arXiv subjects

Jian Zhang

Publications and source records attributed to Jian Zhang.

At least 289 records · Page 16Linked to original sources

arXiv2025

SecureGS: Boosting the Security and Fidelity of 3D Gaussian Splatting Steganography

3D Gaussian Splatting (3DGS) has emerged as a premier method for 3D representation due to its real-time rendering and high-quality outputs, underscoring the critical need to protect the privacy of 3D assets. Traditional NeRF steganography methods fail to address the explicit nature of 3DGS since its point cloud files are publicly accessible. Existing GS steganography solutions mitigate some issues but still struggle with reduced rendering fidelity, increased computational demands, and security flaws, especially in the security of the geometric structure of the visualized point cloud. To address these demands, we propose a SecureGS, a secure and efficient 3DGS steganography framework inspired by Scaffold-GS's anchor point design and neural decoding. SecureGS uses a hybrid decoupled Gaussian encryption mechanism to embed offsets, scales, rotations, and RGB attributes of the hidden 3D Gaussian points in anchor point features, retrievable only by authorized users through privacy-preserving neural networks. To further enhance security, we propose a density region-aware anchor growing and pruning strategy that adaptively locates optimal hiding regions without exposing hidden information. Extensive experiments show that SecureGS significantly surpasses existing GS steganography methods in rendering fidelity, speed, and security.

cs.CV↗

arXiv2025

OmniGuard: Hybrid Manipulation Localization via Augmented Versatile Deep Image Watermarking

With the rapid growth of generative AI and its widespread application in image editing, new risks have emerged regarding the authenticity and integrity of digital content. Existing versatile watermarking approaches suffer from trade-offs between tamper localization precision and visual quality. Constrained by the limited flexibility of previous framework, their localized watermark must remain fixed across all images. Under AIGC-editing, their copyright extraction accuracy is also unsatisfactory. To address these challenges, we propose OmniGuard, a novel augmented versatile watermarking approach that integrates proactive embedding with passive, blind extraction for robust copyright protection and tamper localization. OmniGuard employs a hybrid forensic framework that enables flexible localization watermark selection and introduces a degradation-aware tamper extraction network for precise localization under challenging conditions. Additionally, a lightweight AIGC-editing simulation layer is designed to enhance robustness across global and local editing. Extensive experiments show that OmniGuard achieves superior fidelity, robustness, and flexibility. Compared to the recent state-of-the-art approach EditGuard, our method outperforms it by 4.25dB in PSNR of the container image, 20.7% in F1-Score under noisy conditions, and 14.8% in average bit accuracy.

cs.CV↗

arXiv2025

DR-MPC: Deep Residual Model Predictive Control for Real-world Social Navigation

How can a robot safely navigate around people with complex motion patterns? Deep Reinforcement Learning (DRL) in simulation holds some promise, but much prior work relies on simulators that fail to capture the nuances of real human motion. Thus, we propose Deep Residual Model Predictive Control (DR-MPC) to enable robots to quickly and safely perform DRL from real-world crowd navigation data. By blending MPC with model-free DRL, DR-MPC overcomes the DRL challenges of large data requirements and unsafe initial behavior. DR-MPC is initialized with MPC-based path tracking, and gradually learns to interact more effectively with humans. To further accelerate learning, a safety component estimates out-of-distribution states to guide the robot away from likely collisions. In simulation, we show that DR-MPC substantially outperforms prior work, including traditional DRL and residual DRL models. Hardware experiments show our approach successfully enables a robot to navigate a variety of crowded situations with few errors using less than 4 hours of training data.

cs.RO↗

arXiv2025

LLMs Meet Library Evolution: Evaluating Deprecated API Usage in LLM-based Code Completion

Large language models (LLMs), pre-trained or fine-tuned on large code corpora, have shown effectiveness in generating code completions. However, in LLM-based code completion, LLMs may struggle to use correct and up-to-date Application Programming Interfaces (APIs) due to the rapid and continuous evolution of libraries. While existing studies have highlighted issues with predicting incorrect APIs, the specific problem of deprecated API usage in LLM-based code completion has not been thoroughly investigated. To address this gap, we conducted the first evaluation study on deprecated API usage in LLM-based code completion. This study involved seven advanced LLMs, 145 API mappings from eight popular Python libraries, and 28,125 completion prompts. The study results reveal the status quo (i.e., API usage plausibility and deprecated usage rate) of deprecated API and replacing API usage in LLM-based code completion from the perspectives of model, prompt, and library, and indicate the root causes behind. Based on these findings, we propose two lightweight fixing approaches, REPLACEAPI and INSERTPROMPT, which can serve as baseline approaches for future research on mitigating deprecated API usage in LLM-based completion. Additionally, we provide implications for future research on integrating library evolution with LLM-driven software development.

cs.SE↗

arXiv2025

EPBC-YOLOv8: An efficient and accurate improved YOLOv8 underwater detector based on an attention mechanism

In this study, we enhance underwater target detection by integrating channel and spatial attention into YOLOv8's backbone, applying Pointwise Convolution in FasterNeXt for the FasterPW model, and leveraging Weighted Concat in a BiFPN-inspired WFPN structure for improved cross-scale connections and robustness. Utilizing CARAFE for refined feature reassembly, our framework addresses underwater image degradation, achieving mAP at 0.5 scores of 76.7 percent and 79.0 percent on URPC2019 and URPC2020 datasets, respectively. These scores are 2.3 percent and 0.7 percent higher than the original YOLOv8, showcasing enhanced precision in detecting marine organisms.

cs.CV↗

arXiv2025

Noise is an Efficient Learner for Zero-Shot Vision-Language Models

Recently, test-time adaptation has garnered attention as a method for tuning models without labeled data. The conventional modus operandi for adapting pre-trained vision-language models (VLMs) during test-time primarily focuses on tuning learnable prompts; however, this approach overlooks potential distribution shifts in the visual representations themselves. In this work, we address this limitation by introducing Test-Time Noise Tuning (TNT), a novel method for handling unpredictable shifts in the visual space. TNT leverages, for the first time, a noise adaptation strategy that optimizes learnable noise directly in the visual input space, enabling adaptive feature learning from a single test sample. We further introduce a novel approach for inter-view representation alignment by explicitly enforcing coherence in embedding distances, ensuring consistent feature representations across views. Combined with scaled logits and confident view selection at inference, TNT substantially enhances VLM generalization and calibration, achieving average gains of +7.38% on natural distributions benchmark and +0.80% on cross-dataset evaluations over zero-shot CLIP. These improvements lay a strong foundation for adaptive out-of-distribution handling.

cs.CV↗

arXiv2025

Detecting Mild Traumatic Brain Injury with MEG Scan Data: One-vs-K-Sample Tests

Magnetoencephalography (MEG) scanner has been shown to be more accurate than other medical devices in detecting mild traumatic brain injury (mTBI). However, MEG scan data in certain spectrum ranges can be skewed, multimodal and heterogeneous which can mislead the conventional case-control analysis that requires the data to be homogeneous and normally distributed within the control group. To meet this challenge, we propose a flexible one-vs-K-sample testing procedure for detecting brain injury for a single-case versus heterogeneous controls. The new procedure begins with source magnitude imaging using MEG scan data in frequency domain, followed by region-wise contrast tests for abnormality between the case and controls. The critical values for these tests are automatically determined by cross-validation. We adjust the testing results for heterogeneity effects by similarity analysis. An asymptotic theory is established for the proposed test statistic. By simulated and real data analyses in the context of neurotrauma, we show that the proposed test outperforms commonly used nonparametric methods in terms of overall accuracy and ability in accommodating data non-normality and subject-heterogeneity.

stat.ME↗

arXiv2025

Twisted q-Yangians and Sklyanin determinants

$q$-Yangians can be viewed both as quantum deformations of the loop algebras of upper triangular Lie algebras and deformations of the Yangian algebras. In this paper, we study the quantum affine algebra as a product of two copies of the $q$-Yangian algebras. This viewpoint enables us to investigate the invariant theory of quantum affine algebras and their twisted versions. We introduce the twisted Sklyanin determinant for twisted quantum affine algebras and establish various identities for the Sklyanin determinants.

math.QA↗

arXiv2025

DA-LIF: Dual Adaptive Leaky Integrate-and-Fire Model for Deep Spiking Neural Networks

Spiking Neural Networks (SNNs) are valued for their ability to process spatio-temporal information efficiently, offering biological plausibility, low energy consumption, and compatibility with neuromorphic hardware. However, the commonly used Leaky Integrate-and-Fire (LIF) model overlooks neuron heterogeneity and independently processes spatial and temporal information, limiting the expressive power of SNNs. In this paper, we propose the Dual Adaptive Leaky Integrate-and-Fire (DA-LIF) model, which introduces spatial and temporal tuning with independently learnable decays. Evaluations on both static (CIFAR10/100, ImageNet) and neuromorphic datasets (CIFAR10-DVS, DVS128 Gesture) demonstrate superior accuracy with fewer timesteps compared to state-of-the-art methods. Importantly, DA-LIF achieves these improvements with minimal additional parameters, maintaining low energy consumption. Extensive ablation studies further highlight the robustness and effectiveness of the DA-LIF model.

cs.NE↗

arXiv2025

Invertible Diffusion Models for Compressed Sensing

While deep neural networks (NN) significantly advance image compressed sensing (CS) by improving reconstruction quality, the necessity of training current CS NNs from scratch constrains their effectiveness and hampers rapid deployment. Although recent methods utilize pre-trained diffusion models for image reconstruction, they struggle with slow inference and restricted adaptability to CS. To tackle these challenges, this paper proposes Invertible Diffusion Models (IDM), a novel efficient, end-to-end diffusion-based CS method. IDM repurposes a large-scale diffusion sampling process as a reconstruction model, and fine-tunes it end-to-end to recover original images directly from CS measurements, moving beyond the traditional paradigm of one-step noise estimation learning. To enable such memory-intensive end-to-end fine-tuning, we propose a novel two-level invertible design to transform both (1) multi-step sampling process and (2) noise estimation U-Net in each step into invertible networks. As a result, most intermediate features are cleared during training to reduce up to 93.8% GPU memory. In addition, we develop a set of lightweight modules to inject measurements into noise estimator to further facilitate reconstruction. Experiments demonstrate that IDM outperforms existing state-of-the-art CS networks by up to 2.64dB in PSNR. Compared to the recent diffusion-based approach DDNM, our IDM achieves up to 10.09dB PSNR gain and 14.54 times faster inference. Code is available at https://github.com/Guaishou74851/IDM.

cs.CV↗

arXiv2025

Multi-Frame Blind Manifold Deconvolution for Rotating Synthetic Aperture Imaging

Rotating synthetic aperture (RSA) imaging system captures images of the target scene at different rotation angles by rotating a rectangular aperture. Deblurring acquired RSA images plays a critical role in reconstructing a latent sharp image underlying the scene. In the past decade, the emergence of blind convolution technology has revolutionised this field by its ability to model complex features from acquired images. Most of the existing methods attempt to solve the above ill-posed inverse problem through maximising a posterior. Despite this progress, researchers have paid limited attention to exploring low-dimensional manifold structures of the latent image within a high-dimensional ambient-space. Here, we propose a novel method to process RSA images using manifold fitting and penalisation in the content of multi-frame blind convolution. We develop fast algorithms for implementing the proposed procedure. Simulation studies demonstrate that manifold-based deconvolution can outperform conventional deconvolution algorithms in the sense that it can generate a sharper estimate of the latent image in terms of estimating pixel intensities and preserving structural details.

stat.ME↗

arXiv2025

ILETIA: An AI-enhanced method for individualized trigger-oocyte pickup interval estimation of progestin-primed ovarian stimulation protocol

In vitro fertilization-embryo transfer (IVF-ET) stands as one of the most prevalent treatments for infertility. During an IVF-ET cycle, the time interval between trigger shot and oocyte pickup (OPU) is a pivotal period for follicular maturation, which determines mature oocytes yields and impacts the success of subsequent procedures. However, accurately predicting this interval is severely hindered by the variability of clinicians'experience that often leads to suboptimal oocyte retrieval rate. To address this challenge, we propose ILETIA, the first machine learning-based method that could predict the optimal trigger-OPU interval for patients receiving progestin-primed ovarian stimulation (PPOS) protocol. Specifically, ILETIA leverages a Transformer to learn representations from clinical tabular data, and then employs gradient-boosted trees for interval prediction. For model training and evaluating, we compiled a dataset PPOS-DS of nearly ten thousand patients receiving PPOS protocol, the largest such dataset to our knowledge. Experimental results demonstrate that our method achieves strong performance (AUROC = 0.889), outperforming both clinicians and other widely used computational models. Moreover, ILETIA also supports premature ovulation risk prediction in a specific OPU time (AUROC = 0.838). Collectively, by enabling more precise and individualized decisions, ILETIA has the potential to improve clinical outcomes and lay the foundation for future IVF-ET research.

q-bio.QM↗

arXiv2025

Signature of superconductivity in pressurized La4Ni3O10-x single crystals grown at ambient pressure

Nickelates have attracted enormous attention since the discovery of high-temperature superconductivity in La3Ni2O7 under high pressure. However, whether superconducting nickelate single crystals can be prepared at ambient pressure remains elusive. Here we report signature of superconductivity in pressurized La4Ni3O10-x single crystals grown from potassium carbonate flux at ambient pressure. Single crystal X-ray diffraction and scanning transmission electron microscopy investigations re-vealed high-quality single crystals with perfect stacking of trilayers. Resistivity measurements indicate that the metal-to-metal transition observed at ambient pressure was suppressed under high pressure, and a sharp drop occurred at ~30 K at 77.9 GPa, consistent with superconductivity in pressurized La4Ni3O10 single crystals grown by the floating zone method at an oxygen pressure of >18 bar. Our results not only provide an important path to prepare high-quality nickelate single crystals but also support superconductivity in nickelates under high pressure, promoting more systematic and in-depth research in this compelling field.

cond-mat.supr-con↗

arXiv2025

Double-tough ceramics: Optimization-supported multiscale computational design

To overcome the brittleness limitation of ceramics, various toughening mechanisms have been proposed. Some of the most remarkable, especially for oxides, include the tetragonal-to-monoclinic phase transformation leading to crack shielding in zirconia, and bioinspired brick-and-mortar microstructures fostering crack deflection. It has, however, proven challenging to incorporate both these mechanisms into a single all-ceramic material. In this work, we propose a computational methodology for the design of a material that combines these two toughening strategies, using a multiscale modeling approach that captures both their individual contributions and the overall fracture performance. This is achieved by developing an all-ceramic composite with a brick-and-mortar microstructure, in which the nanocrystalline mortar is transformation-toughened. Key factors influencing phase transformation, such as grain boundary properties, grain orientations, and kinetic coefficients, are analyzed, and the resulting transformation stress-strain behavior is incorporated into the microscale mortar constitutive model. We demonstrate that the synergistic effect of the two toughening mechanisms is achievable, and that it is an extremely effective strategy to boost fracture performance. The influence of brick size, mortar thickness, and properties of the constituent materials is then systematically investigated. Finally, a gradient-free optimization algorithm is employed to identify optimal geometric and material parameters, revealing that longer, thinner bricks with minimal mortar thickness provide the best fracture resistance. Optimal combinations of material properties are identified for given brick sizes and mortar thicknesses.

cond-mat.mtrl-sci↗

arXiv2025

ELEGNT: Expressive and Functional Movement Design for Non-anthropomorphic Robot

Nonverbal behaviors such as posture, gestures, and gaze are essential for conveying internal states, both consciously and unconsciously, in human interaction. For robots to interact more naturally with humans, robot movement design should likewise integrate expressive qualities, such as intention, attention, and emotions, alongside traditional functional considerations like task fulfillment and time efficiency. In this paper, we present the design and prototyping of a lamp-like robot that explores the interplay between functional and expressive objectives in movement design. Using a research-through-design methodology, we document the hardware design process, define expressive movement primitives, and outline a set of interaction scenario storyboards. We propose a framework that incorporates both functional and expressive utilities during movement generation, and implement the robot behavior sequences in different function- and social- oriented tasks. Through a user study comparing expression-driven versus function-driven movements across six task scenarios, our findings indicate that expression-driven movements significantly enhance user engagement and perceived robot qualities. This effect is especially pronounced in social-oriented tasks.

cs.RO↗

arXiv2025

Enhancing LLM Agents for Code Generation with Possibility and Pass-rate Prioritized Experience Replay

Nowadays transformer-based Large Language Models (LLM) for code generation tasks usually apply sampling and filtering pipelines. Due to the sparse reward problem in code generation tasks caused by one-token incorrectness, transformer-based models will sample redundant programs till they find a correct one, leading to low efficiency. To overcome the challenge, we incorporate Experience Replay (ER) in the fine-tuning phase, where codes and programs produced are stored and will be replayed to give the LLM agent a chance to learn from past experiences. Based on the spirit of ER, we introduce a novel approach called BTP pipeline which consists of three phases: beam search sampling, testing phase, and prioritized experience replay phase. The approach makes use of failed programs collected by code models and replays programs with high Possibility and Pass-rate Prioritized value (P2Value) from the replay buffer to improve efficiency. P2Value comprehensively considers the possibility of transformers' output and pass rate and can make use of the redundant resources caused by the problem that most programs collected by LLMs fail to pass any tests. We empirically apply our approach in several LLMs, demonstrating that it enhances their performance in code generation tasks and surpasses existing baselines.

cs.LG↗

arXiv2025

Field-free perpendicular magnetization switching of low critical current density at room temperature in TaIrTe4/ferromagnet heterostructures

Spin-orbit torque-induced perpendicular magnetization switching has attracted much attention due to the advantages of nonvolatility, high density, infinite read/write counts, and low power consumption in spintronic applications. To achieve field-free deterministic switching of perpendicular magnetization, additional magnetic field, magnetic layer assistance, or artificially designed structural symmetry breaking are usually required, which are not conducive to the high-density integration and application of low-power devices. However, 2D Weyl semimetals with low-symmetry structures have recently been found to generate z-spin-polarized currents, which may induce out-of-plane damping-like torques to their neighboring ferromagnetic layers, and realize deterministic perpendicular magnetization switching at zero magnetic field. In this Letter, we report that current-induced field-free magnetization switching at room temperature can be achieved in a perpendicularly magnetized TaIrTe4/Pt/Co/Pt device, and the critical switching current density can be lowered to be about 2.64*105 Acm-2. This study suggests that TaIrTe4 has great potential for the design of room-temperature efficient spintronic devices.

cond-mat.mtrl-sci↗

arXiv2025

Modelling Loss of Complexity in Intermittent Time Series and its Application

In this paper, we developed a novel method of nonparametric relative entropy (RlEn) for modelling loss of complexity in intermittent time series. The method consists of two steps. We first fit a nonlinear autoregressive model to each intermittent time series, where the corresponding lag order and the loss of complexity are determined by Bayesian Information Criterion (BIC) and relative entropy respectively. Then, change-points in the complexity are detected by a cumulative sum (CUSUM) based statistic. Compared to approximate entropy (ApEn), a popular method in literature, the performance of RlEn was assessed by simulations in terms of (1) ability to localize complexity change-points in intermittent time series; (2) ability to faithfully estimate underlying nonlinear models. The performance of the proposal was then examined in a real analysis of fatigue-induced changes in the complexity of human motor outputs. The results showed that the proposed method outperformed the ApEn in accurately detecting changes of complexity in intermittent time series segments.

stat.ME↗