Searcharxiv⌕ Search

arXiv subjects

Xiao Wang

Publications and source records attributed to Xiao Wang.

At least 37 records · Page 2Linked to original sources
arXiv2026

OpenMASC: An Open-Source Pipeline for Cross-Trajectory Metal-Aware Sampling and Correction in Accelerated MRI

Metal implants corrupt MRI measurements throughout $k$-space, yet existing accelerated MRI methods assume clean data and most metal artifact reduction approaches assume fully sampled acquisitions. No public dataset provides paired $k$-space and images with and without metal for the same anatomy, and no framework jointly addresses artifact-aware acquisition and reconstruction across sampling trajectories. We present OpenMASC, an open-source pipeline covering the full workflow from data generation to deployment. A physics-based data generation module converts public CT volumes into paired clean and metal-corrupted MRI data in both Cartesian and radial formats. MA-VarNet, an unrolled reconstruction network with a per-cascade DC Rectifier, corrects artifacts that data-consistency steps reintroduce from corrupted measurements. A reinforcement learning agent actively selects $k$-space readouts and co-trains with the reconstruction network through a decoupled three-stage procedure. The framework is trajectory-agnostic except for the data-consistency operator, supporting both Cartesian and radial acquisition without architectural changes. Experiments on two datasets at $4\times$ and $8\times$ acceleration demonstrate consistent improvements over conventional and learned baselines on both trajectories.

cs.CV↗
arXiv2026

Revisiting AdaGrad in Stochastic Convex Optimization: Last Iterates, High Probability, and Lower Bounds

AdaGrad and AdaGrad-Norm are widely used adaptive methods, but their precise behavior in stochastic convex optimization remains less understood. We first show that AdaGrad-Norm and AdaGrad do not admit any universal \textbf{last-iterate} rate, even under sub-Gaussian noise and bounded iterates. We then prove that bounded variance alone is too weak: even with bounded iterates, it cannot yield \textbf{high-probability average-iterate} rates, and without bounded iterates it may not even guarantee convergence in expectation. Besides, we construct tight $Ω(\log T/\sqrt T)$ lower bounds for both AdaGrad-Norm and AdaGrad under sub-Gaussian noise, showing that $\log T$ in existing average-iterate upper bounds is unavoidable. Finally, we show that this $\log T$ loss disappears once bounded-iterate condition is imposed: under a general ABC condition, both methods achieve rates ${O}(1/\sqrt{T})$.

math.OC↗
arXiv2026

Structure-Guided Masked Autoencoders for Ultra-High Resolution Scientific Image Understanding

Self-supervised pre-training with Vision Transformers, including Masked Autoencoders (MAE), is difficult to apply to gigapixel scientific images. Random masking is poorly matched to the structured, multi-scale morphology of scientific data, while uniform tokenization produces prohibitively long sequences that make $O(N^2)$ attention impractical. We propose SGMA, a structure-guided masked autoencoding framework for ultra-high-resolution scientific images. SGMA couples two components: a content-adaptive quadtree tokenizer that compresses gigapixel images into a fixed-length sequence, and a structure-conditioned masking process that biases reconstruction toward spatially informative regions. To stabilize this process across scales, we introduce Damped Accumulation (DA), which aggregates signal-dependent responses across the tree into a structure canvas used to guide masking. The resulting pre-training task preserves fine microstructure while remaining compatible with standard ViT encoders and MAE-style reconstruction. Across electron microscopy, whole-slide optical microscopy, and X-ray CT datasets, SGMA consistently outperforms MAE baselines. It achieves 95.68% Dice on the 8K x 8K x 28K SpringXCT dataset, improving over the same-architecture MAE baseline by +13.00 points, and 83.21% Dice on the 32K^2 WSI PAIP dataset, improving by +16.84 points, while providing up to a 24.8x inference speedup.

cs.CV↗
arXiv2026

StationPDE: Station-Oriented Surface PDE Learning for Multi-Station Multivariate Weather Forecasting

Multi-station multivariate weather forecasting aims to forecast future weather variables at multiple weather stations from historical surface observations. Existing station forecasting models learn statistical dependencies among discrete stations, but lack explicit physical evolution. Meanwhile, PDE-based weather models provide interpretable physical dynamics, yet require continuous fields and upper-air variables unavailable in surface station data. To bridge this gap, we propose StationPDE, a station-oriented surface PDE learning model. StationPDE constructs a terrain-aware continuous surface field from discrete station observations and decomposes its physical evolution into surface wind transport and upper-air inference. Surface wind transport explicitly evolves observable weather variables, while upper-air inference uses learnable horizontal diffusion to approximate the missing influence of unavailable upper-air variables. A parallel data-driven diffusion branch captures complementary motion patterns, and an adaptive router integrates the two forecasts for station-level multivariate forecasting. Experiments on Weather2K and MeteoNet show that StationPDE consistently outperforms state-of-the-art baselines, reducing MSE by about $9.6\%$ on average compared with the strongest baseline.

cs.LG↗
arXiv2026

Fusing Global Diagnostic Signals and Spectral Data for Electron and Ion Temperature Profile Prediction on EAST via Attention-based Neural Networks

Ion temperature Ti and electron temperature Te are fundamental kinetic parameters for evaluating tokamak plasma confinement, turbulent transport and magnetohydrodynamic stability. Reliable prediction of their spatiotemporal profiles is essential for long-pulse steady-state operation on the Experimental Advanced Superconducting Tokamak (EAST). However, existing EAST diagnostic systems have obvious measurement limitations, including narrow applicable conditions of charge exchange recombination spectroscopy and severe signal degradation of edge temperature diagnostics during long discharges. Classical physics-based transport codes suffer from high computational cost and error accumulation, while existing data-driven models only separately predict Ti or Te relying on spectral data, lacking joint Ti/Te modeling and failing under missing spectral measurements. In this work, we propose a multi-modal (i.e., global macroscopic diagnostic signals and spectral data) fusion attention neural network for simultaneous reconstruction of Ti/Te profiles on EAST. It leverages an adaptive attention module to weight global diagnostic features and suppress noise interference, employs convolutional layers to extract deep spectral representations, and utilizes multi-head self-attention to facilitate cross-modal feature interaction. Two separate prediction heads are constructed to output full radial distributions of Ti and Te. This work builds the first EAST-oriented joint Ti/Te prediction model compatible with operating scenarios without spectral diagnostics. Hierarchical attention mechanisms excavate nonlinear multi-modal correlations to realize high-performance dual-temperature profile prediction. The source code of this paper is available on https://github.com/Event-AHU/OpenFusion/tree/main/TiTe_Prediction

physics.plasm-ph↗
arXiv2026

Nuclear Fusion Knowledge Graph Guided Edge-Localized Mode Recognition on EAST

Edge-localized modes (ELMs) are transient magnetohydrodynamic instabilities commonly observed in tokamak plasmas. Although deep time-series models can learn complex dynamic patterns from multi-diagnostic signals, their predictions are mainly data-driven and lack explicit utilization of ELM physics, plasma operating states, and historical discharge experience. As a result, they may confuse categories with similar temporal patterns, particularly under severe class imbalance. To address this issue, we propose KGF-ELM, a Knowledge Graph Fusion Network for ELM Recognition, and introduce a Knowledge Graph Collaborative Fusion Module (KGCFM) that organizes physical evidence from the current time window, ELM prototypes, relational knowledge graph representations, and similar historical discharge cases into complementary multi-source knowledge representations. KGCFM collaboratively models these knowledge sources through physics prototype matching, graph-structured knowledge encoding, historical case retrieval, cross-evidence consistency analysis, and reliability estimation, thereby generating knowledge representations for enhancing temporal features and correcting classification results. Based on this module, KGF-ELM employs a dual-level reliability-aware fusion mechanism. At the feature level, physical residuals and graph-guided knowledge representations are adaptively incorporated into temporal features according to their reliability. At the decision level, reliability gating, minority-class protection, and bounded knowledge correction are used to safely refine the classification results and reduce the negative influence of unreliable knowledge on the base model.

physics.plasm-ph↗
arXiv2026

Pre-training, Reasoning, Benchmarking: X-ray Report Generation on CheXpert Plus Dataset

X-ray image-based Radiology Report Generation (RRG) constitutes a critical research direction within medical artificial intelligence, with great potential to alleviate clinicians' diagnostic workload and shorten patient waiting periods. Despite substantial advances over recent years, the field faces evident bottlenecks stemming from insufficient standardized benchmarks and inadequate domain adaptation of generic large models. Notably, the newly released CheXpert Plus dataset is provided without accompanying baseline implementations and evaluation results, which impedes standardized training, quantitative evaluation and fair comparison among follow-up algorithms. To mitigate this limitation, we establish a comprehensive benchmark encompassing prevailing X-ray report generation models and Large Language Models on CheXpert Plus. This benchmark delivers a reliable comparative foundation for upcoming methods and enables researchers to rapidly identify state-of-the-art approaches within this domain. Beyond benchmark construction, we rethink X-ray RRG under the paradigm of large models and propose a novel framework termed MambaXray-PRB. Our framework improves report generation performance and enhances model interpretability via multi-stage large-model pre-training and multi-modal Chain-of-Thought reasoning. The pipeline consists of three successive phases: self-supervised auto-regressive modeling, X-ray-report contrastive learning, and post-training optimization for reasoning and report generation. Extensive experiments on IU X-ray, MIMIC-CXR, and CheXpert Plus datasets validate the effectiveness of MambaXray-PRB for radiology report generation. The source code of this paper is available on https://github.com/Event-AHU/Medical_Image_Analysis

cs.CV↗
arXiv2026

MAC-RRG: Iterative Multi-Agent Collaboration for X-ray Radiology Report Generation

Despite the remarkable progress of LLM-based and knowledge graph-augmented Radiology Report Generation (RRG) methods, existing techniques still suffer from inherent defects. Conventional LLM-only models lack structured medical prior knowledge, resulting in frequent medical hallucinations and low diagnostic interpretability. Current knowledge graph-enhanced schemes adopt static one-round knowledge fusion with single-source knowledge, incapable of dynamic knowledge updating according to generation feedback. This paper proposes a novel Multi-Agent Collaborative iterative framework for X-ray Radiology Report Generation, termed MAC-RRG. Inspired by multi-agent technology, our framework constructs a closed-loop optimization paradigm based on task decoupling and collaborative reasoning. Specifically, the framework first generates a preliminary radiology report from input X-ray images via a vision encoder and a basic LLM. Subsequently, a multimodal knowledge graph (MM-KG) agent mines structured disease correlation and anatomical knowledge from medical knowledge graphs, while an auxiliary knowledge agent extracts unstructured domain knowledge from public medical databases. The multi-source knowledge acquired by dual agents is fused and embedded to guide the LLM in iteratively refining the initial report. Extensive quantitative and qualitative experiments on mainstream X-ray RRG datasets, including IU X-ray, MIMIC, and CheXpert Plus, fully verify the superiority of our proposed method. The source code and pre-trained models have been released on https://github.com/Event-AHU/Medical_Image_Analysis

cs.AI↗
arXiv2026

Inherit4Rec: Parameter Inheritance for Efficient Scaling of Recommendation Models

Scaling model capacity has emerged as an effective approach to overcoming performance bottlenecks in industrial recommender systems. However, repeatedly training larger dense models from scratch demands substantial data and time, while their growing computation conflicts with the strict serving budgets of industrial systems. Parameter inheritance provides a promising route for both dense model growth and sparse conversion, yet existing methods are primarily designed for static corpora and can suffer sharp performance drops under dynamically evolving recommendation data. To address these challenges, we propose Inherit4Rec, a parameter-inheritance framework that supports both Dense-to-Dense (D2D) growth and Dense-to-Sparse (D2S) conversion. Inherit4Rec-D2D combines hybrid growth with asymmetric training to preserve the forward function at expansion and maintain update continuity. Inherit4Rec-D2S constructs SMoE networks through co-activation-aware partitioning and a load-balancing loss, preserving dense-model capabilities while promoting balanced expert activation. Experiments on KuaiRand-1K and an industrial short-video recommendation dataset show that both transformations consistently outperform the evaluated inheritance baselines across all prediction objectives. These results demonstrate the effectiveness of Inherit4Rec for continual capacity expansion and computation-efficient sparse conversion in industrial recommender systems.

cs.IR↗
arXiv2026

FORTE: Task-Adaptive Force Capability Optimization for Mobile Manipulators

Effective physical interaction control in robotic manipulation requires not only kinematically feasible motion but also sufficient force-interaction capability. Existing redundancy resolution methods often ignore task-specific force demands or maximize the force capability indiscriminately, sacrificing dexterity when large force margins are unnecessary. We propose a task-oriented force capability optimization framework for redundant mobile manipulators. A Vision-Language Model (VLM) infers object physical properties from an RGB image and a task description, generating a desired task-force sequence that captures gravitational and inertial demands. We then define a task-oriented force capability metric as the signed distance between a task-force uncertainty ball and the dynamic residual force polytope (RFP), quantifying compatibility between task demands and the robot's remaining actuation capacity. This metric is incorporated, alongside manipulability, joint-limit avoidance, trajectory smoothness, and base-oscillation suppression, into a whole-body multi-objective trajectory-optimization problem. Experiments on a mobile manipulator performing lifting and single-point-holding tasks under varying payload conditions demonstrate that the proposed method provides sufficient force capability for heavy loads while preserving high manipulability for light loads. This yields a task-adaptive balance that fixed capability-maximizing baselines (RFP inscribed radius, RFP cone) and manipulability-only optimization fail to achieve. The core implementation is publicly available at https://github.com/yeying256/FORTE.

cs.RO↗
arXiv2026

Model-Based Iterative Reconstruction with View-Dependent Detector Displacements for Cone-Beam CT

Detector shifting is used in industrial cone-beam computed tomography to reduce ring artifacts, but the resulting detector motion can vary nonuniformly across projection views and produce detector positions that cannot be represented by fixed offsets. Although analytical reconstruction can accommodate this motion, approaches that use projection interpolation or rebinning may limit spatial resolution and introduce artifacts. MBIR provides an alternative by representing the acquisition geometry explicitly within the reconstruction model. Existing separable distance-driven MBIR formulations assume fixed detector geometry across projection views and therefore cannot directly represent nonuniform motion in both detector dimensions, as this motion changes the voxel-to-detector mapping. We extend the separable distance-driven MBIR model to incorporate recorded horizontal and vertical detector displacements into the distance-driven overlap computation while leaving measured projections unchanged. Forward-projection validation achieved an NRMSE of 0.0338 across 1080 views. The proposed model achieved a 3D SSIM of 0.9404 and NRMSE of 0.0406, compared with 0.5396 and 0.1740 for fixed-detector MBIR. A second industrial dataset showed reduced structured artifacts compared with FDK.

eess.IV↗
arXiv2026

Semiclassical scaling of eigenstate thermalization in single-particle chaotic systems

We study the off-diagonal matrix elements of real-space observables in time-reversal-invariant single-particle chaotic systems. By analyzing the semiclassical expression for the off-diagonal variance derived from Berry's conjecture, we show that the banded structure of the observable matrix emerges naturally. For local observables, we identify a characteristic bandwidth associated with a late-time timescale inversely proportional to the particle velocity. We further show that, for systems with steep-wall confinement, the predicted magnitude follows the entropy scaling of the eigenstate thermalization hypothesis (ETH), multiplied by an additional kinetic-energy-dependent factor that is independent of spatial dimension and is not captured by conventional many-body ETH. We illustrate these results through a case study of quantum billiards and verify the semiclassical scaling numerically in a generalized quarter-Sinai billiard. Our results elucidate the dynamical implications of Berry's conjecture and provide a comparison between single-particle eigenstate thermalization and many-body ETH.

quant-ph↗
arXiv2026

Syzygies of Polarized Abelian Surfaces: A Reider-Type Criterion

Let $(X,L)$ be a polarized complex abelian surface with $L^2=2d$. We establish a Reider-type criterion for Property $N_p$. If $d\geq7$, then $L$ satisfies Property $N_0$ if and only if there is no elliptic curve $E\subseteq X$ with $L\cdot E\leq2$, with one explicitly described exception. If $p\geq1$ and $d\geq(p+2)^2+1$, then $L$ satisfies Property $N_p$ if and only if there is no elliptic curve $E\subseteq X$ with $L\cdot E\leq p+2$. The numerical bounds on $d$ are optimal for $p=0,1$. These results improve upon earlier work of Küronya--Lozovanu, Ito, and Rojas. We also construct a polarized abelian surface whose basepoint-freeness threshold is irrational.

math.AG↗
arXiv2026

A sequential regularized piecewise affine algorithm for nonconvex nonsmooth multicomposite optimization in RNN training

This paper focuses on a class of nonconvex nonsmooth multicomposite optimization problems for training RNNs (Recurrent Neural Networks). We first establish easily verifiable conditions under which an approximate first-order d-stationary point of the problem is guaranteed to be an approximate second-order d-stationary point. Subsequently, we propose a sequential regularized piecewise affine algorithm, SRPA, that minimizes a regularized piecewise affine function at each iteration, where the idea of active-set strategy is incorporated to reduce the computational cost per iteration. Leveraging the aforementioned conditions for second-order d-stationarity, we establish the global convergence of SRPA to second-order d-stationary points and the complexity bound of $ \mathcal{O}(ε^{-2}) $ for obtaining an $ ε$-approximate second-order d-stationary point. Finally, numerical experiments for training RNNs on synthetic and real-world datasets demonstrate the promising performance of SRPA compared with state-of-the-art algorithms.

math.OC↗
arXiv2026

FLAT: Resampling Image and Text into 1D Flexible-Length Aligned Transmodal Tokens for Retrieval and Generation

Traditional multimodal representation learning and generation are two stages: a contrastive or self-supervised visual encoder is trained first, followed by a separate downstream generative model. This setup bottlenecks generative performance behind frozen embeddings. To bridge this gap, we revisit joint multimodal representation learning and generation to produce linearly interpolatable embeddings that are directly consumable by generative decoders. We present FLAT (Flexible-Length Aligned Transmodal representations), a representation pre-training framework that jointly optimizes a shared multimodal encoder alongside downstream text-to-image (T2I) and image-to-text (I2T) decoders. By combining contrastive alignment with bidirectional cross-modal generative objectives, FLAT ensures its representations function as both discriminative semantic descriptors and generative conditions. Architecturally, FLAT maps visual and textual inputs into a unified continuous 1D sequence space, applying nested dropout over prefix-K tokens to enable dynamic output lengths. A single pre-training stage allows FLAT to perform cross-modal retrieval and generation across variable prefix K, achieving a T2I GenEval score of 71.1. Task-specific fine-tuning aligns model performance with state-of-the-art baselines: 83.1 GenEval on T2I generation; 40.5 BLEU-4 and 138.6 CIDEr on MS-COCO image captioning; and Recall@5 scores of 86.8 (I2T) / 75.8 (T2I) on MS-COCO alongside 98.3 (I2T) / 93.6 (T2I) on Flickr30K. Finally, qualitative evaluations demonstrate that FLAT representations natively support linear interpolation, latent space arithmetic, and zero-shot composed retrieval.

cs.CV↗
arXiv2026

Beyond Noise: Understanding and Overcoming Temperature Effects in Analog DNN Inference

The energy efficiency of analog computing makes it one of the most promising candidates for deploying resource-intensive machine learning workloads on constrained platforms such as mobile and embedded devices. However, analog accelerators are inherently susceptible to noise and non-idealities arising from physical component variations, whose behavior is further sensitive to environmental factors. These effects can significantly degrade inference accuracy. In this work, we conduct a comprehensive experimental study on a representative example of analog hardware to investigate the impact of temperature. We first characterize the behavior of stochastic and systematic non-idealities across a range of operating temperatures. Following this, we compare a set of simulation-based and hardware-based mitigation strategies aimed at improving robustness against temperature-induced performance degradation. Our results suggest that temperature-induced degradation is driven primarily by systematic non-idealities rather than stochastic noise alone. Noise-aware training improves robustness, while hardware-in-the-loop training and temperature-aware calibration provide the strongest accuracy retention across varying thermal conditions.

cs.LG↗
arXiv2026

AIM: A Privacy-Aware Interoperable Memory Framework for Multi-Agent Multi-User LLM Systems

Traditional large language models (LLMs) are scoped to individual user sessions, limiting their knowledge to a single conversation and preventing them from learning user preferences that evolve over time. Existing agentic memory systems address this limitation but generally operate at the individual-user level, restricting the public knowledge that could be shared across users to improve downstream responses. We introduce AIM (Agentic Interoperable Memory), a unified, privacy-aware memory framework that enables multi-agent, multi-user LLM systems to persistently manage private and shared memory. AIM dynamically classifies information as private, scoped to one user and inaccessible to others, or public, accessible to all users. It enforces index-level access controls so that private memories are retrievable only by their owner, protecting sensitive data while allowing beneficial shared knowledge to improve coordination and consistency. We also introduce MUMBench (Multi-User Memory Benchmark), a dataset of multi-user interactions containing private and shareable information across four domains. To our knowledge, MUMBench is the first public dataset designed to evaluate multiple memory operations, including retrieval, creation, update, and deletion, in a multi-user environment. Across three independent runs on MUMBench, AIM achieves 96.0% visibility classification accuracy, 58.8% strict operation accuracy, and 70.5% state-aware operation accuracy.

cs.AI↗
arXiv2026

Making Every Verified Token Count: Adaptive Verification for MoE Speculative Decoding

Tree-based speculative decoding accelerates autoregressive generation by verifying multiple draft candidates in parallel, but this advantage weakens for sparse Mixture-of-Experts (MoE) models. As the draft tree grows, different branches activate different experts, expanding the union of activated experts and substantially increasing target-side verification cost. We propose EVICT, a training-free, hyperparameter-free, and lossless adaptive verification method for MoE speculative decoding. EVICT makes every verified token count by truncating the draft tree before target verification and retaining only the cost-effective prefix. It leverages fine-grained drafter signals to estimate candidate benefit, combines them with offline-profiled verification cost, and remains highly compatible with the high-performance graph-based serving framework SGLang. Extensive experiments on diverse MoE backbones and benchmarks show that EVICT achieves up to 2.35x speedup over autoregressive decoding and an average 1.21x speedup over the state-of-the-art baseline EAGLE-3, while significantly reducing unnecessary expert activations during verification.

cs.CL↗