arXiv subjects

Zhen Chen

Publications and source records attributed to Zhen Chen.

At least 109 records · Page 6Linked to original sources

arXiv2025

Atomistic Structure of Transient Switching States in Ferroelectric AlScN

We resolve the microscopic mechanism of polarization switching in wurtzite ferroelectric AlScN by integrating advanced thin-film fabrication, ferroelectric switching dynamics characterizations, high-resolution scanning transmission electron microscopy (STEM), and large-scale molecular dynamics simulations enabled by a deep neural network-based interatomic potential. Contrary to earlier interpretations proposing a transient nonpolar intermediate phase, we demonstrate that the broad transitional regions previously observed in STEM images are projection artifacts resulting from the intrinsic three-dimensional zigzag morphology of 180$^\circ$ domain walls, which are a characteristic form of inversion domain boundary. This is further confirmed by STEM imaging of strategically prepared, partially switched Al$_{0.75}$Sc$_{0.25}$N thin films. Our simulations reveal that switching proceeds through collective, column-by-column atomic displacements, directly explaining the emergence of zigzag-shaped domain walls, and is consistent with the nucleation-limited switching behavior observed in experimental switching dynamic measurements. Furthermore, we show that increasing Sc content systematically lowers domain wall energy and associated nucleation barrier, thereby reducing the switching field in agreement with experimental trends. These findings establish a direct connection between local domain wall structure, switching kinetics, and macroscopic ferroelectric behavior.

cond-mat.mtrl-sci↗

arXiv2025

Unified Performance Control for Non-Square Nonlinear Systems with Relaxed Controllability

In this paper, we investigate the problem of unified prescribed performance tracking for a class of non-square strict-feedback nonlinear systems under relaxed controllability conditions. By using a skillful matrix decomposition and introducing some feasible auxiliary matrices, a more generalized controllability condition than the current state of the art is constructed, which can be applied to both square and non-square nonlinear systems subject to actuator faults and unknown yet time-varying control gain. Incorporating the relaxed controllability conditions and the uniform performance specifications into the backstepping design procedure, a prescribed performance fault-tolerant controller is developed that can achieve different performance demands without modifying the controller structure, which is more flexible and practical.In addition, the destruction of the system stability by unknown controllability auxiliary matrices and unknown nonlinearities is circumvented by embedding the available core information of the state-dependent uncertainties into the design procedure. Both theoretical analysis and numerical simulation demonstrate the effectiveness and benefits of the proposed method.

eess.SY↗

arXiv2025

Interstitial oxygen order and its competition with superconductivity in La$_2$PrNi$_2$O$_{7+δ}$

High-temperature superconductivity in bilayer nickelate La$_3$Ni$_2$O$_7$ under pressure has attracted significant interest in condensed matter physics. While early samples exhibited limited superconducting volume fractions, Pr substitution for La enabled bulk superconductivity in polycrystals under pressure and enhanced transition temperatures in thin films at ambient pressure. Beyond rare-earth doping, moderate oxygen or ozone annealing improves superconductivity by mitigating oxygen vacancies, whereas high-pressure oxygen annealing leads to a trivial, non-superconducting metallic state across all pressure regimes. These findings highlight the need to elucidate both the individual and combined effects of Pr doping and oxygen stoichiometry in modulating superconductivity in bilayer nickelates. Here, using multislice electron ptychography and electron energy-loss spectroscopy, we investigate the structural and electronic properties of as-grown La$_2$PrNi$_2$O$_7$ and high-pressure-oxygen-annealed La$_2$PrNi$_2$O$_{7+δ}$ polycrystals. We find that Pr dopants preferentially occupy outer La sites, effectively eliminating inner-apical oxygen vacancies and ensuring near-stoichiometry in as-grown La$_2$PrNi$_2$O$_7$ that is bulk-superconducting under pressure. In contrast, high-pressure oxygen annealing induces a striped interstitial oxygen order, introducing quasi-1D lattice potentials and excess hole carriers into p-d hybridized orbitals, ultimately suppressing superconductivity. This behavior starkly contrasts with cuprate superconductors, where similar interstitial oxygen ordering enhances superconductivity instead. Our findings reveal a competition between striped interstitial oxygen order and superconductivity in bilayer nickelates, offering key insights into their distinct pairing mechanisms and providing a roadmap for designing more robust superconducting phases.

cond-mat.supr-con↗

arXiv2025

Atomic-Scale Heterogeneity of Hydrogen in Metal Hydrides Revealed by Electron Ptychography

Hydrogen plays critical roles in materials science, particularly for advancing technologies in hydrogen storage and phase manipulation, while also posing challenges like hydrogen embrittlement. Understanding its behavior, vital for improving material properties, requires precise determination of atomic-scale distribution-a persistent challenge due to hydrogen's weak electron scattering and high mobility, as well as the limitations of conventional transmission electron microscopy. We demonstrate that multislice electron ptychography (MEP) overcomes these constraints through three key advances: exceptional sensitivity for hydrogen occupancy, three-dimensional quantification, and picometer-level precision in atomic positioning. Experimentally, MEP resolves heterogeneous hydrogen distributions and quantifies hydrogen-induced lattice displacements with picometer precision in multi-principal-element alloy hydrides. This work demonstrates MEP as a transformative method for directly probing hydrogen atoms in solids, unlocking fundamental understanding of hydrogen's impact on material properties.

cond-mat.mtrl-sci↗

arXiv2025

HER-Seg: Holistically Efficient Segmentation for High-Resolution Medical Images

High-resolution segmentation is critical for precise disease diagnosis by extracting fine-grained morphological details. Existing hierarchical encoder-decoder frameworks have demonstrated remarkable adaptability across diverse medical segmentation tasks. While beneficial, they usually require the huge computation and memory cost when handling large-size segmentation, which limits their applications in foundation model building and real-world clinical scenarios. To address this limitation, we propose a holistically efficient framework for high-resolution medical image segmentation, called HER-Seg. Specifically, we first devise a computation-efficient image encoder (CE-Encoder) to model long-range dependencies with linear complexity while maintaining sufficient representations. In particular, we introduce the dual-gated linear attention (DLA) mechanism to perform cascaded token filtering, selectively retaining important tokens while ignoring irrelevant ones to enhance attention computation efficiency. Then, we introduce a memory-efficient mask decoder (ME-Decoder) to eliminate the demand for the hierarchical structure by leveraging cross-scale segmentation decoding. Extensive experiments reveal that HER-Seg outperforms state-of-the-arts in high-resolution medical 2D, 3D and video segmentation tasks. In particular, our HER-Seg requires only 0.59GB training GPU memory and 9.39G inference FLOPs per 1024$\times$1024 image, demonstrating superior memory and computation efficiency. The code is available at https://github.com/xq141839/HER-Seg.

eess.IV↗

arXiv2025

Trustworthy Text-to-Image Diffusion Models: A Timely and Focused Survey

Text-to-Image (T2I) Diffusion Models (DMs) have garnered widespread attention for their impressive advancements in image generation. However, their growing popularity has raised ethical and social concerns related to key non-functional properties of trustworthiness, such as robustness, fairness, security, privacy, factuality, and explainability, similar to those in traditional deep learning (DL) tasks. Conventional approaches for studying trustworthiness in DL tasks often fall short due to the unique characteristics of T2I DMs, e.g., the multi-modal nature. Given the challenge, recent efforts have been made to develop new methods for investigating trustworthiness in T2I DMs via various means, including falsification, enhancement, verification \& validation and assessment. However, there is a notable lack of in-depth analysis concerning those non-functional properties and means. In this survey, we provide a timely and focused review of the literature on trustworthy T2I DMs, covering a concise-structured taxonomy from the perspectives of property, means, benchmarks and applications. Our review begins with an introduction to essential preliminaries of T2I DMs, and then we summarise key definitions/metrics specific to T2I tasks and analyses the means proposed in recent literature based on these definitions/metrics. Additionally, we review benchmarks and domain applications of T2I DMs. Finally, we highlight the gaps in current research, discuss the limitations of existing methods, and propose future research directions to advance the development of trustworthy T2I DMs. Furthermore, we keep up-to-date updates in this field to track the latest developments and maintain our GitHub repository at: https://github.com/wellzline/Trustworthy_T2I_DMs

cs.LG↗

arXiv2025

Iterative Sparse Asymptotic Minimum Variance Based Channel Estimation in Fluid Antenna System

With fluid antenna system (FAS) gradually establishing itself as a possible enabling technology for next generation wireless communications, channel estimation for FAS has become a pressing issue. Existing methodologies however face limitations in noise suppression. To overcome this, in this paper, we propose a maximum likelihood (ML)-based channel estimation approach tailored for FAS systems, designed to mitigate noise interference and enhance estimation accuracy. By capitalizing on the inherent sparsity of wireless channels, we integrate an ML-based iterative tomographic algorithm to systematically reduce noise perturbations during the channel estimation process. Furthermore, the proposed approach leverages spatial correlation within the FAS channel to optimize estimation accuracy and spectral efficiency. Simulation results confirm the efficacy of the proposed method, demonstrating superior channel estimation accuracy and robustness compared to existing benchmark techniques.

eess.SP↗

arXiv2025

SurgVisAgent: Multimodal Agentic Model for Versatile Surgical Visual Enhancement

Precise surgical interventions are vital to patient safety, and advanced enhancement algorithms have been developed to assist surgeons in decision-making. Despite significant progress, these algorithms are typically designed for single tasks in specific scenarios, limiting their effectiveness in complex real-world situations. To address this limitation, we propose SurgVisAgent, an end-to-end intelligent surgical vision agent built on multimodal large language models (MLLMs). SurgVisAgent dynamically identifies distortion categories and severity levels in endoscopic images, enabling it to perform a variety of enhancement tasks such as low-light enhancement, overexposure correction, motion blur elimination, and smoke removal. Specifically, to achieve superior surgical scenario understanding, we design a prior model that provides domain-specific knowledge. Additionally, through in-context few-shot learning and chain-of-thought (CoT) reasoning, SurgVisAgent delivers customized image enhancements tailored to a wide range of distortion types and severity levels, thereby addressing the diverse requirements of surgeons. Furthermore, we construct a comprehensive benchmark simulating real-world surgical distortions, on which extensive experiments demonstrate that SurgVisAgent surpasses traditional single-task models, highlighting its potential as a unified solution for surgical assistance.

cs.CV↗

arXiv2025

NuSegDG: Integration of Heterogeneous Space and Gaussian Kernel for Domain-Generalized Nuclei Segmentation

Domain-generalized nuclei segmentation refers to the generalizability of models to unseen domains based on knowledge learned from source domains and is challenged by various image conditions, cell types, and stain strategies. Recently, the Segment Anything Model (SAM) has made great success in universal image segmentation by interactive prompt modes (e.g., point and box). Despite its strengths, the original SAM presents limited adaptation to medical images. Moreover, SAM requires providing manual bounding box prompts for each object to produce satisfactory segmentation masks, so it is laborious in nuclei segmentation scenarios. To address these limitations, we propose a domain-generalizable framework for nuclei image segmentation, abbreviated to NuSegDG. Specifically, we first devise a Heterogeneous Space Adapter (HS-Adapter) to learn multi-dimensional feature representations of different nuclei domains by injecting a small number of trainable parameters into the image encoder of SAM. To alleviate the labor-intensive requirement of manual prompts, we introduce a Gaussian-Kernel Prompt Encoder (GKP-Encoder) to generate density maps driven by a single point, which guides segmentation predictions by mixing position prompts and semantic prompts. Furthermore, we present a Two-Stage Mask Decoder (TSM-Decoder) to effectively convert semantic masks to instance maps without the manual demand for morphological shape refinement. Based on our experimental evaluations, the proposed NuSegDG demonstrates state-of-the-art performance in nuclei instance segmentation, exhibiting superior domain generalization capabilities. The source code is available at https://github.com/xq141839/NuSegDG.

eess.IV↗

arXiv2025

De-LightSAM: Modality-Decoupled Lightweight SAM for Generalizable Medical Segmentation

The universality of deep neural networks across different modalities and their generalization capabilities to unseen domains play an essential role in medical image segmentation. The recent segment anything model (SAM) has demonstrated strong adaptability across diverse natural scenarios. However, the huge computational costs, demand for manual annotations as prompts and conflict-prone decoding process of SAM degrade its generalization capabilities in medical scenarios. To address these limitations, we propose a modality-decoupled lightweight SAM for domain-generalized medical image segmentation, named De-LightSAM. Specifically, we first devise a lightweight domain-controllable image encoder (DC-Encoder) that produces discriminative visual features for diverse modalities. Further, we introduce the self-patch prompt generator (SP-Generator) to automatically generate high-quality dense prompt embeddings for guiding segmentation decoding. Finally, we design the query-decoupled modality decoder (QM-Decoder) that leverages a one-to-one strategy to provide an independent decoding channel for every modality, preventing mutual knowledge interference of different modalities. Moreover, we design a multi-modal decoupled knowledge distillation (MDKD) strategy to leverage robust common knowledge to complement domain-specific medical feature representations. Extensive experiments indicate that De-LightSAM outperforms state-of-the-arts in diverse medical imaging segmentation tasks, displaying superior modality universality and generalization capabilities. Especially, De-LightSAM uses only 2.0% parameters compared to SAM-H. The source code is available at https://github.com/xq141839/De-LightSAM.

eess.IV↗

arXiv2025

Versatile SPH Open Boundary Conditions for Multiphase Flows in Extreme Condition

Although the Smoothed Particle Hydrodynamics (SPH) method has been demonstrated as a promising numerical solver for multiphase flow problems due to its Lagrangian nature, its application to complex channel flow may encounter additional issues such as the open boundary condition and numerical instability in the extreme flow state. The present work aims to establish a general SPH algorithm for accurate and stable simulation of complex multiphase flows in configurations with open boundaries. The general scheme of weakly compressible SPH is adopted with special treatments implemented to ease the numerical oscillation in the density discontinuity scenario, and the turbulent model is implemented for interpretations of extreme flow conditions in high Reynolds numbers. Then, the conventional open boundary condition is fine-tuned by two new algorithms to guarantee the numerical stability in the inflow and the outflow regions. Firstly, a density relaxation is proposed to alleviate the pressure instability in the inflow region, which improves the smoothness of the particle pre-processing procedure. Secondly, the particle shifting technique with adaptive damper is implemented to adjust the magnitude of correction in the outflow region, which helps to suppress the velocity oscillation near the outlet. Validations of the proposed algorithms are carried out through four classic numerical examples, presenting appealing agreements with the analytical solutions and thus demonstrating the versatility in various flow conditions. Then, the robustness of the method is established through the turbulent multiphase channel flow cases and the horizontal slug channel flow with large density ratios. These results shed light on the value of the proposed algorithm as a general solver for complex multiphase flow problems with open boundaries.

physics.flu-dyn↗

arXiv2025

POQD: Performance-Oriented Query Decomposer for Multi-vector retrieval

Although Multi-Vector Retrieval (MVR) has achieved the state of the art on many information retrieval (IR) tasks, its performance highly depends on how to decompose queries into smaller pieces, say phrases or tokens. However, optimizing query decomposition for MVR performance is not end-to-end differentiable. Even worse, jointly solving this problem and training the downstream retrieval-based systems, say RAG systems could be highly inefficient. To overcome these challenges, we propose Performance-Oriented Query Decomposer (POQD), a novel query decomposition framework for MVR. POQD leverages one LLM for query decomposition and searches the optimal prompt with an LLM-based optimizer. We further propose an end-to-end training algorithm to alternatively optimize the prompt for query decomposition and the downstream models. This algorithm can achieve superior MVR performance at a reasonable training cost as our theoretical analysis suggests. POQD can be integrated seamlessly into arbitrary retrieval-based systems such as Retrieval-Augmented Generation (RAG) systems. Extensive empirical studies on representative RAG-based QA tasks show that POQD outperforms existing query decomposition strategies in both retrieval performance and end-to-end QA accuracy. POQD is available at https://github.com/PKU-SDS-lab/POQD-ICML25.

cs.IR↗

arXiv2025

Photonic Structures to Achieve High-Performance Dew-Harvesting in a 24-h Day-Night Cycle

Although most prior research on the dew-harvesting technology has focused on nocturnal operations, achieving round-the-clock freshwater harvesting remains crucial. However, daytime dew-harvesting faces two key challenges as compared to its nighttime counterpart: the high solar irradiance and the large contrast between the ambient temperature and the dewpoint. To address these challenges and guide the photonic design, we develop a theoretical framework to analyze dew-harvesting in a 24-h day-night cycle. Using Nanjing as an example, our analyses reveal that, in the solar regime, a minimum average solar reflectivity of 0.92 is required; in the infrared regime, a 10% reduction in absorptivity outside the 8-13 um transparency window is equivalent to a 5.9% enhancement in emissivity within the window. Guided by these findings, we propose a photonic design, which, in a synthetic experiment with measured meteorological datasets, achieves a water production rate of 313 g/m2-day, in which nearly 40% is contributed by daytime. This performance reaches approximately 70% of the theoretical maximum predicted using the ideal spectrum. We end by optimizing the layout of condensers in practical applications.

physics.optics↗

arXiv2025

RapidPD: Rapid Human and Pet Presence Detection System for Smart Vehicles via Wi-Fi

Heatstroke and life threatening incidents resulting from the retention of children and animals in vehicles pose a critical global safety issue. Current presence detection solutions often require specialized hardware or suffer from detection delays that do not meet safety standards. To tackle this issue, by re-modeling channel state information (CSI) with theoretical analysis of path propagation, this study introduces RapidPD, an innovative system utilizing CSI in subcarrier dimension to detect the presence of humans and pets in vehicles. The system models the impact of motion on CSI and introduces motion statistics in subcarrier dimension using a multi-layer autocorrelation method to quantify environmental changes. RapidPD is implemented using commercial Wi-Fi chipsets and tested in real vehicle environments with data collected from 10 living organisms. Experimental results demonstrate that RapidPD achieves a detection accuracy of 99.05% and a true positive rate of 99.32% within a 1-second time window at a low sampling rate of 20 Hz. These findings represent a significant advancement in vehicle safety and provide a foundation for the widespread adoption of presence detection systems.

eess.SP↗

arXiv2025

CeTAD: Towards Certified Toxicity-Aware Distance in Vision Language Models

Recent advances in large vision-language models (VLMs) have demonstrated remarkable success across a wide range of visual understanding tasks. However, the robustness of these models against jailbreak attacks remains an open challenge. In this work, we propose a universal certified defence framework to safeguard VLMs rigorously against potential visual jailbreak attacks. First, we proposed a novel distance metric to quantify semantic discrepancies between malicious and intended responses, capturing subtle differences often overlooked by conventional cosine similarity-based measures. Then, we devise a regressed certification approach that employs randomized smoothing to provide formal robustness guarantees against both adversarial and structural perturbations, even under black-box settings. Complementing this, our feature-space defence introduces noise distributions (e.g., Gaussian, Laplacian) into the latent embeddings to safeguard against both pixel-level and structure-level perturbations. Our results highlight the potential of a formally grounded, integrated strategy toward building more resilient and trustworthy VLMs.

cs.CV↗

arXiv2025

TAIJI: Textual Anchoring for Immunizing Jailbreak Images in Vision Language Models

Vision Language Models (VLMs) have demonstrated impressive inference capabilities, but remain vulnerable to jailbreak attacks that can induce harmful or unethical responses. Existing defence methods are predominantly white-box approaches that require access to model parameters and extensive modifications, making them costly and impractical for many real-world scenarios. Although some black-box defences have been proposed, they often impose input constraints or require multiple queries, limiting their effectiveness in safety-critical tasks such as autonomous driving. To address these challenges, we propose a novel black-box defence framework called \textbf{T}extual \textbf{A}nchoring for \textbf{I}mmunizing \textbf{J}ailbreak \textbf{I}mages (\textbf{TAIJI}). TAIJI leverages key phrase-based textual anchoring to enhance the model's ability to assess and mitigate the harmful content embedded within both visual and textual prompts. Unlike existing methods, TAIJI operates effectively with a single query during inference, while preserving the VLM's performance on benign tasks. Extensive experiments demonstrate that TAIJI significantly enhances the safety and reliability of VLMs, providing a practical and efficient solution for real-world deployment.

cs.CV↗

arXiv2025

UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation

Pre-training techniques significantly enhance the performance of semantic segmentation tasks with limited training data. However, the efficacy under a large domain gap between pre-training (e.g. RGB) and fine-tuning (e.g. infrared) remains underexplored. In this study, we first benchmark the infrared semantic segmentation performance of various pre-training methods and reveal several phenomena distinct from the RGB domain. Next, our layerwise analysis of pre-trained attention maps uncovers that: (1) There are three typical attention patterns (local, hybrid, and global); (2) Pre-training tasks notably influence the pattern distribution across layers; (3) The hybrid pattern is crucial for semantic segmentation as it attends to both nearby and foreground elements; (4) The texture bias impedes model generalization in infrared tasks. Building on these insights, we propose UNIP, a UNified Infrared Pre-training framework, to enhance the pre-trained model performance. This framework uses the hybrid-attention distillation NMI-HAD as the pre-training target, a large-scale mixed dataset InfMix for pre-training, and a last-layer feature pyramid network LL-FPN for fine-tuning. Experimental results show that UNIP outperforms various pre-training methods by up to 13.5\% in average mIoU on three infrared segmentation tasks, evaluated using fine-tuning and linear probing metrics. UNIP-S achieves performance on par with MAE-L while requiring only 1/10 of the computational cost. Furthermore, UNIP significantly surpasses state-of-the-art (SOTA) infrared or RGB segmentation methods and demonstrates broad potential for application in other modalities, such as RGB and depth. Our code is available at https://github.com/casiatao/UNIP.

cs.CV↗

arXiv2025

Learning to Efficiently Adapt Foundation Models for Self-Supervised Endoscopic 3D Scene Reconstruction from Any Cameras

Accurate 3D scene reconstruction is essential for numerous medical tasks. Given the challenges in obtaining ground truth data, there has been an increasing focus on self-supervised learning (SSL) for endoscopic depth estimation as a basis for scene reconstruction. While foundation models have shown remarkable progress in visual tasks, their direct application to the medical domain often leads to suboptimal results. However, the visual features from these models can still enhance endoscopic tasks, emphasizing the need for efficient adaptation strategies, which still lack exploration currently. In this paper, we introduce Endo3DAC, a unified framework for endoscopic scene reconstruction that efficiently adapts foundation models. We design an integrated network capable of simultaneously estimating depth maps, relative poses, and camera intrinsic parameters. By freezing the backbone foundation model and training only the specially designed Gated Dynamic Vector-Based Low-Rank Adaptation (GDV-LoRA) with separate decoder heads, Endo3DAC achieves superior depth and pose estimation while maintaining training efficiency. Additionally, we propose a 3D scene reconstruction pipeline that optimizes depth maps' scales, shifts, and a few parameters based on our integrated network. Extensive experiments across four endoscopic datasets demonstrate that Endo3DAC significantly outperforms other state-of-the-art methods while requiring fewer trainable parameters. To our knowledge, we are the first to utilize a single network that only requires surgical videos to perform both SSL depth estimation and scene reconstruction tasks. The code will be released upon acceptance.

cs.CV↗