leading to the development of a multi-network ensemble approach with a global-local hierarchical attention mechanism. This approach integrates predictions from diverse models and addresses challenges posed by varying scales, ensuring robust instance segmentation across components. Finally, we provide a comprehensive evaluation of the proposed method's performance using different real-world datasets, highlighting its efficacy and robustness in enhancing oyster phenotype segmentation.

cs.CV↗
arXiv2025

A Comprehensive Survey on Integrating Large Language Models with Knowledge-Based Methods

The rapid development of artificial intelligence has led to marked progress in the field. One interesting direction for research is whether Large Language Models (LLMs) can be integrated with structured knowledge-based systems. This approach aims to combine the generative language understanding of LLMs and the precise knowledge representation systems by which they are integrated. This article surveys the relationship between LLMs and knowledge bases, looks at how they can be applied in practice, and discusses related technical, operational, and ethical challenges. Utilizing a comprehensive examination of the literature, the study both identifies important issues and assesses existing solutions. It demonstrates the merits of incorporating generative AI into structured knowledge-base systems concerning data contextualization, model accuracy, and utilization of knowledge resources. The findings give a full list of the current situation of research, point out the main gaps, and propose helpful paths to take. These insights contribute to advancing AI technologies and support their practical deployment across various sectors.

cs.CL↗
arXiv2024

A Concept-based Interpretable Model for the Diagnosis of Choroid Neoplasias using Multimodal Data

Diagnosing rare diseases presents a common challenge in clinical practice, necessitating the expertise of specialists for accurate identification. The advent of machine learning offers a promising solution, while the development of such technologies is hindered by the scarcity of data on rare conditions and the demand for models that are both interpretable and trustworthy in a clinical context. Interpretable AI, with its capacity for human-readable outputs, can facilitate validation by clinicians and contribute to medical education. In the current work, we focus on choroid neoplasias, the most prevalent form of eye cancer in adults, albeit rare with 5.1 per million. We built the so-far largest dataset consisting of 750 patients, incorporating three distinct imaging modalities collected from 2004 to 2022. Our work introduces a concept-based interpretable model that distinguishes between three types of choroidal tumors, integrating insights from domain experts via radiological reports. Remarkably, this model not only achieves an F1 score of 0.91, rivaling that of black-box models, but also boosts the diagnostic accuracy of junior doctors by 42%. This study highlights the significant potential of interpretable machine learning in improving the diagnosis of rare diseases, laying a groundwork for future breakthroughs in medical AI that could tackle a wider array of complex health scenarios.

cs.LG↗
arXiv2023

Coherent postionization dynamics of molecules based on adiabatic strong-field approximation

Taking N2 and O2 as examples, we theoretically study the post-ionization dynamics of molecules in strong laser fields using a density matrix method for open systems, focusing on the effect of ionization-produced coherence on the dynamics of residual ions. We introduce the adiabatic strong-field approximation (ASFA) method to predict the coherences between ionic states resulting from multiorbital strong-field ionizations. Compared with the standard SFA, the ASFA method can be applied across a wide range of laser intensities due to the consideration of orbital distortion effects. Based on the ASFA, it is found that there are obvious coherences between ionic states in residual molecular ions. These coherences significantly influence the transitions between ionic states, which finally change the post-ionization dynamics of molecular ions. Our findings reveal the importance of the ionization-produced coherences in modulating post-ionization molecular dynamics.

physics.atom-ph↗
arXiv2022

Proceedings of Principle and practice of data and Knowledge Acquisition Workshop 2022 (PKAW 2022)

Over the past two decades, PKAW has provided a forum for researchers and practitioners to discuss the state-of-the-arts in the area of knowledge acquisition and machine intelligence (MI, also Artificial Intelligence, AI). PKAW2022 will continue the above focus and welcome the contributions on the multi-disciplinary approach of human and big data-driven knowledge acquisition, as well as AI techniques and applications.

cs.AI↗
arXiv2022

Hybrid CNN -Interpreter: Interpret local and global contexts for CNN-based Models

Convolutional neural network (CNN) models have seen advanced improvements in performance in various domains, but lack of interpretability is a major barrier to assurance and regulation during operation for acceptance and deployment of AI-assisted applications. There have been many works on input interpretability focusing on analyzing the input-output relations, but the internal logic of models has not been clarified in the current mainstream interpretability methods. In this study, we propose a novel hybrid CNN-interpreter through: (1) An original forward propagation mechanism to examine the layer-specific prediction results for local interpretability. (2) A new global interpretability that indicates the feature correlation and filter importance effects. By combining the local and global interpretabilities, hybrid CNN-interpreter enables us to have a solid understanding and monitoring of model context during the whole learning process with detailed and consistent representations. Finally, the proposed interpretabilities have been demonstrated to adapt to various CNN-based model structures.

cs.LG↗
arXiv2022

A Comprehensive Review on Deep Supervision: Theories and Applications

Deep supervision, or known as 'intermediate supervision' or 'auxiliary supervision', is to add supervision at hidden layers of a neural network. This technique has been increasingly applied in deep neural network learning systems for various computer vision applications recently. There is a consensus that deep supervision helps improve neural network performance by alleviating the gradient vanishing problem, as one of the many strengths of deep supervision. Besides, in different computer vision applications, deep supervision can be applied in different ways. How to make the most use of deep supervision to improve network performance in different applications has not been thoroughly investigated. In this paper, we provide a comprehensive in-depth review of deep supervision in both theories and applications. We propose a new classification of different deep supervision networks, and discuss advantages and limitations of current deep supervision networks in computer vision applications.

cs.CV↗