arXiv subjects

Qing Huang

Publications and source records attributed to Qing Huang.

At least 19 recordsLinked to original sources

arXiv2026

Improving O-RADS Risk Stratification from Ultrasound Reports: A Comparative Evaluation of Hybrid versus End-to-End LLM Reasoning Strategies

Background: Automating clinical guideline-based decision-making with large language models (LLMs) remains challenging because of reliability, hallucination, and limited interpretability. We compared the performance of LLMs and reasoning strategies for automated Ovarian-Adnexal Reporting and Data System (O-RADS) classification from free-text pelvic ultrasound reports. Methods: In this retrospective study, consecutive patients with ovarian masses who underwent pelvic ultrasound were included. Eight LLMs were tested with three reasoning strategies: implicit-knowledge end-to-end, rule-informed end-to-end, and a feature-based hybrid architecture that decoupled feature extraction from rule-based classification. The reference standard was O-RADS categorization established by expert consensus. Results: A total of 310 women with 390 ovarian masses were evaluated. The feature-based hybrid architecture using Gemini 3.6 Flash demonstrated the best performance, achieving an accuracy of 99.2% (387 of 390) and almost perfect agreement with the reference standard (weighted kappa = 1.00; 95% CI: 0.99-1.00). Its performance surpassed that of original clinical reports (accuracy, 87.7% [342 of 390]; weighted kappa = 0.94; 95% CI: 0.91-0.96) and end-to-end LLM strategies (accuracy range, 65.6% [256 of 390] to 95.9% [374 of 390]). For structured feature extraction, Gemini 3.6 Flash demonstrated higher overall accuracy than Claude Fable 5 (98.9% vs 97.8%; P < 0.001). The hybrid architecture reduced misclassification errors and mitigated the overstaging tendency observed in original reports. Conclusion: The feature-based hybrid LLM architecture that separates clinical feature extraction from deterministic guideline execution enables highly accurate, reliable, and interpretable automated O-RADS classification, providing a promising approach for standardized, guideline-based clinical decision-making.

cs.AI↗

arXiv2026

Computational Measurement of Team-Process Phase Dynamics in Collaborative Virtual Reality

Collaborative virtual reality (VR) environments make team communication observable as it unfolds, but conventional transcript analyses often summarize entire trials or divide them into fixed temporal windows. Such approaches can obscure changes in team communication and coordination over time. This article presents a computational framework for detecting and interpreting dynamic team-process phases from timestamped dialogue in a collaborative VR game. The framework uses late chunking to generate context-aware transcript representations, aggregates them into temporal chunks, and applies penalized Gaussian-kernel change-point detection to identify semantic transitions in team communication. After boundary detection, term frequency--inverse document frequency (TF-IDF), non-negative matrix factorization (NMF), and representative transcript segments provide structured evidence for phase interpretation. A locally deployed large language model (LLM) uses in-context learning to generate initial interpretations that are subsequently reviewed by humans. Independently recorded interaction logs are then aligned with the detected phases to examine corresponding task-action patterns. The evaluation compares representations, pooling strategies, segmentation methods, parameter settings, reviewed phase interpretations, and phase-aligned interaction profiles. The results show that the framework identifies coherent and interpretable phase structures while preserving traceability to the underlying transcript evidence. The correspondence between transcript-derived phases and interaction behavior further supports their relevance for analyzing collaborative activity. The framework therefore offers a transparent and transferable approach for studying temporal changes in teamwork from timestamped transcripts across collaborative task settings.

cs.LG↗

arXiv2026

Computational Study of Water Adsorption and Dissociative Mechanisms Impacting g-C3N4's Optical and Electronic Properties

In the quest for sustainable energy solutions, water splitting emerges as a crucial process for generating clean hydrogen a versatile and renewable fuel essential for energy storage, emissions reduction, and achieving sustainability goals. This study employs a comprehensive computational approach, utilizing atomistic simulations to systematically investigate the effects of water absorption on the electronic and optical properties of g-C3N4 nanosheets. Our methodology integrates ab initio computations grounded in density functional theory (DFT), which allows for a detailed characterization of the nanosheet and serves as a benchmark for self-consistent charge density functional tight binding (SCC-DFTB) simulations. This approach provides valuable insights into the behavior of the nanosheet under the influence of absorbed OH and H2O molecules by considering calculated parameters for photocatalytic efficiency. Additionally, we extend our investigation to classical molecular dynamics simulations within the ReaxFF framework, modeling the emission of multiple H2O molecules and assessing the subsequent rate of H2 evolution. A key finding of our study reveals that the dissociation of H2O into HO and O molecules significantly enhances both the optical absorbance and conductance of the nanosheet compared to its pristine state. These results underscore the potential of g-C3N4 nanosheets as effective materials for water splitting applications.

cond-mat.mtrl-sci↗

arXiv2026

PracRepair: LLM-Empowered Automated Program Repair Inspired by Human-Like Debugging Practices

As software systems grow in scale and complexity, debugging and repair remain costly and time-consuming. Large language models (LLMs) have advanced automated program repair (APR), but existing LLM-based APR approaches still largely rely on static or retrieved context, error messages, and coarse-grained validation outcomes. As a result, they underutilize dynamic information for failure understanding and repair, including failure-execution dynamics and patch-validation dynamics. Effectively leveraging such information, however, is challenging: failure-execution traces are large and noisy, raw static-dynamic context is not self-explanatory, and patch-validation dynamics are often reduced to coarse feedback. To address these challenges, we propose \textsc{PracRepair}, a fully automated LLM-based APR framework inspired by human-like debugging practices. \textsc{PracRepair} constructs an on-demand static-dynamic context from buggy programs and failure executions, performs question-driven failure diagnosis to formulate explicit repair hypotheses, and iteratively refines candidate patches using validation diagnostics and trace-level behavioral changes. Experimental results on Defects4J V1.2 and V2.0 show that \textsc{PracRepair} consistently outperforms state-of-the-art baselines. Specifically, under GPT-3.5, \textsc{PracRepair} correctly fixes 139/136 bugs on Defects4J V1.2/V2.0, while under GPT-4o it further improves to 162/171. Moreover, \textsc{PracRepair} generalizes effectively to RWB (Real-World Bugs), achieving the best performance across multiple foundation models.

cs.SE↗

arXiv2026

LLM-Based Synthetic Ground Truth Generation for Audio-Based Emotion Classification via In-Context Learning

Understanding human states and interaction dynamics is a core goal of human-computer interaction (HCI). As interaction paradigms become more immersive, virtual reality (VR) has emerged as a powerful platform for studying collaborative work. In such settings, evaluating team collaboration states, including team performance and team resilience, requires continuous and reliable inference of latent team-level cognitive and affective states from multi-modal sensor data, such as speech signals. However, generating ground truth labels for these latent states remains challenging due to sensor-induced noise, contextual variability, and sparse expert annotations. Traditional self-reporting approaches provide only static and delayed measurements and are therefore insufficient for capturing dynamic team processes reflected in continuous speech data. In this work, we propose a large language model (LLM)-driven, agentic inference workflow for automated emotion-related synthetic ground truth generation from streaming speech data in multi-user VR environments. Leveraging the generalization capabilities of LLMs, we use In-Context Learning (ICL) with few-shot demonstrations of paired audio-based samples and their corresponding transcriptions. ICL tends to achieve task adaptation comparable to model fine-tuning while circumventing the computational overhead of parameter updates. To construct informative and robust in-context prompts, we adopt a retrieval-based selection strategy that dynamically identifies relevant audio demonstrations based on similarity in the acoustic feature space.

cs.SD↗

arXiv2026

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation

The rise of AI-generated images (AIGIs) poses growing challenges for digital authenticity, prompting the need for efficient, generalizable image forgery detection systems. Existing methods, whether non-LLM-based or LLM-based, exhibit distinct advantages and limitations. While non-LLM-based models offer efficient low-level artifact detection, they often lack semantic understanding. Conversely, LLM-based methods provide strong semantic reasoning and explainability but are computationally intensive and less sensitive to subtle visual artifacts. Moreover, the true contribution of explanatory reasoning texts to forgery detection performance remains unclear. In this work, we investigate the intrinsic value and potential of LLM-generated reasoning texts, considering it a source of generalization and semantic-error sensitivity. Based on these findings, we propose ReAlign, a novel framework that distills high-quality reasoning texts generated by a GRPO-optimized LLM into a lightweight AIGI detector via contrastive learning. ReAlign effectively inherits the generalization ability and semantic sensitivity capability of reasoning textual representations, while remaining efficient and lightweight for deployment. Moreover, ReAlign adopts a tailored joint optimization strategy that integrates contrastive loss for image-text alignment and classification loss for accurate forgery discrimination. Experimental results on AIGCDetectBenchmark, AIGI-Holmes, and our newly constructed UltraSynth-10k demonstrate that ReAlign consistently outperforms existing state-of-the-art detectors in both accuracy and generalization, particularly when facing complex, high-fidelity forgeries from modern generative models.

cs.CV↗

arXiv2026

GenShield: Unified Detection and Artifact Correction for AI-Generated Images

Diffusion-based image synthesis has made AI-generated images (AIGI) increasingly photorealistic, raising urgent concerns about authenticity in applications such as misinformation detection, digital forensics, and content moderation. Despite the substantial advances in AIGI detection, how to correct detected AI-generated images with visible artifacts and restore realistic appearance remains largely underexplored. Moreover, few existing work has established the connection between AIGI detection and artifact correction. To fill this gap, we propose GenShield, a unified autoregressive framework that jointly performs explainable AIGI detection and controllable artifact correction in a closed loop from diagnosis to restoration, revealing a mutually reinforcing relationship between these two tasks. We further introduce a Visual Chain-of-Thought based curriculum learning strategy that enables self-explained, multi-step ``diagnose-then-repair'' correction with an explicit stopping criterion. A high-quality dataset with large-scale ``artifact-restored'' pairs is also constructed alongside a unified evaluation pipeline. Extensive experiments on our correction benchmark and mainstream AIGI detection benchmarks demonstrate state-of-the-art performance and strong generalization of our method. The code is available at https://github.com/zhipeixu/GenShield.

cs.CV↗

arXiv2026

NeocorRAG: Less Irrelevant Information, More Explicit Evidence, and More Effective Recall via Evidence Chains

Although precise recall is a core objective in Retrieval-Augmented Generation (RAG), a critical oversight persists in the field: improvements in retrieval performance do not consistently translate to commensurate gains in downstream reasoning. To diagnose this gap, we propose the Recall Conversion Rate (RCR), a novel evaluation metric to quantify the contribution of retrieval to reasoning accuracy. Our quantitative analysis of mainstream RAG methods reveals that as Recall@5 improves, the RCR exhibits a near-linear decay. We identify the neglect of retrieval quality in these methods as the underlying cause. In contrast, approaches that focus solely on quality optimization often suffer from inferior recall performance. Both categories lack a comprehensive understanding of retrieval quality optimization, resulting in a trade-off dilemma. To address these challenges, we propose comprehensive retrieval quality optimization criteria and introduce the NeocorRAG framework. This framework achieves holistic retrieval quality optimization by systematically mining and utilizing Evidence Chains. Specifically, NeocorRAG first employs an innovative activated search algorithm to obtain a refined candidate space. Then it ensures precise evidence chain generation through constrained decoding. Finally, the retrieved set of evidence chains guides the retrieval optimization process. Evaluated on benchmarks including HotpotQA, 2WikiMultiHopQA, MuSiQue, and NQ, NeocorRAG achieves SOTA performance on both 3B and 70B parameter models, while consuming less than 20% of tokens used by comparable methods. This study presents an efficient, training-free paradigm for RAG enhancement that effectively optimizes retrieval quality while maintaining high recall. Our code is released at https://github.com/BUPT-Reasoning-Lab/NeocorRAG.

cs.IR↗

arXiv2026

WebMAC: A Multi-Agent Collaborative Framework for Scenario Testing of Web Systems

Scenario testing is an important technique for detecting errors in web systems. Testers draft test scenarios and convert them into test scripts for execution. Early methods relied on testers to convert test scenarios into test scripts. Recent LLM-based scenario testing methods can generate test scripts from natural language descriptions of test scenarios. However, these methods are not only limited by the incompleteness of descriptions but also overlook test adequacy criteria, making it difficult to detect potential errors. To address these limitations, this paper proposes WebMAC, a multi-agent collaborative framework for scenario testing of web systems. WebMAC can complete natural language descriptions of test scenarios through interactive clarification and transform adequate instantiated test scenarios via equivalence class partitioning. WebMAC consists of three multi-agent modules, responsible respectively for completing natural language descriptions of test scenarios, transforming test scenarios, and converting test scripts. We evaluated WebMAC on four web systems. Compared with the SOTA method, WebMAC improves the execution success rate of generated test scripts by 30%-60%, increases testing efficiency by 29%, and reduces token consumption by 47.6%. Furthermore, WebMAC can effectively detect more errors in web systems.

cs.SE↗

arXiv2026

SemFuzz: A Semantics-Aware Fuzzing Framework for Network Protocol Implementations

Network protocols are the foundation of modern communication, yet their implementations often contain semantic vulnerabilities stemming from inadequate understanding of specification semantics. Existing gray-box and black-box testing approaches lack semantic modeling of protocols, making it difficult to precisely express testing intent and cover boundary conditions. Moreover, they typically rely on coarse-grained oracles such as crashes, which are inadequate for identifying deep semantic vulnerabilities. To address these limitations, we present a semantics-aware fuzzing framework, SemFuzz. The framework leverages large language models to extract structured semantic rules from RFC documents and generates test cases that intentionally violate these rules to encode specific testing intents. It then detects deep semantic vulnerabilities by comparing the observed responses with the expected ones. Evaluation on seven widely deployed protocol implementations shows that SemFuzz identified sixteen potential vulnerabilities, ten of which have been confirmed. Among the confirmed vulnerabilities, five were previously unknown and four have been assigned CVEs. These results demonstrate the effectiveness of SemFuzz in detecting semantic vulnerabilities.

cs.CR↗

arXiv2026

Cross-sectional helium irradiation reveals interface-controlled bubble evolution in Cr/CrAlSiN multilayer coatings on zirconium alloys

The irradiation stability of Cr based protective coatings on zirconium alloys is critical for the development of accident-tolerant fuel claddings. However, conventional surface irradiation often produces shallow, nonuniform damage, obscuring interfacial behavior. In this study, we perform cross-sectional He irradiation to directly examine the interfacial response and He bubble evolution across Cr monolayer and Cr and CrAlSiN multilayer coatings on Zr substrates. Irradiation was carried out at 500 C and 750 C to doses of 2 and 3 dpa, enabling a direct comparison of temperature-dependent microstructural evolution. In the Cr monolayer, He implantation produced a homogeneous distribution of nanoscale bubbles throughout the damaged region and large cavities at the Cr and Zr interface, indicating severe Kirkendall-type voiding and interfacial decohesion at elevated temperature. In contrast, the Cr/CrAlSiN multilayer exhibited a periodically modulated bubble distribution, with bubble fragmentation and transformation into nanoscale platelets at CrAlSiN interfaces. A N-enriched Zr(N) interlayer formed spontaneously at the CrAlSiN and Zr interface, effectively suppressing bubble accumulation and interdiffusion. The nanochannel interfaces acted as He sinks and diffusion barriers, enhancing interfacial bonding and mitigating swelling. This work demonstrates that cross-sectional ion irradiation is a powerful approach for probing interfacial stability in multilayer systems, offering new insights into He-defect interactions and radiation tolerance engineering at buried interfaces. The findings highlight the potential of Cr and CrAlSiN multilayers as advanced coating architectures for high-temperature nuclear environments.

cond-mat.mtrl-sci↗

arXiv2025

Seeing to Act, Prompting to Specify: A Bayesian Factorization of Vision Language Action Policy

The pursuit of out-of-distribution generalization in Vision-Language-Action (VLA) models is often hindered by catastrophic forgetting of the Vision-Language Model (VLM) backbone during fine-tuning. While co-training with external reasoning data helps, it requires experienced tuning and data-related overhead. Beyond such external dependencies, we identify an intrinsic cause within VLA datasets: modality imbalance, where language diversity is much lower than visual and action diversity. This imbalance biases the model toward visual shortcuts and language forgetting. To address this, we introduce BayesVLA, a Bayesian factorization that decomposes the policy into a visual-action prior, supporting seeing-to-act, and a language-conditioned likelihood, enabling prompt-to-specify. This inherently preserves generalization and promotes instruction following. We further incorporate pre- and post-contact phases to better leverage pre-trained foundation models. Information-theoretic analysis formally validates our effectiveness in mitigating shortcut learning. Extensive experiments show superior generalization to unseen instructions, objects, and environments compared to existing methods. Project page is available at: https://xukechun.github.io/papers/BayesVLA.

cs.RO↗

arXiv2025

Domain-constrained Synthesis of Inconsistent Key Aspects in Textual Vulnerability Descriptions

Textual Vulnerability Descriptions (TVDs) are crucial for security analysts to understand and address software vulnerabilities. However, the key aspect inconsistencies in TVDs from different repositories pose challenges for achieving a comprehensive understanding of vulnerabilities. Existing approaches aim to mitigate inconsistencies by aligning TVDs with external knowledge bases, but they often discard valuable information and fail to synthesize comprehensive representations. In this paper, we propose a domain-constrained LLM-based synthesis framework for unifying key aspects of TVDs. Our framework consists of three stages: 1) Extraction, guided by rule-based templates to ensure all critical details are captured; 2) Self-evaluation, using domain-specific anchor words to assess semantic variability across sources; and 3) Fusion, leveraging information entropy to reconcile inconsistencies and prioritize relevant details. This framework improves synthesis performance, increasing the F1 score for key aspect augmentation from 0.82 to 0.87, while enhancing comprehension and efficiency by over 30\%. We further develop Digest Labels, a practical tool for visualizing TVDs, which human evaluations show significantly boosts usability.

cs.SE↗

arXiv2025

Dissociative Mechanism from NH3 and CH4 on Ni-Doped Graphene: Tuning Electronic and Optical Properties

In this study, we employ a multi-scale computational modeling approach, combining density functional theory (DFT) and self-consistent charge density functional tight binding (SCC-DFTB), to investigate hydrogen (H2) production and dissociation mechanisms from ammonia (NH3) and methane (CH4) on pristine and nickel-doped graphene. These two-dimensional materials hold significant potential for applications in advanced gas sensing and catalysis. Our analysis reveals that Ni-doped graphene, validated through work function calculations, is a promising material for gas separation and hydrogen production. The samples with adsorbed molecules are characterized by calculating chemical potential, chemical hardness, electronegativity, electrophilicity, vibrational frequencies, adsorbtion and Gibbs energies by DFT calculations. Methane molecules preferentially adsorb at the hexagonal ring centers of graphene, while ammonia inter-acts more strongly with carbon atoms, highlighting distinct molecular doping mechanisms for CH4 and NH3. Dynamic simulations show that CH4 splits into CH3+H, with Ni-doped graphene facilitating enhanced hydrogen transmission, while NH3 dissociates into NH2+H, which may lead to N2H4 formation. Our non-equilibrium Green's function (NEGF) simulations demonstrate increased H-atom transmission on Ni-doped graphene during gas interactions. These findings suggest that Ni-doped graphene is superior to pristine graphene for applications in gas separation, hydrogen production, and high-sensitivity sensors.

cond-mat.mtrl-sci↗

arXiv2025

CoNi-MOF laccase-like nanozymes prepared by dielectric barrier discharge plasma for treatment of antibiotic pollution

Laccase is a natural green catalyst and utilized in pollution treatment. Nevertheless, its practical application is constrained by limitations including high cost, poor stability, and difficulties in recovery. Herein, with inspiration from catalytic mechanism of natural laccase, we designed and prepared a bimetallic metal-organic framework, namely, CoNi-MOF, using low-temperature plasma (LTP) technology. We employed dielectric barrier discharge (DBD) plasma to prepare CoNi-MOF, and by precisely modulating the N2/O2 gas ratio, we could modulate the distribution concentration of oxygen vacancies in CoNi-MOF. Experimental investigations and density functional theory (DFT) calculations elucidated that the critical role of the oxygen vacancies in enhancing the laccase-like activity, which promoted the activation of molecular oxygen (O2) for generation of reactive oxygen species (ROS). Compared to natural laccase, CoNi-MOF exhibited superior catalytic performance in the degradation of antibiotic tetracycline (TC), along with enhanced resistance to harsh environmental conditions, improved stability, and low biotoxicity. Notably, aeration increased the dissolved oxygen (DO) content, further improving the TC degradation efficiency. As such, this study not only proposes a facile and efficient low-temperature plasma technology for synthesizing high-performance laccase-like nanozymes but also provides a promising and environmentally friendly strategy for the remediation of antibiotic contamination in the environment.

cond-mat.mtrl-sci↗

arXiv2025

Facet Specific Electron Conduction in Pentavalent (W5+) WO3 Drives Superior Photocatalytic CO 2 Reduction in (002) Plane

This article reports a concept of heat-induced topological modifications of non-layered WO 3 followed by successful synthesis of oxygen-vacant more-porous nanosheets with exposed active (002) facet. Experimental measurements and Density Functional Theory (DFT) calculations have revealed that the photoexcited electrons are found to accumulate preferentially on (002) facet to yield enhanced electron conduction, and consequently, strengthen the reduction potential as active catalytic sites for photocatalytic CO2 reduction. Owing to these beneficial properties, the more-porous nanosheets of WO 3 with (002) facet have exhibited superior performance than that of less-porous nanosheets of WO3 with (220) facet and bulk WO3 with (205) facet. This study therefore provides a new understanding of regulating physical, optical, and electronic properties through intricate atomic structure modulation of WO3, and may find widespread application in optoelectronics, sensors, and energy conversion.

cond-mat.mtrl-sci↗

arXiv2025

UniShield: An Adaptive Multi-Agent Framework for Unified Forgery Image Detection and Localization

With the rapid advancements in image generation, synthetic images have become increasingly realistic, posing significant societal risks, such as misinformation and fraud. Forgery Image Detection and Localization (FIDL) thus emerges as essential for maintaining information integrity and societal security. Despite impressive performances by existing domain-specific detection methods, their practical applicability remains limited, primarily due to their narrow specialization, poor cross-domain generalization, and the absence of an integrated adaptive framework. To address these issues, we propose UniShield, the novel multi-agent-based unified system capable of detecting and localizing image forgeries across diverse domains, including image manipulation, document manipulation, DeepFake, and AI-generated images. UniShield innovatively integrates a perception agent with a detection agent. The perception agent intelligently analyzes image features to dynamically select suitable detection models, while the detection agent consolidates various expert detectors into a unified framework and generates interpretable reports. Extensive experiments show that UniShield achieves state-of-the-art results, surpassing both existing unified approaches and domain-specific detectors, highlighting its superior practicality, adaptiveness, and scalability.

cs.CV↗

arXiv2025

Si-Substituted MAX Phases and In-Situ Formation of Si-coated MXene Composites via Chlorosilane Etching

Silicon-based MAX phases are a promising class of layered ceramics with superior thermal and chemical stability. However, their synthesis remains challenging due to inherent thermodynamic instability at high temperatures. Herein, we develop a general top-down strategy to synthesize a broad family of Si-substituted MAX phases (M = Ti, V, Nb, Ta, Cr; X = C, N) by reacting Al-based MAX precursors with SiCl4 vapor. This approach not only circumvents traditional high-temperature limitations but also enables precise A-site defect engineering, resulting in phases with controlled vacancy concentrations (e.g., Nb2Si3/4C and Nb2Si1/2C). Furthermore, we introduce a redox potential-based model that rationalizes the reaction pathway. Using Tin+1AlXn etched with SiCl4 as an example, the process simultaneously forms Cl-terminated MXene (Mn+1XnCl2) and amorphous nano-Si, enabling the one-step synthesis of Si-coated MXene composites. This methodology provides new avenues for designing advanced MAX phases and MXene-based hybrids with tailored functionalities for applications in energy storage and catalysis.

cond-mat.mtrl-sci↗