arXiv subjects

Xiao Wang

Publications and source records attributed to Xiao Wang.

At least 181 records · Page 10Linked to original sources

arXiv2026

SUN-DSBO: A Structured Unified Framework for Nonconvex Decentralized Stochastic Bilevel Optimization

Decentralized stochastic bilevel optimization (DSBO) is a powerful tool for various machine learning tasks, including decentralized meta-learning and hyperparameter tuning. Existing DSBO methods primarily address problems with strongly convex lower-level objective functions. However, nonconvex objective functions are increasingly prevalent in modern deep learning. In this work, we introduce SUN-DSBO, a Structured Unified framework for Nonconvex DSBO, in which both the upper- and lower-level objective functions may be nonconvex. Notably, SUN-DSBO offers the flexibility to incorporate decentralized stochastic gradient descent or various techniques for mitigating data heterogeneity, such as gradient tracking (GT). We demonstrate that SUN-DSBO-GT, an adaptation of the GT technique within our framework, achieves a linear speedup with respect to the number of agents. This is accomplished without relying on restrictive assumptions, such as gradient boundedness or any specific assumptions regarding gradient heterogeneity. Numerical experiments validate the effectiveness of our method.

math.OC↗

arXiv2026

MASC: Metal-Aware Sampling and Correction via Reinforcement Learning for Accelerated MRI

Metal implants in MRI cause severe artifacts that degrade image quality and hinder clinical diagnosis. Traditional approaches address metal artifact reduction (MAR) and accelerated MRI acquisition as separate problems. We propose MASC, a unified reinforcement learning framework that jointly optimizes metal-aware k-space sampling and artifact correction for accelerated MRI. To enable supervised training, we construct a paired MRI dataset using physics-based simulation, generating k-space data and reconstructions for phantoms with and without metal implants. This paired dataset provides simulated 3D MRI scans with and without metal implants, where each metal-corrupted sample has an exactly matched clean reference, enabling direct supervision for both artifact reduction and acquisition policy learning. We formulate active MRI acquisition as a sequential decision-making problem, where an artifact-aware Proximal Policy Optimization (PPO) agent learns to select k-space phase-encoding lines under a limited acquisition budget. The agent operates on undersampled reconstructions processed through a U-Net-based MAR network, learning patterns that maximize reconstruction quality. We further propose an end-to-end training scheme where the acquisition policy learns to select k-space lines that best support artifact removal while the MAR network simultaneously adapts to the resulting undersampling patterns. Experiments demonstrate that MASC's learned policies outperform conventional sampling strategies, and end-to-end training improves performance compared to using a frozen pre-trained MAR network, validating the benefit of joint optimization. Cross-dataset experiments on FastMRI with physics-based artifact simulation further confirm generalization to realistic clinical MRI data. The code and models of MASC have been made publicly available: https://github.com/hrlblab/masc

cs.CV↗

arXiv2026

DeepBooTS: Dual-Stream Residual Boosting for Drift-Resilient Time-Series Forecasting

Time-Series (TS) exhibits pronounced non-stationarity. Consequently, most forecasting methods display compromised robustness to concept drift, despite the prevalent application of instance normalization. We tackle this challenge by first analysing concept drift through a bias-variance lens and proving that weighted ensemble reduces variance without increasing bias. These insights motivate DeepBooTS, a novel end-to-end dual-stream residual-decreasing boosting method that progressively reconstructs the intrinsic signal. In our design, each block of a deep model becomes an ensemble of learners with an auxiliary output branch forming a highway to the final prediction. The block-wise outputs correct the residuals of previous blocks, leading to a learning-driven decomposition of both inputs and targets. This method enhances versatility and interpretability while substantially improving robustness to concept drift. Extensive experiments, including those on large-scale datasets, show that the proposed method outperforms existing methods by a large margin, yielding an average performance improvement of 15.8% across various datasets, establishing a new benchmark for TS forecasting.

cs.LG↗

arXiv2026

Implicit Neural Representation Facilitates Unified Universal Vision Encoding

Models for image representation learning are typically designed for either recognition or generation. Various forms of contrastive learning help models learn to convert images to embeddings that are useful for classification, detection, and segmentation. On the other hand, models can be trained to reconstruct images with pixel-wise, perceptual, and adversarial losses in order to learn a latent space that is useful for image generation. We seek to unify these two directions with a first-of-its-kind model that learns representations which are simultaneously useful for recognition and generation. We train our model as a hyper-network for implicit neural representation, which learns to map images to model weights for fast, accurate reconstruction. We further integrate our INR hyper-network with knowledge distillation to improve its generalization and performance. Beyond the novel training design, the model also learns an unprecedented compressed embedding space with outstanding performance for various visual tasks. The complete model competes with state-of-the-art results for image representation learning, while also enabling generative capabilities with its high-quality tiny embeddings. The code is available at https://github.com/tiktok/huvr.

cs.CV↗

arXiv2026

Coherent Two-State Oscillations in False Vacuum Decay Regimes

Coherent two-state oscillations are observed in numerical simulations of the one-dimensional transverse-longitudinal-field Ising model (TLFIM) within false vacuum decay regimes. Starting from the false vacuum (a nearly fully polarized ferromagnetic state), we show that in moderate-sized systems, at resonances $h\approx 2J/n$ (with longitudinal field $h$, transverse field $J$, and an integer $n$), the expected decay can give way to coherent oscillations between the false vacuum and a symmetric resonant state. The oscillation frequency, i.e., the tunneling splitting, is observed notably to exhibit a superradiant-like $\sqrt{L}$ enhancement, as confirmed by a Schrieffer-Wolff analysis. In large chains, coherence remains for $n\gtrsim L/2$ due to bubble-size blockade and is robust against stronger transverse fields; for small $n$, long-range interactions can stabilize the oscillations by lifting multi-bubble degeneracies, establishing a robust many-body coherence mechanism beyond perturbative and finite-size limits.

quant-ph↗

arXiv2026

Electrically tunable nonrigid moire exciton polariton supersolids at room temperature

A supersolid is a macroscopic quantum state which sustains superfluid and crystallizing structure together after breaking the U(1) symmetry and translational symmetry. On the other hand, a moire pattern can form by superimposing two periodic structures along a particular direction. Up to now, supersolids and moire states are disconnected from each other. In this work we show that exciton polariton supersolids can form moire states in a double degenerate parametric scattering process which creates two constituted supersolids with different periods in a liquid crystal microcavity. In addition, we demonstrate the nonrigidity of the moire exciton polariton supersolids by electrically tuning the wavevector and period of one supersolid component with another one being fixed. Our work finds a simple way to link moire states and supersolids, which offers to study nontrivial physics emerging from the combination of moire lattices and supersolids which can be electrically tuned at room temperature.

physics.optics↗

arXiv2026

The Geometric Origin of the Cayley-Hamilton Theorem: A Constructive Proof via Dimensional Syzygy

We demonstrate that the Cayley-Hamilton theorem is a derived consequence of a more fundamental dimensional constraint: the syzygy formed by the tensor product of two Levi-Civita symbols, which vanishes identically in m-dimensional space. By shifting perspective from the tensor A to the isotropic operators that induce A's invariants through contraction, we reveal that the Cayley-Hamilton identity emerges when this vanishing operator acts on the m-fold tensor product of A. The intrinsic tensorial form of the theorem--invariant coefficients multiplying tensor powers--is inherited from the contraction structure rather than imposed ad hoc. We provide explicit verification for two-dimensional space and a dimension-independent proof using Laplace expansion combined with Newton-Girard identities. This framework clarifies why the theorem's structure depends on ambient dimension and suggests extensions to higher-order tensors where classical characteristic polynomial methods fail.

math.RA↗

arXiv2026

Decoupling Amplitude and Phase Attention in Frequency Domain for RGB-Event based Visual Object Tracking

Existing RGB-Event visual object tracking approaches primarily rely on conventional feature-level fusion, failing to fully exploit the unique advantages of event cameras. In particular, the high dynamic range and motion-sensitive nature of event cameras are often overlooked, while low-information regions are processed uniformly, leading to unnecessary computational overhead for the backbone network. To address these issues, we propose a novel tracking framework that performs early fusion in the frequency domain, enabling effective aggregation of high-frequency information from the event modality. Specifically, RGB and event modalities are transformed from the spatial domain to the frequency domain via the Fast Fourier Transform, with their amplitude and phase components decoupled. High-frequency event information is selectively fused into RGB modality through amplitude and phase attention, enhancing feature representation while substantially reducing backbone computation. In addition, a motion-guided spatial sparsification module leverages the motion-sensitive nature of event cameras to capture the relationship between target motion cues and spatial probability distribution, filtering out low-information regions and enhancing target-relevant features. Finally, a sparse set of target-relevant features is fed into the backbone network for learning, and the tracking head predicts the final target position. Extensive experiments on three widely used RGB-Event tracking benchmark datasets, including FE108, FELT, and COESOT, demonstrate the high performance and efficiency of our method. The source code of this paper will be released on https://github.com/Event-AHU/OpenEvTracking

cs.CV↗

arXiv2025

From cluster to nanocrystal: the continuous evolution and critical size of copper clusters revealed by machine learning

The evolution of cluster structure with size and the critical size for the transition from cluster to nanocrystal have long been fundamental problems in nanoscience. Due to limitations of experimental technology and computational methods, the exploration of the continuous evolution of clusters towards nanocrystal is still a big challenge. Here, we proposed a machine learning force field (MLFF) that can generalize well to various copper systems ranging from small clusters to large clusters and bulk. The continuous evolution of copper clusters CuN towards nanocrystal was revealed by investigating clusters in a wide size range (7 <= N <= 17885) based on MLFF simulated annealing. For small CuN (N < 40), electron counting rule plays a major role in stability. For large CuN (N > 80), geometric magic number rule plays a dominant role and the evolution of clusters is based on the formation of more and more icosahedral shells. For medium size CuN (40 <= N <= 80), both rules contribute. The critical size from cluster to nanocrystal was calculated to be around 8000 atoms (about 6 nm in diameter). Our work terminates the long-term challenge in nanoscience, and lay the methodological foundation for subsequent research on other cluster systems.

cond-mat.mtrl-sci↗

arXiv2025

Deep learning-enhanced dual-mode multiplexed optical sensor for point-of-care diagnostics of cardiovascular diseases

Rapid and accessible cardiac biomarker testing is essential for the timely diagnosis and risk assessment of myocardial infarction (MI) and heart failure (HF), two interrelated conditions that frequently coexist and drive recurrent hospitalizations with high mortality. However, current laboratory and point-of-care testing systems are limited by long turnaround times, narrow dynamic ranges for the tested biomarkers, and single-analyte formats that fail to capture the complexity of cardiovascular disease. Here, we present a deep learning-enhanced dual-mode multiplexed vertical flow assay (xVFA) with a portable optical reader and a neural network-based quantification pipeline. This optical sensor integrates colorimetric and chemiluminescent detection within a single paper-based cartridge to complementarily cover a large dynamic range (spanning ~6 orders of magnitude) for both low- and high-abundance biomarkers, while maintaining quantitative accuracy. Using 50 uL of serum, the optical sensor simultaneously quantifies cardiac troponin I (cTnI), creatine kinase-MB (CK-MB), and N-terminal pro-B-type natriuretic peptide (NT-proBNP) within 23 min. The xVFA achieves sub-pg/mL sensitivity for cTnI and sub-ng/mL sensitivity for CK-MB and NT-proBNP, spanning the clinically relevant ranges for these biomarkers. Neural network models trained and blindly tested on 92 patient serum samples yielded a robust quantification performance (Pearson's r > 0.96 vs. reference assays). By combining high sensitivity, multiplexing, and automation in a compact and cost-effective optical sensor format, the dual-mode xVFA enables rapid and quantitative cardiovascular diagnostics at the point of care.

physics.med-ph↗

arXiv2025

Statistical structural properties of many-body chaotic eigenfunctions and applications

In this paper, we employ a semiperturbative theory to study the statistical structural properties of energy eigenfunctions (EFs) in many-body quantum chaotic systems consisting of a central system coupled to an environment. Under certain assumptions, we derive both the average shape and the statistical fluctuations of EFs on the basis formed by the direct product of the energy eigenbases of the system and the environment. Furthermore, we apply our results to two fundamental questions: (i) the properties of the reduced density matrix of the central system in an eigenstate, and (ii) the structure of the off-diagonal smooth function within the framework of the eigenstate thermalization hypothesis. Numerical results are also presented in support of our main findings.

cond-mat.stat-mech↗

arXiv2025

Vehicle-centric Perception via Multimodal Structured Pre-training

Vehicle-centric perception plays a crucial role in many intelligent systems, including large-scale surveillance systems, intelligent transportation, and autonomous driving. Existing approaches lack effective learning of vehicle-related knowledge during pre-training, resulting in poor capability for modeling general vehicle perception representations. To handle this problem, we propose VehicleMAE-V2, a novel vehicle-centric pre-trained large model. By exploring and exploiting vehicle-related multimodal structured priors to guide the masked token reconstruction process, our approach can significantly enhance the model's capability to learn generalizable representations for vehicle-centric perception. Specifically, we design the Symmetry-guided Mask Module (SMM), Contour-guided Representation Module (CRM) and Semantics-guided Representation Module (SRM) to incorporate three kinds of structured priors into token reconstruction including symmetry, contour and semantics of vehicles respectively. SMM utilizes the vehicle symmetry constraints to avoid retaining symmetric patches and can thus select high-quality masked image patches and reduce information redundancy. CRM minimizes the probability distribution divergence between contour features and reconstructed features and can thus preserve holistic vehicle structure information during pixel-level reconstruction. SRM aligns image-text features through contrastive learning and cross-modal distillation to address the feature confusion caused by insufficient semantic understanding during masked reconstruction. To support the pre-training of VehicleMAE-V2, we construct Autobot4M, a large-scale dataset comprising approximately 4 million vehicle images and 12,693 text descriptions. Extensive experiments on five downstream tasks demonstrate the superior performance of VehicleMAE-V2.

cs.CV↗

arXiv2025

SLCFormer: Spectral-Local Context Transformer with Physics-Grounded Flare Synthesis for Nighttime Flare Removal

Lens flare is a common nighttime artifact caused by strong light sources scattering within camera lenses, leading to hazy streaks, halos, and glare that degrade visual quality. However, existing methods usually fail to effectively address nonuniform scattered flares, which severely reduces their applicability to complex real-world scenarios with diverse lighting conditions. To address this issue, we propose SLCFormer, a novel spectral-local context transformer framework for effective nighttime lens flare removal. SLCFormer integrates two key modules: the Frequency Fourier and Excitation Module (FFEM), which captures efficient global contextual representations in the frequency domain to model flare characteristics, and the Directionally-Enhanced Spatial Module (DESM) for local structural enhancement and directional features in the spatial domain for precise flare removal. Furthermore, we introduce a ZernikeVAE-based scatter flare generation pipeline to synthesize physically realistic scatter flares with spatially varying PSFs, bridging optical physics and data-driven training. Extensive experiments on the Flare7K++ dataset demonstrate that our method achieves state-of-the-art performance, outperforming existing approaches in both quantitative metrics and perceptual visual quality, and generalizing robustly to real nighttime scenes with complex flare artifacts.

cs.CV↗

arXiv2025

Constraining the dark matter origin of the halo-like 20 GeV $γ$-ray excess with the AMS-02 antiproton data

Very recently, a significant $\sim 20$ GeV gamma-ray excess in the Milky Way halo has been reported and a dark matter origin has been suggested. The inferred dark matter parameters are $ m_χ\sim 0.5-0.8 $ TeV and $ \langle σv \rangle \sim (5-8) \times 10^{-25}~{\rm cm^3~s^{-1}}$ for the $ b\bar{b} $ channel. If correct, prominent antiproton emission is produced and can be directly tested by the AMS-02 data. In this work we calculate the corresponding antiproton emission and show that the expected flux at $\sim 100$ GeV is already above the AMS-02 observation. A proper treatment on the antiproton background resulting from the high energy cosmic ray propagation would suggest an annihilation cross section of $< 2\times 10^{-26}~{\rm cm^3~s^{-1}}$, which is a few$\times 10$ times lower than that needed to interpret the potential signal. We therefore conclude that the $\sim 20$ GeV gamma-ray excess in the Milky Way halo is not a viable dark matter signal.

astro-ph.HE↗

arXiv2025

RoadBench: A Vision-Language Foundation Model and Benchmark for Road Damage Understanding

Accurate road damage detection is crucial for timely infrastructure maintenance and public safety, but existing vision-only datasets and models lack the rich contextual understanding that textual information can provide. To address this limitation, we introduce RoadBench, the first multimodal benchmark for comprehensive road damage understanding. This dataset pairs high resolution images of road damages with detailed textual descriptions, providing a richer context for model training. We also present RoadCLIP, a novel vision language model that builds upon CLIP by integrating domain specific enhancements. It includes a disease aware positional encoding that captures spatial patterns of road defects and a mechanism for injecting road-condition priors to refine the model's understanding of road damages. We further employ a GPT driven data generation pipeline to expand the image to text pairs in RoadBench, greatly increasing data diversity without exhaustive manual annotation. Experiments demonstrate that RoadCLIP achieves state of the art performance on road damage recognition tasks, significantly outperforming existing vision-only models by 19.2%. These results highlight the advantages of integrating visual and textual information for enhanced road condition analysis, setting new benchmarks for the field and paving the way for more effective infrastructure monitoring through multimodal learning.

cs.CE↗

arXiv2025

Diffusion Model Regularized Implicit Neural Representation for CT Metal Artifact Reduction

Computed tomography (CT) images are often severely corrupted by artifacts in the presence of metals. Existing supervised metal artifact reduction (MAR) approaches suffer from performance instability on known data due to their reliance on limited paired metal-clean data, which limits their clinical applicability. Moreover, existing unsupervised methods face two main challenges: 1) the CT physical geometry is not effectively incorporated into the MAR process to ensure data fidelity; 2) traditional heuristics regularization terms cannot fully capture the abundant prior knowledge available. To overcome these shortcomings, we propose diffusion model regularized implicit neural representation framework for MAR. The implicit neural representation integrates physical constraints and imposes data fidelity, while the pre-trained diffusion model provides prior knowledge to regularize the solution. Experimental results on both simulated and clinical data demonstrate the effectiveness and generalization ability of our method, highlighting its potential to be applied to clinical settings.

cs.CV↗

arXiv2025

DualHash: A Stochastic Primal-Dual Algorithm with Theoretical Guarantee for Deep Hashing

Deep hashing converts high-dimensional feature vectors into compact binary codes, enabling efficient large-scale retrieval. A fundamental challenge in deep hashing stems from the discrete nature of quantization in generating the codes. W-type regularizations, such as $||z|-1|$, have been proven effective as they encourage variables toward binary values. However, existing methods often directly optimize these regularizations without convergence guarantees. While proximal gradient methods offer a promising solution, the coupling between W-type regularizers and neural network outputs results in composite forms that generally lack closed-form proximal solutions. In this paper, we present a stochastic primal-dual hashing algorithm, referred to as DualHash, that provides rigorous complexity bounds. Using Fenchel duality, we partially transform the nonconvex W-type regularization optimization into the dual space, which results in a proximal operator that admits closed-form solutions. We derive two algorithm instances: a momentum-accelerated version with $\mathcal{O}(\varepsilon^{-4})$ complexity and an improved $\mathcal{O}(\varepsilon^{-3})$ version using variance reduction. Experiments on three image retrieval databases demonstrate the superior performance of DualHash.

math.OC↗

arXiv2025

Phase-multiplexed optical computing: Reconfiguring a multi-task diffractive optical processor using illumination phase diversity

We report a monochrome multi-task diffractive network architecture that leverages illumination phase multiplexing to dynamically reconfigure its output function and accurately implement a large group of complex-valued linear transformations between an input and output aperture. Each member of the desired group of T unique transformations is encoded and addressed with a distinct 2D illumination phase profile, termed "phase key", which illuminates the input aperture, activating the corresponding transformation at the output field-of-view. A common diffractive optical network, optimized with T phase keys, demultiplexes these encoded inputs and accurately executes any of the T distinct linear transformations at its output. We demonstrate that a diffractive network composed of N = 2 x T x Ni x No optimized diffractive features can realize T distinct complex-valued linear transformations, accurately executed for any complex field at the input aperture, where Ni and No refer to the input/output pixels, respectively. In our proof-of-concept numerical analysis, T = 512 complex-valued transformations are implemented by the same monochrome diffractive network with negligible error using illumination phase diversity. Compared with wavelength-multiplexed diffractive systems, phase-multiplexing architecture significantly lowers the transformation errors, potentially enabling larger-scale optical transformations to be implemented through a monochrome processor. Phase-multiplexed multi-task diffractive networks would enhance the capabilities of optical computing and machine-vision systems.

physics.optics↗