arXiv subjects

Xiao Wang

Publications and source records attributed to Xiao Wang.

At least 217 records · Page 12Linked to original sources

arXiv2025

Unifying and Enhancing Graph Transformers via a Hierarchical Mask Framework

Graph Transformers (GTs) have emerged as a powerful paradigm for graph representation learning due to their ability to model diverse node interactions. However, existing GTs often rely on intricate architectural designs tailored to specific interactions, limiting their flexibility. To address this, we propose a unified hierarchical mask framework that reveals an underlying equivalence between model architecture and attention mask construction. This framework enables a consistent modeling paradigm by capturing diverse interactions through carefully designed attention masks. Theoretical analysis under this framework demonstrates that the probability of correct classification positively correlates with the receptive field size and label consistency, leading to a fundamental design principle: an effective attention mask should ensure both a sufficiently large receptive field and a high level of label consistency. While no single existing mask satisfies this principle across all scenarios, our analysis reveals that hierarchical masks offer complementary strengths, motivating their effective integration. Then, we introduce M3Dphormer, a Mixture-of-Experts-based Graph Transformer with Multi-Level Masking and Dual Attention Computation. M3Dphormer incorporates three theoretically grounded hierarchical masks and employs a bi-level expert routing mechanism to adaptively integrate multi-level interaction information. To ensure scalability, we further introduce a dual attention computation scheme that dynamically switches between dense and sparse modes based on local mask sparsity. Extensive experiments across multiple benchmarks demonstrate that M3Dphormer achieves state-of-the-art performance, validating the effectiveness of our unified framework and model design.

cs.CV↗

arXiv2025

EMRRG: Efficient Fine-Tuning Pre-trained X-ray Mamba Networks for Radiology Report Generation

X-ray image-based medical report generation (MRG) is a pivotal area in artificial intelligence that can significantly reduce diagnostic burdens for clinicians and patient wait times. Existing MRG models predominantly rely on Large Language Models (LLMs) to improve report generation, with limited exploration of pre-trained vision foundation models or advanced fine-tuning techniques. Mainstream frameworks either avoid fine-tuning or utilize simplistic methods like LoRA, often neglecting the potential of enhancing cross-attention mechanisms. Additionally, while Transformer-based models dominate vision-language tasks, non-Transformer architectures, such as the Mamba network, remain underexplored for medical report generation, presenting a promising avenue for future research. In this paper, we propose EMRRG, a novel X-ray report generation framework that fine-tunes pre-trained Mamba networks using parameter-efficient methods. Specifically, X-ray images are divided into patches, tokenized, and processed by an SSM-based vision backbone for feature extraction, with Partial LoRA yielding optimal performance. An LLM with a hybrid decoder generates the medical report, enabling end-to-end training and achieving strong results on benchmark datasets. Extensive experiments on three widely used benchmark datasets fully validated the effectiveness of our proposed strategies for the X-ray MRG. The source code of this paper will be released on https://github.com/Event-AHU/Medical_Image_Analysis.

cs.CV↗

arXiv2025

AngularFuse: A Closer Look at Angle-based Perception for Spatial-Sensitive Multi-Modality Image Fusion

Visible-infrared image fusion is crucial in key applications such as autonomous driving and nighttime surveillance. Its main goal is to integrate multimodal information to produce enhanced images that are better suited for downstream tasks. Although deep learning based fusion methods have made significant progress, mainstream unsupervised approaches still face serious challenges in practical applications. Existing methods mostly rely on manually designed loss functions to guide the fusion process. However, these loss functions have obvious limitations. On one hand, the reference images constructed by existing methods often lack details and have uneven brightness. On the other hand, the widely used gradient losses focus only on gradient magnitude. To address these challenges, this paper proposes an angle-based perception framework for spatial-sensitive image fusion (AngularFuse). At first, we design a cross-modal complementary mask module to force the network to learn complementary information between modalities. Then, a fine-grained reference image synthesis strategy is introduced. By combining Laplacian edge enhancement with adaptive histogram equalization, reference images with richer details and more balanced brightness are generated. Last but not least, we introduce an angle-aware loss, which for the first time constrains both gradient magnitude and direction simultaneously in the gradient domain. AngularFuse ensures that the fused images preserve both texture intensity and correct edge orientation. Comprehensive experiments on the MSRS, RoadScene, and M3FD public datasets show that AngularFuse outperforms existing mainstream methods with clear margin. Visual comparisons further confirm that our method produces sharper and more detailed results in challenging scenes, demonstrating superior fusion capability.

cs.CV↗

arXiv2025

Semiclassical analytical solutions of the eigenstate thermalization hypothesis in a quantum billiard

We derive semiclassical analytical solutions for both the diagonal and off-diagonal functions in the eigenstate thermalization hypothesis (ETH) in a quarter-stadium quantum billiard. For a representative observable, we obtain an explicit expression and an asymptotic closed-form solution that naturally separate into a local contribution and a phase-space correlation term. These analytical results predict the band structure of the observable matrix, including its bandwidth and scaling behavior. We further demonstrate that our analytical formula is equivalent to the prediction of Berry's conjecture. Supported by numerical evidence, we show that Berry's conjecture captures the energetic long-wavelength behavior in the space of eigenstates, while our analytical solution describes the asymptotic behavior of the f function in the semiclassical limit. Finally, by revealing the connection between the bandwidth scaling and the underlying classical dynamics, our results suggest that the ETH carries important physical implications in single-particle and few-body systems, where "thermalization" manifests as the loss of information about initial conditions.

quant-ph↗

arXiv2025

Scrutinizing the impact of the solar modulation on AMS-02 antiproton excess

This study examines the impact of solar modulation on the antiproton excess observed by AMS-02, which may indicate dark matter (DM) annihilation. We analyze three solar modulation models: the force-field approximation (FFA), a time-, charge-, and rigidity-dependent FFA, and a three-dimensional numerical simulation based on the Parker transport equation. Based on AMS-02 latest antiproton data (2025), our results show that the significance of the DM signal is sensitive to the chosen modulation model, with a 2$σ$ signal for the FFA (4$σ$ if including data from H, He, C, O, B/C, and B/O) and a reduced significance for more complex models. We also address systematic uncertainties using two methods: the add-in-quadrature method, which assumes uncorrelated uncertainties between energy bins, and the nuisance parameter method, which treats systematic uncertainties as nuisance parameters during the fitting process. Fitted to AMS-02 antiproton data, DM annihilation to the $b\bar{b}$ scenario with three different solar modulation models shows that the add-in-quadrature method causes overfitting, whereas the nuisance parameters approach leads to underfitting. Statistically, the signal region of the FFA model using the add-in-quadrature method is the most reliable. This work highlights the need for refined solar modulation models and a better treatment of uncertainties for a conclusive interpretation of the AMS-02 data.

astro-ph.CO↗

arXiv2025

CTR-LoRA: Curvature-Aware and Trust-Region Guided Low-Rank Adaptation for Large Language Models

Parameter-efficient fine-tuning (PEFT) has become the standard approach for adapting large language models under limited compute and memory budgets. Although previous methods improve efficiency through low-rank updates, quantization, or heuristic budget reallocation, they often decouple the allocation of capacity from the way updates evolve during training. In this work, we introduce CTR-LoRA, a framework guided by curvature trust region that integrates rank scheduling with stability-aware optimization. CTR-LoRA allocates parameters based on marginal utility derived from lightweight second-order proxies and constrains updates using a Fisher/Hessian-metric trust region. Experiments on multiple open-source backbones (7B-13B), evaluated on both in-distribution and out-of-distribution benchmarks, show consistent improvements over strong PEFT baselines. In addition to increased accuracy, CTR-LoRA enhances training stability, reduces memory requirements, and achieves higher throughput, positioning it on the Pareto frontier of performance and efficiency. These results highlight a principled path toward more robust and deployable PEFT.

cs.LG↗

arXiv2025

MoRE-Brain: Routed Mixture of Experts for Interpretable and Generalizable Cross-Subject fMRI Visual Decoding

Decoding visual experiences from fMRI offers a powerful avenue to understand human perception and develop advanced brain-computer interfaces. However, current progress often prioritizes maximizing reconstruction fidelity while overlooking interpretability, an essential aspect for deriving neuroscientific insight. To address this gap, we propose MoRE-Brain, a neuro-inspired framework designed for high-fidelity, adaptable, and interpretable visual reconstruction. MoRE-Brain uniquely employs a hierarchical Mixture-of-Experts architecture where distinct experts process fMRI signals from functionally related voxel groups, mimicking specialized brain networks. The experts are first trained to encode fMRI into the frozen CLIP space. A finetuned diffusion model then synthesizes images, guided by expert outputs through a novel dual-stage routing mechanism that dynamically weighs expert contributions across the diffusion process. MoRE-Brain offers three main advancements: First, it introduces a novel Mixture-of-Experts architecture grounded in brain network principles for neuro-decoding. Second, it achieves efficient cross-subject generalization by sharing core expert networks while adapting only subject-specific routers. Third, it provides enhanced mechanistic insight, as the explicit routing reveals precisely how different modeled brain regions shape the semantic and spatial attributes of the reconstructed image. Extensive experiments validate MoRE-Brain's high reconstruction fidelity, with bottleneck analyses further demonstrating its effective utilization of fMRI signals, distinguishing genuine neural decoding from over-reliance on generative priors. Consequently, MoRE-Brain marks a substantial advance towards more generalizable and interpretable fMRI-based visual decoding. Code will be publicly available soon: https://github.com/yuxiangwei0808/MoRE-Brain.

cs.LG↗

arXiv2025

Fast-RF-Shimming: Accelerate RF Shimming in 7T MRI using Deep Learning

Ultrahigh field (UHF) Magnetic Resonance Imaging (MRI) offers an elevated signal-to-noise ratio (SNR), enabling exceptionally high spatial resolution that benefits both clinical diagnostics and advanced research. However, the jump to higher fields introduces complications, particularly transmit radiofrequency (RF) field ($B_{1}^{+}$) inhomogeneities, manifesting as uneven flip angles and image intensity irregularities. These artifacts can degrade image quality and impede broader clinical adoption. Traditional RF shimming methods, such as Magnitude Least Squares (MLS) optimization, effectively mitigate $B_{1}^{+}$ inhomogeneity, but remain time-consuming. Recent machine learning approaches, including RF Shim Prediction by Iteratively Projected Ridge Regression and other deep learning architectures, suggest alternative pathways. Although these approaches show promise, challenges such as extensive training periods, limited network complexity, and practical data requirements persist. In this paper, we introduce a holistic learning-based framework called Fast-RF-Shimming, which achieves a 5000x speed-up compared to the traditional MLS method. In the initial phase, we employ random-initialized Adaptive Moment Estimation (Adam) to derive the desired reference shimming weights from multi-channel $B_{1}^{+}$ fields. Next, we train a Residual Network (ResNet) to map $B_{1}^{+}$ fields directly to the ultimate RF shimming outputs, incorporating the confidence parameter into its loss function. Finally, we design Non-uniformity Field Detector (NFD), an optional post-processing step, to ensure the extreme non-uniform outcomes are identified. Comparative evaluations with standard MLS optimization underscore notable gains in both processing speed and predictive accuracy, which indicates that our technique shows a promising solution for addressing persistent inhomogeneity challenges.

cs.CV↗

arXiv2025

CryoCCD: Conditional Cycle-consistent Diffusion with Biophysical Modeling for Cryo-EM Synthesis

Single-particle cryo-electron microscopy (cryo-EM) has become a cornerstone of structural biology, enabling near-atomic resolution analysis of macromolecules through advanced computational methods. However, the development of cryo-EM processing tools is constrained by the scarcity of high-quality annotated datasets. Synthetic data generation offers a promising alternative, but existing approaches lack thorough biophysical modeling of heterogeneity and fail to reproduce the complex noise observed in real imaging. To address these limitations, we present CryoCCD, a synthesis framework that unifies versatile biophysical modeling with the first conditional cycle-consistent diffusion model tailored for cryo-EM. The biophysical engine provides multi-functional generation capabilities to capture authentic biological organization, and the diffusion model is enhanced with cycle consistency and mask-guided contrastive learning to ensure realistic noise while preserving structural fidelity. Extensive experiments demonstrate that CryoCCD generates structurally faithful micrographs, enhances particle picking and pose estimation, as well as achieves superior performance over state-of-the-art baselines, while also generalizing effectively to held-out protein families.

cs.CV↗

arXiv2025

Towards Foundation Models for Cryo-ET Subtomogram Analysis

Cryo-electron tomography (cryo-ET) enables in situ visualization of macromolecular structures, where subtomogram analysis tasks such as classification, alignment, and averaging are critical for structural determination. However, effective analysis is hindered by scarce annotations, severe noise, and poor generalization. To address these challenges, we take the first step towards foundation models for cryo-ET subtomograms. First, we introduce CryoEngine, a large-scale synthetic data generator that produces over 904k subtomograms from 452 particle classes for pretraining. Second, we design an Adaptive Phase Tokenization-enhanced Vision Transformer (APT-ViT), which incorporates adaptive phase tokenization as an equivariance-enhancing module that improves robustness to both geometric and semantic variations. Third, we introduce a Noise-Resilient Contrastive Learning (NRCL) strategy to stabilize representation learning under severe noise conditions. Evaluations across 24 synthetic and real datasets demonstrate state-of-the-art (SOTA) performance on all three major subtomogram tasks and strong generalization to unseen datasets, advancing scalable and robust subtomogram analysis in cryo-ET.

cs.CV↗

arXiv2025

GEM: 3D Gaussian Splatting for Efficient and Accurate Cryo-EM Reconstruction

Cryo-electron microscopy (cryo-EM) has become a central tool for high-resolution structural biology, yet the massive scale of datasets (often exceeding 100k particle images) renders 3D reconstruction both computationally expensive and memory intensive. Traditional Fourier-space methods are efficient but lose fidelity due to repeated transforms, while recent real-space approaches based on neural radiance fields (NeRFs) improve accuracy but incur cubic memory and computation overhead. Therefore, we introduce GEM, a novel cryo-EM reconstruction framework built on 3D Gaussian Splatting (3DGS) that operates directly in real-space while maintaining high efficiency. Instead of modeling the entire density volume, GEM represents proteins with compact 3D Gaussians, each parameterized by only 11 values. To further improve the training efficiency, we designed a novel gradient computation to 3D Gaussians that contribute to each voxel. This design substantially reduced both memory footprint and training cost. On standard cryo-EM benchmarks, GEM achieves up to 48% faster training and 12% lower memory usage compared to state-of-the-art methods, while improving local resolution by as much as 38.8%. These results establish GEM as a practical and scalable paradigm for cryo-EM reconstruction, unifying speed, efficiency, and high-resolution accuracy. Our code is available at https://github.com/UNITES-Lab/GEM.

cs.CV↗

arXiv2025

An operator-Weyl-symbol approach to eigenstate thermalization hypothesis

In this letter, by an approach that employs Weyl symbols for operators, a semiclassical theory is developed for the offdiagonal function in the eigenstate thermalization hypothesis, which is for offdiagonal elements $\langle{E_i}\left|O\right|{E_j}\rangle$ of an observable $O$ on the energy basis. It is shown analytically that the matrix of $O$ has a banded structure, possessing a bandwidth $w_b$ that scales linearly with $\hbar$, a phase-space gradient of the classical Hamiltonian, $\langle\left|{\boldsymbol{\nabla }H_{\rm cl}}\right|\rangle$, and an $O$-dependent property. This predicts that the thermalization timescale of a quantum system may be inversely proportional to the phase-space gradient of the Hamiltonian, aligning with intuitions in classical thermalization. This approach also elucidates the origin of a $ρ_{\rm dos}^{-1/2}$-scaling of the offdiagonal function. The analytical predictions are checked numerically in the Lipkin-Meshkov-Glick model.

quant-ph↗

arXiv2025

First-order methods almost always avoid saddle points: the case of vanishing step-sizes

In a series of papers \cite{LSJR16, PP17, LPP}, it was established that some of the most commonly used first order methods almost surely (under random initializations) and with step-size being small enough, avoid strict saddle points, as long as the objective function $f$ is $C^2$ and has Lipschitz gradient. The key observation was that first order methods can be studied from a dynamical systems perspective, in which instantiations of Center-Stable manifold theorem allow for a global analysis. The results of the aforementioned papers were limited to the case where the step-size $α$ is constant, i.e., does not depend on time (and bounded from the inverse of the Lipschitz constant of the gradient of $f$). It remains an open question whether or not the results still hold when the step-size is time dependent and vanishes with time. In this paper, we resolve this question on the affirmative for gradient descent, mirror descent, manifold descent and proximal point. The main technical challenge is that the induced (from each first order method) dynamical system is time non-homogeneous and the stable manifold theorem is not applicable in its classic form. By exploiting the dynamical systems structure of the aforementioned first order methods, we are able to prove a stable manifold theorem that is applicable to time non-homogeneous dynamical systems and generalize the results in \cite{LPP} for vanishing step-sizes.

math.OC↗

arXiv2025

Last iterate convergence in no-regret learning: constrained min-max optimization for convex-concave landscapes

In a recent series of papers it has been established that variants of Gradient Descent/Ascent and Mirror Descent exhibit last iterate convergence in convex-concave zero-sum games. Specifically, \cite{DISZ17, LiangS18} show last iterate convergence of the so called "Optimistic Gradient Descent/Ascent" for the case of \textit{unconstrained} min-max optimization. Moreover, in \cite{Metal} the authors show that Mirror Descent with an extra gradient step displays last iterate convergence for convex-concave problems (both constrained and unconstrained), though their algorithm does not follow the online learning framework; it uses extra information rather than \textit{only} the history to compute the next iteration. In this work, we show that "Optimistic Multiplicative-Weights Update (OMWU)" which follows the no-regret online learning framework, exhibits last iterate convergence locally for convex-concave games, generalizing the results of \cite{DP19} where last iterate convergence of OMWU was shown only for the \textit{bilinear case}. We complement our results with experiments that indicate fast convergence of the method.

cs.LG↗

arXiv2025

Stochastic Interpolants via Conditional Dependent Coupling

Existing image generation models face critical challenges regarding the trade-off between computation and fidelity. Specifically, models relying on a pretrained Variational Autoencoder (VAE) suffer from information loss, limited detail, and the inability to support end-to-end training. In contrast, models operating directly in the pixel space incur prohibitive computational cost. Although cascade models can mitigate computational cost, stage-wise separation prevents effective end-to-end optimization, hampers knowledge sharing, and often results in inaccurate distribution learning within each stage. To address these challenges, we introduce a unified multistage generative framework based on our proposed Conditional Dependent Coupling strategy. It decomposes the generative process into interpolant trajectories at multiple stages, ensuring accurate distribution learning while enabling end-to-end optimization. Importantly, the entire process is modeled as a single unified Diffusion Transformer, eliminating the need for disjoint modules and also enabling knowledge sharing. Extensive experiments demonstrate that our method achieves both high fidelity and efficiency across multiple resolutions.

cs.CV↗

arXiv2025

PHASE: Physics-Integrated, Heterogeneity-Aware Surrogates for Scientific Simulations

Large-scale numerical simulations underpin modern scientific discovery but remain constrained by prohibitive computational costs. AI surrogates offer acceleration, yet adoption in mission-critical settings is limited by concerns over physical plausibility, trustworthiness, and the fusion of heterogeneous data. We introduce PHASE, a modular deep-learning framework for physics-integrated, heterogeneity-aware surrogates in scientific simulations. PHASE combines data-type-aware encoders for heterogeneous inputs with multi-level physics-based constraints that promote consistency from local dynamics to global system behavior. We validate PHASE on the biogeochemical (BGC) spin-up workflow of the U.S. Department of Energy's Energy Exascale Earth System Model (E3SM) Land Model (ELM), presenting-to our knowledge-the first scientifically validated AI-accelerated solution for this task. Using only the first 20 simulation years, PHASE infers a near-equilibrium state that otherwise requires more than 1,200 years of integration, yielding an effective reduction in required integration length by at least 60x. The framework is enabled by a pipeline for fusing heterogeneous scientific data and demonstrates strong generalization to higher spatial resolutions with minimal fine-tuning. These results indicate that PHASE captures governing physical regularities rather than surface correlations, enabling practical, physically consistent acceleration of land-surface modeling and other complex scientific workflows.

cs.LG↗

arXiv2025

Pedestrian Attribute Recognition via Hierarchical Cross-Modality HyperGraph Learning

Current Pedestrian Attribute Recognition (PAR) algorithms typically focus on mapping visual features to semantic labels or attempt to enhance learning by fusing visual and attribute information. However, these methods fail to fully exploit attribute knowledge and contextual information for more accurate recognition. Although recent works have started to consider using attribute text as additional input to enhance the association between visual and semantic information, these methods are still in their infancy. To address the above challenges, this paper proposes the construction of a multi-modal knowledge graph, which is utilized to mine the relationships between local visual features and text, as well as the relationships between attributes and extensive visual context samples. Specifically, we propose an effective multi-modal knowledge graph construction method that fully considers the relationships among attributes and the relationships between attributes and vision tokens. To effectively model these relationships, this paper introduces a knowledge graph-guided cross-modal hypergraph learning framework to enhance the standard pedestrian attribute recognition framework. Comprehensive experiments on multiple PAR benchmark datasets have thoroughly demonstrated the effectiveness of our proposed knowledge graph for the PAR task, establishing a strong foundation for knowledge-guided pedestrian attribute recognition. The source code of this paper will be released on https://github.com/Event-AHU/OpenPAR

cs.CV↗

arXiv2025

Persistence modules induced by inner functions

As well-known, inner functions play an important role in the study of bounded analytic function theory. In recent years, persistence module theory, as a main tool applied to Topological Data Analysis, has received widespread attention. In this paper, we aim to use persistence module theory to study inner functions. We introduce the persistence modules arised from the level sets of inner functions. Some properties of these persistence modules are shown. In particular, we prove that the persistence modules (potentially not of locally finite type) induced by a class of inner functions have interval module decompositions. Furthermore, we demonstrate that the interleaving distance of the persistence modules is continuous with respect to the supremum norm for a class of Blaschke products, which could be used to discuss the path-connectedness of Blaschke products. As an example, we provide an explicit formula for the interleaving distance of the persistence modules induced by the Blaschke products with order two.

math.AT↗