SearcharxivSearch

arXiv subjects

Haoxuan Zhang

Publications and source records attributed to Haoxuan Zhang.

14 recordsLinked to original sources

A physics-enhanced bidirectional multi-order graph fusion network for interpretable bearing remaining useful life prediction

Accurate prediction of bearing remaining useful life (RUL) is a key challenge for intelligent maintenance. Although deep learning-based prediction methods have showed effectiveness, existing methods still have limitations in learning nonlinear bearing degradation processes and model interpretability. Especially in engineering applications, the "black box" nature of deep learning models can easily raise concerns about their reliability. Therefore, we propose a physics-enhanced bidirectional multi-order graph fusion network for interpretable bearing RUL prediction. Our network mines complementary information from both forward and backward degradation sequences. Specifically, our network introduces a multi-order graph propagator to capture the local-global degradation dependencies. A gated cross-fusion mechanism is further designed to dynamically balance the feature contributions from both forward and backward directions. Then, our network stores representative historical degradation prototypes in dynamic memory, so that the final RUL prediction no longer depends solely on the current latent features, but is guided by reusable historical degradation knowledge. To reveal how our model learns the nonlinear degradation process, the feature mapping parts utilize the Kolmogorov-Arnold network, which allows the nonlinear mapping to be visualized using learnable functions. Finally, a physics-enhanced dynamic loss function is developed to help our network learn effective and reliable degradation representations. Extensive experiments on two public datasets show that our method achieves the lowest error while providing more conservative estimates than existing methods. Our code is available at https://github.com/IMGresearcher/PE-BMGN.

cs.CE

Evolving Roles of LLMs in Scientific Innovation: Assistant, Collaborator, Scientist, and Evaluator

Large language models (LLMs) are increasingly used in scientific research and discovery, supporting tasks ranging from literature retrieval and synthesis to hypothesis generation, autonomous experimentation, and research evaluation. Existing surveys often conflate scientific research with scientific discovery and typically organize systems by domain, task, or autonomy level alone. In this survey, we propose a four-role framework for understanding LLMs in scientific innovation: Assistant, Collaborator, Scientist, and Evaluator. The framework integrates three complementary dimensions: autonomy level, cognitive function, and scientific innovation, to distinguish research-oriented support from frontier-oriented discovery. We review representative methods, benchmarks, and evaluation practices for each role, examining their capabilities, limitations, and human oversight requirements. Across the literature, Assistant systems are comparatively mature in retrieval and synthesis but remain unreliable in open-ended applications; Collaborator systems expand the space of candidate hypotheses yet struggle with novelty-grounding trade-offs; Scientist systems increasingly automate research workflows but face reliability and safety bottlenecks; and Evaluator systems support review and verification while remaining weak in novelty assessment. We argue that progress in AI for science depends not only on model capability, but also on evaluation, oversight, accountability, and institutional integration.

cs.DL

LongSumEval: Question-Answering Based Evaluation and Feedback-Driven Refinement for Long Document Summarization

Evaluating long document summaries remains the primary bottleneck in summarization research. Existing metrics correlate weakly with human judgments and produce aggregate scores without explaining deficiencies or guiding improvement, preventing effective refinement in applications requiring verifiable accuracy. We introduce LongSumEval, a unified framework bridging evaluation and generation through structured question-answering feedback. The framework operationalizes summary quality as answerability and factual alignment of question-answer pairs, generating interpretable scores and actionable feedback that identifies coverage gaps and factual inconsistencies. This resolves the misalignment where evaluation operates independently of generation objectives. Meta-evaluation of our QA-based evaluation module across seven benchmarks demonstrates substantially stronger agreement with human judgments compared to established metrics. Structured feedback enables significant quality improvements through self-refinement without retraining. By demonstrating that evaluation feedback can serve as executable instructions for generation, this work establishes a generalizable paradigm for aligning assessment with improvement, with direct implications for controllable text generation requiring verifiable accuracy and transparent quality control. All code and datasets will be released in GitHub for reproducibility.

cs.CL

LLM-ReSum: A Framework for LLM Reflective Summarization through Self-Evaluation

Reliable evaluation of large language model (LLM)-generated summaries remains an open challenge, particularly across heterogeneous domains and document lengths. We conduct a comprehensive meta-evaluation of 14 automatic summarization metrics and LLM-based evaluators across seven datasets spanning five domains, covering documents from short news articles to long scientific, governmental, and legal texts (2K-27K words) with over 1,500 human-annotated summaries. Our results show that traditional lexical overlap metrics (e.g., ROUGE, BLEU) exhibit weak or negative correlation with human judgments, while task-specific neural metrics and LLM-based evaluators achieve substantially higher alignment, especially for linguistic quality assessment. Leveraging these findings, we propose LLM-ReSum, a self-reflective summarization framework that integrates LLM-based evaluation and generation in a closed feedback loop without model finetuning. Across three domains, LLM-ReSum improves low-quality summaries by up to 33% in factual accuracy and 39% in coverage, with human evaluators preferring refined summaries in 89% of cases. We additionally introduce PatentSumEval, a new human-annotated benchmark for legal document summarization comprising 180 expert-evaluated summaries. All code and datasets will be released in GitHub.

cs.CL

MetaGAI: A Large-Scale and High-Quality Benchmark for Generative AI Model and Data Card Generation

The rapid proliferation of Generative AI necessitates rigorous documentation standards for transparency and governance. However, manual creation of Model and Data Cards is not scalable, while automated approaches lack large-scale, high-fidelity benchmarks for systematic evaluation. We introduce MetaGAI, a comprehensive benchmark comprising 2,541 verified document triplets constructed through semantic triangulation of academic papers, GitHub repositories, and Hugging Face artifacts. Unlike prior single-source datasets, MetaGAI employs a multi-agent framework with specialized Retriever, Generator, and Editor agents, validated through four-dimensional human-in-the-loop assessment, including human evaluation of editor-refined ground truth. We establish a robust evaluation protocol combining automated metrics with validated LLM-as-a-Judge frameworks. Extensive analysis reveals that sparse Mixture-of-Experts architectures achieve superior cost-quality efficiency, while a fundamental trade-off exists between faithfulness and completeness. MetaGAI provides a foundational testbed for benchmarking, training, and analyzing automated Model and Data Card generation methods at scale. Our data and code are available at: https://github.com/haoxuan-unt2024/MetaGAI-Benchmark.

cs.AI

Chip-based f-2f interferometry in periodically tapered lithium niobate nanophotonic waveguides

Nanophotonic supercontinuum generation offers a practical route to chip-based f-2f interferometry by leveraging coexisting chi(2) and chi(3) nonlinearities. In conventional uniform waveguides, the phase-matching bandwidth for second-harmonic generation (SHG) is intrinsically narrow, restricting the spectral overlap factor for heterodyne beating. To address this limitation, we introduce a periodically-tapered nanophotonic waveguide made from MgO-doped, z-cut thin-film lithium niobate for energy-efficient and fabrication-robust f-2f operation. By adiabatically varying the waveguide width within a dual phase-matching window that supports concurrent dispersive wave (DW) emission and SHG, we routinely achieved a broad spectral overlap between the SHG and DW components. This capability enables robust detection of the carrier-envelope offset frequency (fceo) at substantially lower pulse energies than that in uniform-waveguide approaches. We further developed a compact waveguide module that operates reliably under temperature fluctuations and is capable of interfacing with high-repetition-rate (500 MHz) mode-locked lasers, enabling detection and phase locking of fceo with a signal-to-noise ratio of 48 dB. These results highlight the potential of nanophotonic chips for developing compact, field-deployable frequency comb systems.

physics.optics

AdaQE-CG: Adaptive Query Expansion for Web-Scale Generative AI Model and Data Card Generation

Transparent and standardized documentation is essential for building trustworthy generative AI (GAI) systems. However, existing automated methods for generating model and data cards still face three major challenges: (i) static templates, as most systems rely on fixed query templates that cannot adapt to diverse paper structures or evolving documentation requirements; (ii) information scarcity, since web-scale repositories such as Hugging Face often contain incomplete or inconsistent metadata, leading to missing or noisy information; and (iii) lack of benchmarks, as the absence of standardized datasets and evaluation protocols hinders fair and reproducible assessment of documentation quality. To address these limitations, we propose AdaQE-CG, an Adaptive Query Expansion for Card Generation framework that combines dynamic information extraction with cross-card knowledge transfer. Its Intra-Paper Extraction via Context-Aware Query Expansion (IPE-QE) module iteratively refines extraction queries to recover richer and more complete information from scientific papers and repositories, while its Inter-Card Completion using the MetaGAI Pool (ICC-MP) module fills missing fields by transferring semantically relevant content from similar cards in a curated dataset. In addition, we introduce MetaGAI-Bench, the first large-scale, expert-annotated benchmark for evaluating GAI documentation. Comprehensive experiments across five quality dimensions show that AdaQE-CG substantially outperforms existing approaches, exceeds human-authored data cards, and approaches human-level quality for model cards. Code, prompts, and data are publicly available at: https://github.com/haoxuan-unt2024/AdaQE-CG.

cs.AI

Paired Image Generation with Diffusion-Guided Diffusion Models

The segmentation of mass lesions in digital breast tomosynthesis (DBT) images is very significant for the early screening of breast cancer. However, the high-density breast tissue often leads to high concealment of the mass lesions, which makes manual annotation difficult and time-consuming. As a result, there is a lack of annotated data for model training. Diffusion models are commonly used for data augmentation, but the existing methods face two challenges. First, due to the high concealment of lesions, it is difficult for the model to learn the features of the lesion area. This leads to the low generation quality of the lesion areas, thus limiting the quality of the generated images. Second, existing methods can only generate images and cannot generate corresponding annotations, which restricts the usability of the generated images in supervised training. In this work, we propose a paired image generation method. The method does not require external conditions and can achieve the generation of paired images by training an extra diffusion guider for the conditional diffusion model. During the experimental phase, we generated paired DBT slices and mass lesion masks. Then, we incorporated them into the supervised training process of the mass lesion segmentation task. The experimental results show that our method can improve the generation quality without external conditions. Moreover, it contributes to alleviating the shortage of annotated data, thus enhancing the performance of downstream tasks. The source code is available at https://github.com/zhanghx1320/PIG.

cs.CV

ReviewGuard: Enhancing Deficient Peer Review Detection via LLM-Driven Data Augmentation

Peer review serves as the gatekeeper of science, yet the surge in submissions and widespread adoption of large language models (LLMs) in scholarly evaluation present unprecedented challenges. While recent work has focused on using LLMs to improve review efficiency, unchecked deficient reviews from both human experts and AI systems threaten to systematically undermine academic integrity. To address this issue, we introduce ReviewGuard, an automated system for detecting and categorizing deficient reviews through a four-stage LLM-driven framework: data collection from ICLR and NeurIPS on OpenReview, GPT-4.1 annotation with human validation, synthetic data augmentation yielding 6,634 papers with 24,657 real and 46,438 synthetic reviews, and fine-tuning of encoder-based models and open-source LLMs. Feature analysis reveals that deficient reviews exhibit lower rating scores, higher self-reported confidence, reduced structural complexity, and more negative sentiment than sufficient reviews. AI-generated text detection shows dramatic increases in AI-authored reviews since ChatGPT's emergence. Mixed training with synthetic and real data substantially improves detection performance - for example, Qwen 3-8B achieves recall of 0.6653 and F1 of 0.7073, up from 0.5499 and 0.5606 respectively. This study presents the first LLM-driven system for detecting deficient peer reviews, providing evidence to inform AI governance in peer review. Code, prompts, and data are available at https://github.com/haoxuan-unt2024/ReviewGuard

cs.CL

Unveiling the Merits and Defects of LLMs in Automatic Review Generation for Scientific Papers

The surge in scientific submissions has placed increasing strain on the traditional peer-review process, prompting the exploration of large language models (LLMs) for automated review generation. While LLMs demonstrate competence in producing structured and coherent feedback, their capacity for critical reasoning, contextual grounding, and quality sensitivity remains limited. To systematically evaluate these aspects, we propose a comprehensive evaluation framework that integrates semantic similarity analysis and structured knowledge graph metrics to assess LLM-generated reviews against human-written counterparts. We construct a large-scale benchmark of 1,683 papers and 6,495 expert reviews from ICLR and NeurIPS in multiple years, and generate reviews using five LLMs. Our findings show that LLMs perform well in descriptive and affirmational content, capturing the main contributions and methodologies of the original work, with GPT-4o highlighted as an illustrative example, generating 15.74% more entities than human reviewers in the strengths section of good papers in ICLR 2025. However, they consistently underperform in identifying weaknesses, raising substantive questions, and adjusting feedback based on paper quality. GPT-4o produces 59.42% fewer entities than real reviewers in the weaknesses and increases node count by only 5.7% from good to weak papers, compared to 50% in human reviews. Similar trends are observed across all conferences, years, and models, providing empirical foundations for understanding the merits and defects of LLM-generated reviews and informing the development of future LLM-assisted reviewing tools. Data, code, and more detailed results are publicly available at https://github.com/RichardLRC/Peer-Review.

cs.CL

Cooperative Payload Estimation by a Team of Mocobots

For high-performance autonomous manipulation of a payload by a mobile manipulator team, or for collaborative manipulation with the human, robots should be able to discover where other robots are attached to the payload, as well as the payload's mass and inertial properties. In this paper, we describe a method for the robots to autonomously discover this information. The robots cooperatively manipulate the payload, and the twist, twist derivative, and wrench data at their grasp frames are used to estimate the transformation matrices between the grasp frames, the location of the payload's center of mass, and the payload's inertia matrix. The method is validated experimentally with a team of three mobile cobots, or mocobots.

cs.RO

PINN-MG: A physics-informed neural network for mesh generation

In numerical simulation, structured mesh generation often requires a lot of time and manpower investment. The general scheme for structured quad mesh generation is to find a mapping between the computational domain and the physical domain. This mapping can be obtained by solving partial differential equations. However, existing structured mesh generation methods are difficult to ensure both efficiency and mesh quality. In this paper, we propose a structured mesh generation method based on physics-informed neural network, PINN-MG. It takes boundary curves as input and then utilizes an attention network to capture the potential mapping between computational and physical domains, generating structured meshes for the input physical domain. PINN-MG introduces the Navier-Lamé equation in linear elastic as a partial differential equation term in the loss function, ensuring that the neural network conforms to the law of elastic body deformation when optimizing the loss value. The training process of PINN-MG is completely unsupervised and does not require any prior knowledge or datasets, which greatly reduces the previous workload of producing structured mesh datasets. Experimental results show that PINN-MG can generate higher quality structured quad meshes than other methods, and has the advantages of traditional algebraic methods and differential methods.

cs.CE

Estimating Factor-Based Spot Volatility Matrices with Noisy and Asynchronous High-Frequency Data

We propose a new estimator of high-dimensional spot volatility matrices satisfying a low-rank plus sparse structure from noisy and asynchronous high-frequency data collected for an ultra-large number of assets. The noise processes are allowed to be temporally correlated, heteroskedastic, asymptotically vanishing and dependent on the efficient prices. We define a kernel-weighted pre-averaging method to jointly tackle the microstructure noise and asynchronicity issues, and we obtain uniformly consistent estimates for latent prices. We impose a continuous-time factor model with time-varying factor loadings on the price processes, and estimate the common factors and loadings via a local principal component analysis. Assuming a uniform sparsity condition on the idiosyncratic volatility structure, we combine the POET and kernel-smoothing techniques to estimate the spot volatility matrices for both the latent prices and idiosyncratic errors. Under some mild restrictions, the estimated spot volatility matrices are shown to be uniformly consistent under various matrix norms. We provide Monte-Carlo simulation and empirical studies to examine the numerical performance of the developed estimation methodology.

econ.EM

MQENet: A Mesh Quality Evaluation Neural Network Based on Dynamic Graph Attention

With the development of computational fluid dynamics, the requirements for the fluid simulation accuracy in industrial applications have also increased. The quality of the generated mesh directly affects the simulation accuracy. However, previous mesh quality metrics and models cannot evaluate meshes comprehensively and objectively. To this end, we propose MQENet, a structured mesh quality evaluation neural network based on dynamic graph attention. MQENet treats the mesh evaluation task as a graph classification task for classifying the quality of the input structured mesh. To make graphs generated from structured meshes more informative, MQENet introduces two novel structured mesh preprocessing algorithms. These two algorithms can also improve the conversion efficiency of structured mesh data. Experimental results on the benchmark structured mesh dataset NACA-Market show the effectiveness of MQENet in the mesh quality evaluation task.

cs.CE