arXiv subjects

Juan Du

Publications and source records attributed to Juan Du.

At least 19 recordsLinked to original sources

arXiv2026

Open-Source Autonomous Driving System Analysis and Multi-Disciplinary Hardware-in-the-Loop Research Paradigm with Reinforcement-Learning Testing and Large Language Models

Open-source autonomous driving systems provide an inspectable software foundation for intelligent vehicle research. Under real-vehicle deployment conditions, the recording and review of experimental conditions are important for interpreting system behavior and reusing experimental results. However, in a shared real-vehicle environment involving multiple vehicles, task processes, code modifications, and hardware testing feedback are often distributed across different teams and experimental stages, making it challenging to maintain continuous and reviewable experimental records. To address this limitation, this paper examines an Apollo-on-Hongqi EV environment and proposes a real-vehicle experimental framework. The framework connects multi-vehicle experiments, repository-based code reuse and software-hardware testing feedback within a unified review process. Large language models and RL-based testing serve as auxiliary components for record organization, anomaly summarization, and simulation-based candidate scenario generation. Based on this setting, this paper analyzes preliminary evidence from multi-vehicle collaborative experimentation, code and experimental-skill sharing, and software-hardware collaborative testing. The analysis shows that experimental records can be examined together with their operating conditions, providing a reviewable basis for Apollo-on-Hongqi EV research.

cs.SE↗

arXiv2026

Superconducting $T_\mathrm{c}$ up to 20.6 K in bulk YSi$_2$ and YSi$_2$/Si superlattices due to chemical flattening

Currently, the fundamental building blocks of leading quantum computers are Josephson junctions, whose core is usually the superconducting Al on Si wafers. However, the transition temperature $T_\mathrm{c}$ of bulk Al ($\sim1.1$ K) is below the boiling point of liquid helium ($\sim4.2$ K), which is one of the challenges to its widespread application. Here, we propose a Si-matched AlB$_2$-type superconductor YSi$_2$ as a promising alternative to Al. The solution of anisotropic (isotropic) Migdal-Eliashberg equation without (with) anharmonicity gives $T_\mathrm{c}\sim20.6$ K ($17.2$ K), which is at the highest level in silicides. Its excellent superconductivity can be attributed mainly to the Si honeycombs, which become plane here due to the 'chemical flattening' effects of the Y atoms instead of being buckled in most silicides. We tested its thermodynamical, kinetic, dynamical, and mechanical stability by first-principles calculations. Particularly, the negative elastic stiffness constant $C_{66}$ calculated by usual methods turns positive even without the zero-point energy once the Si honeycombs are compressed below a threshold. This strain can also make its calculated lattice constants agree with the experimental ones. We propose structures to realize this strain, i.e., YSi$_2$(0001)/Si(111) superlattices, which can also strengthen the overall stability of YSi$_2$ while maintaining its $T_\mathrm{c}$ above $7.0$ K.

cond-mat.supr-con↗

arXiv2026

Tacmap: Bridging the Tactile Sim-to-Real Gap via Geometry-Consistent Penetration Depth Map

Vision-Based Tactile Sensors (VBTS) are essential for achieving dexterous robotic manipulation, yet the tactile sim-to-real gap remains a fundamental bottleneck. Current tactile simulations suffer from a persistent dilemma: simplified geometric projections lack physical authenticity, while high-fidelity Finite Element Methods (FEM) are too computationally prohibitive for large-scale reinforcement learning. In this work, we present Tacmap, a high-fidelity, computationally efficient tactile simulation framework anchored in volumetric penetration depth. Our key insight is to bridge the tactile sim-to-real gap by unifying both domains through a shared deform map representation. Specifically, we compute 3D intersection volumes as depth maps in simulation, while in the real world, we employ an automated data-collection rig to learn a robust mapping from raw tactile images to ground-truth depth maps. By aligning simulation and real-world in this unified geometric space, Tacmap minimizes domain shift while maintaining physical consistency. Quantitative evaluations across diverse contact scenarios demonstrate that Tacmap's deform maps closely mirror real-world measurements. Moreover, we validate the utility of Tacmap through an in-hand rotation task, where a policy trained exclusively in simulation achieves zero-shot transfer to a physical robot.

cs.RO↗

arXiv2026

Align3D-AD: Cross-Modal Feature Alignment and Dual-Prompt Learning for Zero-shot 3D Anomaly Detection

Zero-shot 3D anomaly detection aims to identify anomalies without access to training data from target categories. However, existing methods mainly rely on projecting 3D observations into multi-view representations that primarily capture geometric cues rather than realistic visual semantics and process them with vision encoders pretrained on RGB data, leading to a significant domain gap between the encoder and the projected representations. To address this issue, we propose Align3D-AD, a unified two-stage framework that leverages the RGB modality from auxiliary categories as cross-modal guidance for zero-shot 3D anomaly detection. First, we introduce a cross-modal feature alignment paradigm that maps rendering features into the RGB semantic space. Unlike prior works that implicitly rely on pretrained encoders, our method enables direct semantic transfer from RGB observations. A semantic consistency reweighting strategy is further introduced to refine feature alignment by reweighting local regions according to holistic semantic consistency. Second, we propose a modality-aware prompt learning framework with dual-prompt contrastive alignment. By assigning independent prompts to RGB-aligned and rendering features, our method captures complementary semantics across modalities, while the contrastive alignment further enhances prompt representations to improve discriminability. Extensive experiments on MVTec3D-AD, Eyecandies, and Real3D-AD demonstrate that Align3D-AD consistently outperforms existing zero-shot methods under both one-vs-rest and cross-dataset settings, highlighting its generalization capability and robustness. Code and the dataset will be made available once our paper is accepted.

cs.CV↗

arXiv2026

Ultrafast electron vortex produced by a grating made of light

The generation of vortex matter waves carrying quantized orbital angular momentum is challenging and relies heavily on the material nanofabrication methods due to their extremely small de-Broglie wavelengths. Here, we introduce an all-optical method for generating an electron vortex by diffraction through a grating made of light. We realize the orbital angular momentum transfer between free electrons and photons by stimulated Compton scattering. The transferred angular momentum quantum number can be freely tuned. The method can be generalized to a broad range of charged particles, neutral atoms, and molecules of diverse masses. Our results open up novel opportunities for applications in free electron lasers and ultrafast electron microscopy by utilizing the orbital angular momentum degree of freedom of free electrons.

physics.atom-ph↗

arXiv2026

FORGE: Fine-grained Multimodal Evaluation for Manufacturing Scenarios

The manufacturing sector is increasingly adopting Multimodal Large Language Models (MLLMs) to transition from simple perception to autonomous execution, yet current evaluations fail to reflect the rigorous demands of real-world manufacturing environments. Progress is hindered by data scarcity and a lack of fine-grained domain semantics in existing datasets. To bridge this gap, we introduce FORGE. Wefirst construct a high-quality multimodal dataset that combines real-world 2D images and 3D point clouds, annotated with fine-grained domain semantics (e.g., exact model numbers). We then evaluate 18 state-of-the-art MLLMs across three manufacturing tasks, namely workpiece verification, structural surface inspection, and assembly verification, revealing significant performance gaps. Counter to conventional understanding, the bottleneck analysis shows that visual grounding is not the primary limiting factor. Instead, insufficient domain-specific knowledge is the key bottleneck, setting a clear direction for future research. Beyond evaluation, we show that our structured annotations can serve as an actionable training resource: supervised fine-tuning of a compact 3B-parameter model on our data yields up to 90.8% relative improvement in accuracy on held-out manufacturing scenarios, providing preliminary evidence for a practical pathway toward domain-adapted manufacturing MLLMs. The code and datasets are available at https://ai4manufacturing.github.io/forge-web.

cs.CV↗

arXiv2026

TurboAgent: An LLM-Driven Autonomous Multi-Agent Framework for Turbomachinery Aerodynamic Design

The aerodynamic design of turbomachinery is a complex and tightly coupled multi-stage process involving geometry generation, performance prediction, optimization, and high-fidelity physical validation. Existing intelligent design approaches typically focus on individual stages or rely on loosely coupled pipelines, making fully autonomous end-to-end design challenging. To address this issue, this study proposes TurboAgent, a large language model (LLM)-driven autonomous multi-agent framework for turbomachinery aerodynamic design and optimization. The LLM serves as the core for task planning and coordination, while specialized agents handle generative design, rapid performance prediction, multi-objective optimization, and physics-based validation. The framework transforms traditional trial-and-error design into a data-driven collaborative workflow, with high-fidelity simulations retained for final verification. A transonic single-rotor compressor is used for validation. The results show strong agreement between target performance, generated designs, and CFD simulations. The coefficients of determination for mass flow rate, total pressure ratio, and isentropic efficiency all exceed 0.91, with normalized RMSE values below 8%. The optimization agent further improves isentropic efficiency by 1.61% and total pressure ratio by 3.02%. The complete workflow can be executed within approximately 30 minutes under parallel computing. These results demonstrate that TurboAgent enables an autonomous closed-loop design process from natural language requirements to final design generation, providing an efficient and scalable paradigm for turbomachinery aerodynamic design.

cs.AI↗

arXiv2026

SGANet: Semantic and Geometric Alignment for Multimodal Multi-view Anomaly Detection

Multi-view anomaly detection aims to identify surface defects on complex objects using observations captured from multiple viewpoints. However, existing unsupervised methods often suffer from feature inconsistency arising from viewpoint variations and modality discrepancies. To address these challenges, we propose a Semantic and Geometric Alignment Network (SGANet), a unified framework for multimodal multi-view anomaly detection that effectively combines semantic and geometric alignment to learn physically coherent feature representations across viewpoints and modalities. SGANet consists of three key components. The Selective Cross-view Feature Refinement Module (SCFRM) selectively aggregates informative patch features from adjacent views to enhance cross-view feature interaction. The Semantic-Structural Patch Alignment (SSPA) enforces semantic alignment across modalities while maintaining structural consistency under viewpoint transformations. The Multi-View Geometric Alignment (MVGA) further aligns geometrically corresponding patches across viewpoints. By jointly modeling feature interaction, semantic and structural consistency, and global geometric correspondence, SGANet effectively enhances anomaly detection performance in multimodal multi-view settings. Extensive experiments on the SiM3D and Eyecandies datasets demonstrate that SGANet achieves state-of-the-art performance in both anomaly detection and localization, validating its effectiveness in realistic industrial scenarios.

cs.CV↗

arXiv2026

Dislocation-ledge coupling governs semicoherent precipitate growth

Many crystalline materials acquire their properties as one crystal phase grows through another, but a long-standing defect-kinetic puzzle remains: how dense interfacial dislocation networks between two crystals advance, reorganize, and accommodate strain without relying on ordinary glide. Here, using in situ transmission electron microscopy, O-lattice analysis, and three-dimensional phase-field crystal simulations, we identify how semicoherent interfaces overcome this constraint during lath precipitate growth. In situ observations of austenite precipitates in duplex stainless steel reveal nanometer-high growth ledges propagating laterally along migrating habit planes. O-lattice analysis shows how lattice misfit prescribes a closed network across habit planes, side facets, and end faces. Simulations resolve the hidden three-dimensional dynamics: the network undergoes diffusion-assisted, non-conservative motion, producing steady end-face advance and ledge-mediated broad-facet migration while accommodating transformation strain. These results reveal a general defect-kinetic route linking point-defect transport, dislocation-network motion, interface migration, and morphology evolution.

cond-mat.mtrl-sci↗

arXiv2026

3D-SONAR: Self-Organizing Network for 3D Anomaly Ranking

Surface anomaly detection using 3D point cloud data has gained increasing attention in industrial inspection. However, most existing methods rely on deep learning techniques that are highly dependent on large-scale datasets for training, which are difficult and expensive to acquire in real-world applications. To address this challenge, we propose a novel method based on self-organizing network for 3D anomaly ranking, also named 3D-SONAR. The core idea is to model the 3D point cloud as a dynamic system, where the points are represented as an undirected graph and interact via attractive and repulsive forces. The energy distribution induced by these forces can reveal surface anomalies. Experimental results show that our method achieves superior anomaly detection performance in both open surface and closed surface without training. This work provides a new perspective on unsupervised inspection and highlights the potential of physics-inspired models in industrial anomaly detection tasks with limited data.

stat.AP↗

arXiv2025

From Pretraining to Privacy: Federated Ultrasound Foundation Model with Self-Supervised Learning

Ultrasound imaging is widely used in clinical diagnosis due to its non-invasive nature and real-time capabilities. However, traditional ultrasound diagnostics relies heavily on physician expertise and is often hampered by suboptimal image quality, leading to potential diagnostic errors. While artificial intelligence (AI) offers a promising solution to enhance clinical diagnosis by detecting abnormalities across various imaging modalities, existing AI methods for ultrasound face two major challenges. First, they typically require vast amounts of labeled medical data, raising serious concerns regarding patient privacy. Second, most models are designed for specific tasks, which restricts their broader clinical utility. To overcome these challenges, we present UltraFedFM, an innovative privacy-preserving ultrasound foundation model. UltraFedFM is collaboratively pre-trained using federated learning across 16 distributed medical institutions in 9 countries, leveraging a dataset of over 1 million ultrasound images covering 19 organs and 10 ultrasound modalities. This extensive and diverse data, combined with a secure training framework, enables UltraFedFM to exhibit strong generalization and diagnostic capabilities. It achieves an average area under the receiver operating characteristic curve (AUROC) of 0.927 for disease diagnosis and a dice similarity coefficient (DSC) of 0.878 for lesion segmentation. Notably, UltraFedFM surpasses the diagnostic accuracy of mid-level ultrasonographers (4-8 years of experience) and matches the performance of expert-level sonographers (10+ years of experience) in the joint diagnosis of 8 common systemic diseases.c These findings indicate that UltraFedFM can significantly enhance clinical diagnostics while safeguarding patient privacy, marking a significant advancement in AI-driven ultrasound imaging for future clinical applications.

eess.IV↗

arXiv2025

An Efficient Interaction Human-AI Synergy System Bridging Visual Awareness and Large Language Model for Intensive Care Units

Intensive Care Units (ICUs) are critical environments characterized by high-stakes monitoring and complex data management. However, current practices often rely on manual data transcription and fragmented information systems, introducing potential risks to patient safety and operational efficiency. To address these issues, we propose a human-AI synergy system based on a cloud-edge-end architecture, which integrates visual-aware data extraction and semantic interaction mechanisms. Specifically, a visual-aware edge module non-invasively captures real-time physiological data from bedside monitors, reducing manual entry errors. To improve accessibility to fragmented data sources, a semantic interaction module, powered by a Large Language Model (LLM), enables physicians to perform efficient and intuitive voice-based queries over structured patient data. The hierarchical cloud-edge-end deployment ensures low-latency communication and scalable system performance. Our system reduces the cognitive burden on ICU nurses and physicians and demonstrates promising potential for broader applications in intelligent healthcare systems.

cs.HC↗

arXiv2025

Double-Bridge Mechanism for Enhancing Tc in Oxide Superconductors

We propose a new double-bridge mechanism to significantly enhance $T_c$ in ionic oxide superconductors. Based on our recently proposed ionic-bond-driven O/Cu-bridged (bridge-I) pairing e$^-$-O-e$^-$/h$^+$-Cu-h$^+$ formed in the pseudogap phase ($T_c<T<T^*$), we reveal a key bridge-II Cu/O-mediated inter-pair attraction that overcomes direct Coulomb repulsion and drives coherent Bose-Einstein condensation (BEC) of preformed Cooper pairs. Within the BEC framework (Eq.(3)), $T_c$ follows the Uemura scaling $(n_{\rm pair}^{\rm 3D})^{2/3}/m_{\rm pair}^*$ or $n_{\rm pair}^{\rm 2D}/m_{\rm pair}^*$ and increases linearly with the attractive scattering length $a<0$. Strengthening bridge-II attraction, minimizing $m_{\rm pair}^*$, and optimizing $n_{\rm pair}^{\rm 3D}$ are the key to maximizing $T_c$. This double-bridge mechanism unifies the \textbf{eV-scale} strong pairing at room temperature and BEC, provides a universal route toward higher $T_c$, and guides the design of next-generation superconductors.

cond-mat.supr-con↗

arXiv2025

Diffuse to Detect: A Generalizable Framework for Anomaly Detection with Diffusion Models Applications to UAVs and Beyond

Anomaly detection in complex, high-dimensional data, such as UAV sensor readings, is essential for operational safety but challenging for existing methods due to their limited sensitivity, scalability, and inability to capture intricate dependencies. We propose the Diffuse to Detect (DTD) framework, a novel approach that innovatively adapts diffusion models for anomaly detection, diverging from their conventional use in generative tasks with high inference time. By comparison, DTD employs a single-step diffusion process to predict noise patterns, enabling rapid and precise identification of anomalies without reconstruction errors. This approach is grounded in robust theoretical foundations that link noise prediction to the data distribution's score function, ensuring reliable deviation detection. By integrating Graph Neural Networks to model sensor relationships as dynamic graphs, DTD effectively captures spatial (inter-sensor) and temporal anomalies. Its two-branch architecture, with parametric neural network-based energy scoring for scalability and nonparametric statistical methods for interpretability, provides flexible trade-offs between computational efficiency and transparency. Extensive evaluations on UAV sensor data, multivariate time series, and images demonstrate DTD's superior performance over existing methods, underscoring its generality across diverse data modalities. This versatility, combined with its adaptability, positions DTD as a transformative solution for safety-critical applications, including industrial monitoring and beyond.

cs.LG↗

arXiv2025

Dynamical phase evolution of Coulomb-focused electrons in strong-field ionization probed by a standing light wave

We investigate the dynamical phase evolution of Coulomb-focused electrons in strong-field ionization. We diffract the electrons with an ultrashort standing light wave to track their time-dependent phase. Our findings show that low-energy electrons exhibit a unique chromosome-shaped diffraction pattern, distinct from higher-energy electrons. Our numerical model quantitatively reproduces the experimental results, confirming this pattern maps the electron's time-dependent phase evolution as it escapes from a Coulomb potential. Our pulsed diffraction grating technique offers a new way to sense an electron's quantum phase without interfering its release mechanism.

physics.atom-ph↗

arXiv2025

IAENet: An Importance-Aware Ensemble Model for 3D Point Cloud-Based Anomaly Detection

Surface anomaly detection is pivotal for ensuring product quality in industrial manufacturing. While 2D image-based methods have achieved remarkable success, 3D point cloud-based detection remains underexplored despite its richer geometric cues. We argue that the key bottleneck is the absence of powerful pretrained foundation backbones in 3D comparable to those in 2D. To bridge this gap, we propose Importance-Aware Ensemble Network (IAENet), an ensemble framework that synergizes 2D pretrained expert with 3D expert models. However, naively fusing predictions from disparate sources is non-trivial: existing strategies can be affected by a poorly performing modality and thus degrade overall accuracy. To address this challenge, We introduce an novel Importance-Aware Fusion (IAF) module that dynamically assesses the contribution of each source and reweights their anomaly scores. Furthermore, we devise critical loss functions that explicitly guide the optimization of IAF, enabling it to combine the collective knowledge of the source experts but also preserve their unique strengths, thereby enhancing the overall performance of anomaly detection. Extensive experiments on MVTec 3D-AD demonstrate that our IAENet achieves a new state-of-the-art with a markedly lower false positive rate, underscoring its practical value for industrial deployment.

cs.CV↗

arXiv2025

HyPCV-Former: Hyperbolic Spatio-Temporal Transformer for 3D Point Cloud Video Anomaly Detection

Video anomaly detection is a fundamental task in video surveillance, with broad applications in public safety and intelligent monitoring systems. Although previous methods leverage Euclidean representations in RGB or depth domains, such embeddings are inherently limited in capturing hierarchical event structures and spatio-temporal continuity. To address these limitations, we propose HyPCV-Former, a novel hyperbolic spatio-temporal transformer for anomaly detection in 3D point cloud videos. Our approach first extracts per-frame spatial features from point cloud sequences via point cloud extractor, and then embeds them into Lorentzian hyperbolic space, which better captures the latent hierarchical structure of events. To model temporal dynamics, we introduce a hyperbolic multi-head self-attention (HMHA) mechanism that leverages Lorentzian inner products and curvature-aware softmax to learn temporal dependencies under non-Euclidean geometry. Our method performs all feature transformations and anomaly scoring directly within full Lorentzian space rather than via tangent space approximation. Extensive experiments demonstrate that HyPCV-Former achieves state-of-the-art performance across multiple anomaly categories, with a 7\% improvement on the TIMo dataset and a 5.6\% gain on the DAD dataset compared to benchmarks. The code will be released upon paper acceptance.

cs.CV↗

arXiv2025

G$^{2}$SF-MIAD: Geometry-Guided Score Fusion for Multimodal Industrial Anomaly Detection

Industrial quality inspection plays a critical role in modern manufacturing by identifying defective products during production. While single-modality approaches using either 3D point clouds or 2D RGB images suffer from information incompleteness, multimodal anomaly detection offers promise through the complementary fusion of crossmodal data. However, existing methods face challenges in effectively integrating unimodal results and improving discriminative power. To address these limitations, we first reinterpret memory bank-based anomaly scores in single modalities as isotropic Euclidean distances in local feature spaces. Dynamically evolving from Euclidean metrics, we propose a novel \underline{G}eometry-\underline{G}uided \underline{S}core \underline{F}usion (G$^{2}$SF) framework that progressively learns an anisotropic local distance metric as a unified score for the fusion task. Through a geometric encoding operator, a novel Local Scale Prediction Network (LSPN) is proposed to predict direction-aware scaling factors that characterize first-order local feature distributions, thereby enhancing discrimination between normal and anomalous patterns. Additionally, we develop specialized loss functions and score aggregation strategy from geometric priors to ensure both metric generalization and efficacy. Comprehensive evaluations on the MVTec-3D AD and Eyecandies datasets demonstrate the state-of-the-art detection performance of our method, and detailed ablation analysis validates each component's contribution. Our code is available at https://github.com/ctaoaa/G2SF.

eess.IV↗