arXiv subjects

Gang Xu

Publications and source records attributed to Gang Xu.

At least 55 records · Page 3Linked to original sources

arXiv2025

StyleTailor: Towards Personalized Fashion Styling via Hierarchical Negative Feedback

The advancement of intelligent agents has revolutionized problem-solving across diverse domains, yet solutions for personalized fashion styling remain underexplored, which holds immense promise for promoting shopping experiences. In this work, we present StyleTailor, the first collaborative agent framework that seamlessly unifies personalized apparel design, shopping recommendation, virtual try-on, and systematic evaluation into a cohesive workflow. To this end, StyleTailor pioneers an iterative visual refinement paradigm driven by multi-level negative feedback, enabling adaptive and precise user alignment. Specifically, our framework features two core agents, i.e., Designer for personalized garment selection and Consultant for virtual try-on, whose outputs are progressively refined via hierarchical vision-language model feedback spanning individual items, complete outfits, and try-on efficacy. Counterexamples are aggregated into negative prompts, forming a closed-loop mechanism that enhances recommendation quality. To assess the performance, we introduce a comprehensive evaluation suite encompassing style consistency, visual quality, face similarity, and artistic appraisal. Extensive experiments demonstrate StyleTailor's superior performance in delivering personalized designs and recommendations, outperforming strong baselines without negative feedback and establishing a new benchmark for intelligent fashion systems.

cs.CV↗

arXiv2025

Generative AI for Object-Oriented Programming: Writing the Right Code and Reasoning the Right Logic

We find ourselves in the midst of an explosion in artificial intelligence research, particularly with large language models (LLMs). These models have diverse applications spanning finance, commonsense knowledge graphs, medicine, and visual analysis. In the world of Object-Oriented Programming(OOP), a robust body of knowledge and methods has been developed for managing complex tasks through object-oriented thinking. However, the intersection of LLMs with OOP remains an underexplored territory. Empirically, we currently possess limited understanding of how LLMs can enhance the effectiveness of OOP learning and code writing, as well as how we can evaluate such AI-powered tools. Our work aims to address this gap by presenting a vision from the perspectives of key stakeholders involved in an OOP task: programmers, mariners, and experienced programmers. We identify critical junctures within typical coding workflows where the integration of LLMs can offer significant benefits. Furthermore, we propose ways to augment existing logical reasoning and code writing, ultimately enhancing the programming experience.

cs.SE↗

arXiv2025

The Missing Covariate Indicator Method is Nearly Valid Almost Always

Background: Although the missing covariate indicator method (MCIM) has been shown to be biased under extreme conditions, the degree and determinants of bias have not been formally assessed. We derived the formula for the relative bias in the MCIM and systematically investigated conditions under which bias arises. We found that the extent of bias is independent of both the disease rate and the exposure-outcome association, but it is a function of 5 parameters: exposure and covariate prevalences, covariate missingness proportion, and associations of covariate with exposure and outcome. The MCIM was unbiased when the missing covariate is a risk factor for the outcome but not a confounder. The average median relative bias was zero across each of the parameters over a wide range of values considered. Our simulation study demonstrated that the mean and median of relative bias of MCIM was comparable to that of the no missingness method, which used the full sample with complete information for all variables, as long as the missingness of covariate is independent of the outcome. When missingness was no greater than 50%, less than 5% of the scenarios considered had relative bias greater than 10%. In several analyses of the Harvard cohort studies, the MCIM produced materially the same results as the multiple imputation method. In conclusion, the MCIM is nearly valid almost always in settings typically encountered in epidemiology and its continued use is recommended, unless the covariate is missing in an extreme proportion or acts as a strong confounder.

stat.AP↗

arXiv2025

Global smooth solutions to 2D semilinear wave equations with large data

We are interested in coupled semi-linear wave equations satisfying the null condition in two space dimensions, a basic model in nonlinear wave equations. Our aim is to establish global existence of smooth solutions to this system with large initial data of short pulse type. Major difficulties arise due to the largeness of initial data and the slow decay nature of 2D wave equations. To overcome the difficulties, by careful examination of the local solutions, we adapt various vector-field methods to different spacetime regions with several novel weighted energy estimates.

math.AP↗

arXiv2025

Timing-injection locking in a self-starting Mamyshev oscillator induced by the dissipative Faraday instability

Mamyshev oscillators (MOs), a novel class of passively mode-locked fiber lasers, serve as an excellent platform to explore complex nonlinear dynamics, ranging from localized structures to chaos. Despite their versatility, achieving self-starting mode-locking remains a significant challenge. In this study, we unveil the critical role of the dissipative Faraday instability (DFI) in facilitating the self-starting process of MOs, where the DFI triggers the symmetry breaking of the homogeneous solution to overcome the initiation barriers. A panoramic view of several distinct operational regimes with distinct DFI patterns is provided, namely the non-self-starting states, the irregular patterns, the harmonic mode locking regime, the stable single pulse and the stable multi pulse regime. For the lattest case, we uncover the origins of randomness in these pulse sequences through analyzing the causality between the timing of the random pulses and the initial seeding conditions. Building upon these findings, we propose the novel time-injection locking technique to customize the temporal locations of the pulses as well as the pattern timing in MOs, thus demonstrating its potential for applications in all-optical data storage and tunable ultrashort pulse sources.

physics.optics↗

arXiv2025

Promising ferroelectric metal EuAuBi with switchable giant shift current

The coexistence of metallicity and ferroelectricity in ferroelectric (FE) metals defies conventional wisdom and enables novel functionalities in electronic and optoelectronic systems. However, intrinsic FE metals remain extremely rare and challenging. Here, using first-principles calculations, we identify that a huge spontaneous polarization of 16.6-20.2 $μ\text{C}/\text{cm}^2$, a moderate switching barrier of 68.5 meV/f.u., and a low carrier concentration of $ \sim 2.5 \times 10^{20}$ cm$^{-3}$ coexist in topological semimetal EuAuBi. Further electron-phonon coupling calculations reveal that the metallic carriers interact weakly with the FE phonon mode, consistent with the decoupled electron mechanism. Moreover, EuAuBi exhibits a pronounced bulk photovoltaic effect characterized by a giant polarization-dependent shift current with the magnitude of conductivity up to 370 $μ\text{A}/\text{V}^2$. Thus, a feasible FE metal verification setup is proposed based on the shift current measurement. These results not only demonstrate that EuAuBi is a promising FE metal, but also propose a practical route for FE metals identification, which could promote the FE metals study greatly.

cond-mat.mtrl-sci↗

arXiv2025

FNBench: Benchmarking Robust Federated Learning against Noisy Labels

Robustness to label noise within data is a significant challenge in federated learning (FL). From the data-centric perspective, the data quality of distributed datasets can not be guaranteed since annotations of different clients contain complicated label noise of varying degrees, which causes the performance degradation. There have been some early attempts to tackle noisy labels in FL. However, there exists a lack of benchmark studies on comprehensively evaluating their practical performance under unified settings. To this end, we propose the first benchmark study FNBench to provide an experimental investigation which considers three diverse label noise patterns covering synthetic label noise, imperfect human-annotation errors and systematic errors. Our evaluation incorporates eighteen state-of-the-art methods over five image recognition datasets and one text classification dataset. Meanwhile, we provide observations to understand why noisy labels impair FL, and additionally exploit a representation-aware regularization method to enhance the robustness of existing methods against noisy labels based on our observations. Finally, we discuss the limitations of this work and propose three-fold future directions. To facilitate related communities, our source code is open-sourced at https://github.com/Sprinter1999/FNBench.

cs.CV↗

arXiv2025

Safe-VAR: Safe Visual Autoregressive Model for Text-to-Image Generative Watermarking

With the success of autoregressive learning in large language models, it has become a dominant approach for text-to-image generation, offering high efficiency and visual quality. However, invisible watermarking for visual autoregressive (VAR) models remains underexplored, despite its importance in misuse prevention. Existing watermarking methods, designed for diffusion models, often struggle to adapt to the sequential nature of VAR models. To bridge this gap, we propose Safe-VAR, the first watermarking framework specifically designed for autoregressive text-to-image generation. Our study reveals that the timing of watermark injection significantly impacts generation quality, and watermarks of different complexities exhibit varying optimal injection times. Motivated by this observation, we propose an Adaptive Scale Interaction Module, which dynamically determines the optimal watermark embedding strategy based on the watermark information and the visual characteristics of the generated image. This ensures watermark robustness while minimizing its impact on image quality. Furthermore, we introduce a Cross-Scale Fusion mechanism, which integrates mixture of both heads and experts to effectively fuse multi-resolution features and handle complex interactions between image content and watermark patterns. Experimental results demonstrate that Safe-VAR achieves state-of-the-art performance, significantly surpassing existing counterparts regarding image quality, watermarking fidelity, and robustness against perturbations. Moreover, our method exhibits strong generalization to an out-of-domain watermark dataset QR Codes.

cs.MM↗

arXiv2025

Inter3D: A Benchmark and Strong Baseline for Human-Interactive 3D Object Reconstruction

Recent advancements in implicit 3D reconstruction methods, e.g., neural rendering fields and Gaussian splatting, have primarily focused on novel view synthesis of static or dynamic objects with continuous motion states. However, these approaches struggle to efficiently model a human-interactive object with n movable parts, requiring 2^n separate models to represent all discrete states. To overcome this limitation, we propose Inter3D, a new benchmark and approach for novel state synthesis of human-interactive objects. We introduce a self-collected dataset featuring commonly encountered interactive objects and a new evaluation pipeline, where only individual part states are observed during training, while part combination states remain unseen. We also propose a strong baseline approach that leverages Space Discrepancy Tensors to efficiently modelling all states of an object. To alleviate the impractical constraints on camera trajectories across training states, we propose a Mutual State Regularization mechanism to enhance the spatial density consistency of movable parts. In addition, we explore two occupancy grid sampling strategies to facilitate training efficiency. We conduct extensive experiments on the proposed benchmark, showcasing the challenges of the task and the superiority of our approach.

cs.GR↗

arXiv2025

OmniSR: Shadow Removal under Direct and Indirect Lighting

Shadows can originate from occlusions in both direct and indirect illumination. Although most current shadow removal research focuses on shadows caused by direct illumination, shadows from indirect illumination are often just as pervasive, particularly in indoor scenes. A significant challenge in removing shadows from indirect illumination is obtaining shadow-free images to train the shadow removal network. To overcome this challenge, we propose a novel rendering pipeline for generating shadowed and shadow-free images under direct and indirect illumination, and create a comprehensive synthetic dataset that contains over 30,000 image pairs, covering various object types and lighting conditions. We also propose an innovative shadow removal network that explicitly integrates semantic and geometric priors through concatenation and attention mechanisms. The experiments show that our method outperforms state-of-the-art shadow removal techniques and can effectively generalize to indoor and outdoor scenes under various lighting conditions, enhancing the overall effectiveness and applicability of shadow removal methods.

cs.CV↗

arXiv2025

Efficient and accurate analysis of oscillation dynamics for dissipative cavity solitons based on the artificial neural network

As a conventional means to analyze the system mechanism based on partial differential equations (PDE) or nonlinear dynamics, iterative algorithms are computationally intensive. In this framework, the details of oscillating dynamics of cavity solitons are beyond the reach of traditional mathematical analysis. In this work, we demonstrate that this long-standing challenge could be tackled down with the Long Short-Term Memory (LSTM) neural network. We propose the incorporating parameter-fed ports, which are capable of recognizing period-doubling bifurcations of respiratory solitons and quickly predicting nonlinear dynamics of solitons with arbitrary parameter combinations and arbitrary time series lengths. The model predictions capture oscillatory features with a small Root Mean Square Errors (RMSE) = 0.01676 and an absolute error that barely grows with the length of the prediction time. Lugiato-Lefever equation (LLE) based parameter space boundaries for typical oscillatory patterns are plotted at about 120 times the speed relative to the split-step Fourier method (SSFM) and higher resolution.

physics.optics↗

arXiv2024

Anisotropic and tunable vortex topology in multiband iron-based superconductors

Building on the multiband nature of iron-based superconductors (FeSCs), we have uncovered pronounced anisotropy in Majorana vortex topology arising from the interaction between vortex orientation and multiple electronic topologies. This anisotropy manifests in two distinct vortex configurations: the z-vortex and x-vortex, oriented perpendicular and parallel to the Dirac axis (z-axis for FeSCs), respectively. The x-vortex exhibits a unique duality, displaying two distinct topological phase diagrams. One is strikingly simple, comprising only trivial and topological superconducting phases, and remains resilient to multiband entanglement. The other mirrors the z-vortex's complex diagram, featuring alternating trivial, topological crystalline and topological superconducting phases. Crucially, the former is exclusive to the x-vortex and supports unpaired Majorana vortices across a wide parameter range, even with Dirac nodes in electronic bands. Notably, uniaxial strain can modulate these x-vortex phases, enabling the x-vortex to support both stable Majorana vortices and rich exotic physics in a controllable manner. Moreover, we propose that the x-vortex offers promising advantages for developing iron-based superconducting quantum devices. Our findings introduce a novel paradigm in vortex topology within multiband superconducting systems, highlighting the x-vortex as a promising platform for exploring Majorana physics and advancing iron-based superconducting quantum technology.

cond-mat.supr-con↗

arXiv2024

Detail-Preserving Latent Diffusion for Stable Shadow Removal

Achieving high-quality shadow removal with strong generalizability is challenging in scenes with complex global illumination. Due to the limited diversity in shadow removal datasets, current methods are prone to overfitting training data, often leading to reduced performance on unseen cases. To address this, we leverage the rich visual priors of a pre-trained Stable Diffusion (SD) model and propose a two-stage fine-tuning pipeline to adapt the SD model for stable and efficient shadow removal. In the first stage, we fix the VAE and fine-tune the denoiser in latent space, which yields substantial shadow removal but may lose some high-frequency details. To resolve this, we introduce a second stage, called the detail injection stage. This stage selectively extracts features from the VAE encoder to modulate the decoder, injecting fine details into the final results. Experimental results show that our method outperforms state-of-the-art shadow removal techniques. The cross-dataset evaluation further demonstrates that our method generalizes effectively to unseen data, enhancing the applicability of shadow removal methods.

cs.CV↗

arXiv2024

Robust and Feature-Preserving Offset Meshing

We introduce a novel offset meshing approach that can robustly handle a 3D surface mesh with an arbitrary geometry and topology configurations, while nicely capturing the sharp features on the original input for both inward and outward offsets. Compared to the existing approaches focusing on constant-radius offset, to the best of our knowledge, we propose the first-ever solution for mitered offset that can well preserve sharp features. Our method is designed based on several core principals: 1) explicitly generating the offset vertices and triangles with feature-capturing energy and constraints; 2) prioritizing the generation of the offset geometry before establishing its connectivity, 3) employing exact algorithms in critical pipeline steps for robustness, balancing the use of floating-point computations for efficiency, 4) applying various conservative speed up strategies including early reject non-contributing computations to the final output. Our approach further uniquely supports variable offset distances on input surface elements, offering a wider range practical applications compared to conventional methods. We have evaluated our method on a subset of Thinkgi10K, containing models with diverse topological and geometric complexities created by practitioners in various fields. Our results demonstrate the superiority of our approach over current state-of-the-art methods in terms of element count, feature preservation, and non-uniform offset distances of the resulting offset mesh surfaces, marking a significant advancement in the field.

cs.GR↗

arXiv2024

Polarization faticons: Chiral localized structures in self-defocusing Kerr resonators

We report on numerical predictions and experimental observations of a novel type of temporal localized dissipative structures that manifest themselves in the self-defocusing regime of driven nonlinear optical resonators with two polarization modes. These chiral dissipative solitons, which we term polarization faticons, break both temporal and polarization symmetry and consist of two bright lobes of opposite polarization handedness, interlocked by a domain wall. Our study reveals that faticons are connected to a vectorial modulational instability, from which they can be excited through a collapsing dynamic. Faticons could offer a novel pathway for frequency comb generation in normal dispersion resonators. More generally, they offer new fundamental insights into vectorial localized dissipative structures and could be relevant to other multi-component dissipative systems.

physics.optics↗

arXiv2024

A numerical method for designing topological superconductivity induced by s-wave pairing

Topological superconductors have garnered significant attention due to their potential for realizing topological quantum computation. However, a universal computational tool based on first-principles calculations for predicting topological superconductivity has not yet been fully developed, posing substantial challenges in identifying topological superconducting materials. In this paper, we present a numerical method to characterize the superconducting spectrum and topological invariants of two-dimensional (2D) slab systems using first-principles calculations, implemented in the open-source software WannierTools. To more accurately model the superconducting proximity effect, we integrate an SC pairing decay module into the program. Our approach can be applied to classical superconductor-topological insulator (SC-TI) heterostructures, SC-semiconductor heterostructures, and intrinsic topological superconductors. The program's validity is demonstrated using the topological crystal insulator SnTe, the Rashba semiconductor InSb, and the superconductor NbSe2 as examples. We anticipate that this tool will accelerate the discovery of topological superconductor candidates.

cond-mat.supr-con↗

arXiv2024

Hierarchical Search-Based Cooperative Motion Planning

Cooperative path planning, a crucial aspect of multi-agent systems research, serves a variety of sectors, including military, agriculture, and industry. Many existing algorithms, however, come with certain limitations, such as simplified kinematic models and inadequate support for multiple group scenarios. Focusing on the planning problem associated with a nonholonomic Ackermann model for Unmanned Ground Vehicles (UGV), we propose a leaderless, hierarchical Search-Based Cooperative Motion Planning (SCMP) method. The high-level utilizes a binary conflict search tree to minimize runtime, while the low-level fabricates kinematically feasible, collision-free paths that are shape-constrained. Our algorithm can adapt to scenarios featuring multiple groups with different shapes, outlier agents, and elaborate obstacles. We conduct algorithm comparisons, performance testing, simulation, and real-world testing, verifying the effectiveness and applicability of our algorithm. The implementation of our method will be open-sourced at https://github.com/WYCUniverStar/SCMP.

cs.RO↗

arXiv2024

Causal Inference with Double/Debiased Machine Learning for Evaluating the Health Effects of Multiple Mismeasured Pollutants

One way to quantify exposure to air pollution and its constituents in epidemiologic studies is to use an individual's nearest monitor. This strategy results in potential inaccuracy in the actual personal exposure, introducing bias in estimating the health effects of air pollution and its constituents, especially when evaluating the causal effects of correlated multi-pollutant constituents measured with correlated error. This paper addresses estimation and inference for the causal effect of one constituent in the presence of other PM2.5 constituents, accounting for measurement error and correlations. We used a linear regression calibration model, fitted with generalized estimating equations in an external validation study, and extended a double/debiased machine learning (DML) approach to correct for measurement error and estimate the effect of interest in the main study. We demonstrated that the DML estimator with regression calibration is consistent and derived its asymptotic variance. Simulations showed that the proposed estimator reduced bias and attained nominal coverage probability across most simulation settings. We applied this method to assess the causal effects of PM2.5 constituents on cognitive function in the Nurses' Health Study and identified two PM2.5 constituents, Br and Mn, that showed a negative causal effect on cognitive function after measurement error correction.

stat.AP↗