arXiv subjects

Xiao Wang

Publications and source records attributed to Xiao Wang.

At least 289 records · Page 16Linked to original sources

arXiv2025

Continuous-Time Analysis of Heavy Ball Momentum in Min-Max Games

Since Polyak's pioneering work, heavy ball (HB) momentum has been widely studied in minimization. However, its role in min-max games remains largely unexplored. As a key component of practical min-max algorithms like Adam, this gap limits their effectiveness. In this paper, we present a continuous-time analysis for HB with simultaneous and alternating update schemes in min-max games. Locally, we prove smaller momentum enhances algorithmic stability by enabling local convergence across a wider range of step sizes, with alternating updates generally converging faster. Globally, we study the implicit regularization of HB, and find smaller momentum guides algorithms trajectories towards shallower slope regions of the loss landscapes, with alternating updates amplifying this effect. Surprisingly, all these phenomena differ from those observed in minimization, where larger momentum yields similar effects. Our results reveal fundamental differences between HB in min-max games and minimization, and numerical experiments further validate our theoretical results.

cs.GT↗

arXiv2025

Describe Anything in Medical Images

Localized image captioning has made significant progress with models like the Describe Anything Model (DAM), which can generate detailed region-specific descriptions without explicit region-text supervision. However, such capabilities have yet to be widely applied to specialized domains like medical imaging, where diagnostic interpretation relies on subtle regional findings rather than global understanding. To mitigate this gap, we propose MedDAM, the first comprehensive framework leveraging large vision-language models for region-specific captioning in medical images. MedDAM employs medical expert-designed prompts tailored to specific imaging modalities and establishes a robust evaluation benchmark comprising a customized assessment protocol, data pre-processing pipeline, and specialized QA template library. This benchmark evaluates both MedDAM and other adaptable large vision-language models, focusing on clinical factuality through attribute-level verification tasks, thereby circumventing the absence of ground-truth region-caption pairs in medical datasets. Extensive experiments on the VinDr-CXR, LIDC-IDRI, and SkinCon datasets demonstrate MedDAM's superiority over leading peers (including GPT-4o, Claude 3.7 Sonnet, LLaMA-3.2 Vision, Qwen2.5-VL, GPT-4Rol, and OMG-LLaVA) in the task, revealing the importance of region-level semantic alignment in medical image understanding and establishing MedDAM as a promising foundation for clinical vision-language integration.

cs.CV↗

arXiv2025

DocFusion: A Unified Framework for Document Parsing Tasks

Document parsing is essential for analyzing complex document structures and extracting fine-grained information, supporting numerous downstream applications. However, existing methods often require integrating multiple independent models to handle various parsing tasks, leading to high complexity and maintenance overhead. To address this, we propose DocFusion, a lightweight generative model with only 0.28B parameters. It unifies task representations and achieves collaborative training through an improved objective function. Experiments reveal and leverage the mutually beneficial interaction among recognition tasks, and integrating recognition data significantly enhances detection performance. The final results demonstrate that DocFusion achieves state-of-the-art (SOTA) performance across four key tasks.

cs.CL↗

arXiv2025

Paradigm Shift in Infrastructure Inspection Technology: Leveraging High-performance Imaging and Advanced AI Analytics to Inspect Road Infrastructure

Effective road infrastructure management is crucial for modern society. Traditional manual inspection techniques remain constrained by cost, efficiency, and scalability, while camera and laser imaging methods fail to capture subsurface defects critical for long-term structural integrity. This paper introduces ROVAI, an end-to-end framework that integrates high-resolution X-ray computed tomography imaging and advanced AI-driven analytics, aiming to transform road infrastructure inspection technologies. By leveraging the computational power of world-leading supercomputers, Fugaku and Frontier, and SoTA synchrotron facility (Spring-8), ROVAI enables scalable and high-throughput processing of massive 3D tomographic datasets. Our approach overcomes key challenges, such as the high memory requirements of vision models, the lack of labeled training data, and storage I/O bottlenecks. This seamless integration of imaging and AI analytics facilitates automated defect detection, material composition analysis, and lifespan prediction. Experimental results demonstrate the effectiveness of ROVAI in real-world scenarios, setting a new standard for intelligent, data-driven infrastructure management.

cs.DC↗

arXiv2025

Towards Low-Latency Event Stream-based Visual Object Tracking: A Slow-Fast Approach

Existing tracking algorithms typically rely on low-frame-rate RGB cameras coupled with computationally intensive deep neural network architectures to achieve effective tracking. However, such frame-based methods inherently face challenges in achieving low-latency performance and often fail in resource-constrained environments. Visual object tracking using bio-inspired event cameras has emerged as a promising research direction in recent years, offering distinct advantages for low-latency applications. In this paper, we propose a novel Slow-Fast Tracking paradigm that flexibly adapts to different operational requirements, termed SFTrack. The proposed framework supports two complementary modes, i.e., a high-precision slow tracker for scenarios with sufficient computational resources, and an efficient fast tracker tailored for latency-aware, resource-constrained environments. Specifically, our framework first performs graph-based representation learning from high-temporal-resolution event streams, and then integrates the learned graph-structured information into two FlashAttention-based vision backbones, yielding the slow and fast trackers, respectively. The fast tracker achieves low latency through a lightweight network design and by producing multiple bounding box outputs in a single forward pass. Finally, we seamlessly combine both trackers via supervised fine-tuning and further enhance the fast tracker's performance through a knowledge distillation strategy. Extensive experiments on public benchmarks, including FE240, COESOT, and EventVOT, demonstrate the effectiveness and efficiency of our proposed method across different real-world scenarios. The source code has been released on https://github.com/Event-AHU/SlowFast_Event_Track.

cs.CV↗

arXiv2025

Dynamic Graph Induced Contour-aware Heat Conduction Network for Event-based Object Detection

Event-based Vision Sensors (EVS) have demonstrated significant advantages over traditional RGB frame-based cameras in low-light conditions, high-speed motion capture, and low latency. Consequently, object detection based on EVS has attracted increasing attention from researchers. Current event stream object detection algorithms are typically built upon Convolutional Neural Networks (CNNs) or Transformers, which either capture limited local features using convolutional filters or incur high computational costs due to the utilization of self-attention. Recently proposed vision heat conduction backbone networks have shown a good balance between efficiency and accuracy; however, these models are not specifically designed for event stream data. They exhibit weak capability in modeling object contour information and fail to exploit the benefits of multi-scale features. To address these issues, this paper proposes a novel dynamic graph induced contour-aware heat conduction network for event stream based object detection, termed CvHeat-DET. The proposed model effectively leverages the clear contour information inherent in event streams to predict the thermal diffusivity coefficients within the heat conduction model, and integrates hierarchical structural graph features to enhance feature learning across multiple scales. Extensive experiments on three benchmark datasets for event stream-based object detection fully validated the effectiveness of the proposed model. The source code of this paper will be released on https://github.com/Event-AHU/OpenEvDET.

cs.CV↗

arXiv2025

Spatiotemporal plasma hologram

We present the first experimental realization of a four-dimensional (4D) plasma hologram capable of recording and reconstructing the full spatiotemporal information of intense laser pulses. The holographic encoding is achieved through the interference of a long object pulse and a counter-propagating short reference pulse, generating an ionized plasma grating that captures both spatial and temporal characteristics of the laser field. A first-order diffractive probe enables the retrieval of encoded information, successfully reconstructing the spatiotemporal profiles of Gaussian and Laguerre-Gaussian beams. The experiment demonstrates the ability to encode artificial information into the laser pulse via spectral modulation and retrieve it through plasma grating diffraction, high-lighting potential applications in ultraintense optical data processing. Key innovations include a single-shot, background-free method for direct far-field spatiotemporal measurement and the obser-vation of laser focus propagation dynamics in plasma. The plasma grating exhibits a stable lifetime of 30-40 ps and supports high repetition rates, suggesting usage for high-speed optical switches and plasmatic analog memory. These advancements establish plasma holography as a robust platform for ultrafast laser manipulation, with implications for secure optical communication, analog computing,and precision spatiotemporal control of high-intensity lasers.

physics.plasm-ph↗

arXiv2025

Adaptive Tokenization: On the Hop-Overpriority Problem in Tokenized Graph Learning Models

Graph Transformers, leveraging the global attention to capture long-range dependencies in graph structures, have significantly advanced graph machine learning, but face prohibitive computational complexity. Tokenized Graph Learning Models (TGLMs) address this issue by converting graphs into ordered token lists for scalable processing. Besides, TGLMs also empower Large Language Models (LLMs) to handle text-attributed graphs more effectively and thus are also employed in Graph LLMs. However, existing TGLMs rely on hand-designed token lists and their adaptability to diverse graph learning scenarios remains unexplored. In this paper, we first conduct extensive empirical and theoretical preliminary studies for hand-designed token lists. Surprisingly, we identify an unexplored hop-overpriority problem: the common pre-defined token lists overemphasize nearby nodes and overwhelm the ability of TGLMs to balance local and global signals. This phenomenon is especially harmful for heterophilic graphs. To address this problem, we propose the Learnable Graph Token List (LGTL), a plug-and-play module to replace hand-designed token lists in TGLMs. Specifically, LGTL adaptively adjusts the weights across hops and prioritizes informative nodes within hops through a graph attention gate module and a selection module, respectively. In this way, contextually informative nodes can be adaptively emphasized for both homophilic and heterophilic graphs. Besides, we theoretically show that LGTL can address the hop-overpriority problem. Extensive experiments on benchmarks validate the efficacy of LGTL across both Graph Transformers and Graph LLM backbones.

cs.LG↗

arXiv2025

Lightweight Spatio-Temporal Attention Network with Graph Embedding and Rotational Position Encoding for Traffic Forecasting

Traffic forecasting is a key task in the field of Intelligent Transportation Systems. Recent research on traffic forecasting has mainly focused on combining graph neural networks (GNNs) with other models. However, GNNs only consider short-range spatial information. In this study, we present a novel model termed LSTAN-GERPE (Lightweight Spatio-Temporal Attention Network with Graph Embedding and Rotational Position Encoding). This model leverages both Temporal and Spatial Attention mechanisms to effectively capture long-range traffic dynamics. Additionally, the optimal frequency for rotational position encoding is determined through a grid search approach in both the spatial and temporal attention mechanisms. This systematic optimization enables the model to effectively capture complex traffic patterns. The model also enhances feature representation by incorporating geographical location maps into the spatio-temporal embeddings. Without extensive feature engineering, the proposed method in this paper achieves advanced accuracy on the real-world traffic forecasting datasets PeMS04 and PeMS08.

cs.AI↗

arXiv2025

TGBFormer: Transformer-GraphFormer Blender Network for Video Object Detection

Video object detection has made significant progress in recent years thanks to convolutional neural networks (CNNs) and vision transformers (ViTs). Typically, CNNs excel at capturing local features but struggle to model global representations. Conversely, ViTs are adept at capturing long-range global features but face challenges in representing local feature details. Off-the-shelf video object detection methods solely rely on CNNs or ViTs to conduct feature aggregation, which hampers their capability to simultaneously leverage global and local information, thereby resulting in limited detection performance. In this paper, we propose a Transformer-GraphFormer Blender Network (TGBFormer) for video object detection, with three key technical improvements to fully exploit the advantages of transformers and graph convolutional networks while compensating for their limitations. First, we develop a spatial-temporal transformer module to aggregate global contextual information, constituting global representations with long-range feature dependencies. Second, we introduce a spatial-temporal GraphFormer module that utilizes local spatial and temporal relationships to aggregate features, generating new local representations that are complementary to the transformer outputs. Third, we design a global-local feature blender module to adaptively couple transformer-based global representations and GraphFormer-based local representations. Extensive experiments demonstrate that our TGBFormer establishes new state-of-the-art results on the ImageNet VID dataset. Particularly, our TGBFormer achieves 86.5% mAP while running at around 41.0 FPS on a single Tesla A100 GPU.

cs.CV↗

arXiv2025

Kauffman bracket skein module of two families of Seifert manifolds

We compute the Kauffman bracket skein modules of Seifert manifolds $Σ_{0,1}((k_1,1),(k_2,1))$ and $Σ_{0,0}((k_1,1),(k_2,1),(k_3,1))$ by providing presentations of them. From the obtained presentations, we show that the Kauffman bracket skein modules of $Σ_{0,1}((k_1,1),(k_2,1))$ are free with infinitely many generators when $k_1,k_2\ge 1$ and that of $Σ_{0,0}((k_1,1),(k_2,1),(k_3,1))$ are finitely generated when $k_1,k_2,k_3 \ge 2$. We also show that the empty link in either case is not trivial.

math.GT↗

arXiv2025

Homology of Yang-Baxter modules

We study the Yang-Baxter operator for the vector representation $V_m$ of the quantum group $U_q(sl_m)$. We consider the one-term Yang-Baxter homology with coefficients in $V_m$-modules and provide a direct sum decomposition of the one term Yang-Baxter chain complex. The homology is explicitly computed for some specific $V_m$-modules.

math.QA↗

arXiv2025

SSTFormer: Bridging Spiking Neural Network and Memory Support Transformer for Frame-Event based Recognition

Event camera-based pattern recognition is a newly arising research topic in recent years. Current researchers usually transform the event streams into images, graphs, or voxels, and adopt deep neural networks for event-based classification. Although good performance can be achieved on simple event recognition datasets, however, their results may be still limited due to the following two issues. Firstly, they adopt spatial sparse event streams for recognition only, which may fail to capture the color and detailed texture information well. Secondly, they adopt either Spiking Neural Networks (SNN) for energy-efficient recognition with suboptimal results, or Artificial Neural Networks (ANN) for energy-intensive, high-performance recognition. However, seldom of them consider achieving a balance between these two aspects. In this paper, we formally propose to recognize patterns by fusing RGB frames and event streams simultaneously and propose a new RGB frame-event recognition framework to address the aforementioned issues. The proposed method contains four main modules, i.e., memory support Transformer network for RGB frame encoding, spiking neural network for raw event stream encoding, multi-modal bottleneck fusion module for RGB-Event feature aggregation, and prediction head. Due to the scarce of RGB-Event based classification dataset, we also propose a large-scale PokerEvent dataset which contains 114 classes, and 27102 frame-event pairs recorded using a DVS346 event camera. Extensive experiments on two RGB-Event based classification datasets fully validated the effectiveness of our proposed framework. We hope this work will boost the development of pattern recognition by fusing RGB frames and event streams. Both our dataset and source code of this work will be released at https://github.com/Event-AHU/SSTFormer

cs.CV↗

arXiv2025

Residual-based Alternative Partial Least Squares for Generalized Functional Linear Models

Many biomedical studies collect high-dimensional medical imaging data to identify biomarkers for the detection, diagnosis, and treatment of human diseases. Consequently, it is crucial to develop accurate models that can predict a wide range of clinical outcomes (both discrete and continuous) based on imaging data. By treating imaging predictors as functional data, we propose a residual-based alternative partial least squares (RAPLS) model for a broad class of generalized functional linear models that incorporate both functional and scalar covariates. Our RAPLS method extends the alternative partial least squares (APLS) algorithm iteratively to accommodate additional scalar covariates and non-continuous outcomes. We establish the convergence rate of the RAPLS estimator for the unknown slope function and, with an additional calibration step, we prove the asymptotic normality and efficiency of the calibrated RAPLS estimator for the scalar parameters. The effectiveness of the RAPLS algorithm is demonstrated through multiple simulation studies and an application predicting Alzheimer's disease progression using neuroimaging data from the Alzheimer's Disease Neuroimaging Initiative (ADNI).

stat.ME↗

arXiv2025

The 2D Materials Roadmap

Over the past two decades, 2D materials have rapidly evolved into a diverse and expanding family of material platforms. Many members of this materials class have demonstrated their potential to deliver transformative impact on fundamental research and technological applications across different fields. In this roadmap, we provide an overview of the key aspects of 2D material research and development, spanning synthesis, properties and commercial applications. We specifically present roadmaps for high impact 2D materials, including graphene and its derivatives, transition metal dichalcogenides, MXenes as well as their heterostructures and moiré systems. The discussions are organized into thematic sections covering emerging research areas (e.g., twisted electronics, moiré nano-optoelectronics, polaritronics, quantum photonics, and neuromorphic computing), breakthrough applications in key technologies (e.g., 2D transistors, energy storage, electrocatalysis, filtration and separation, thermal management, flexible electronics, sensing, electromagnetic interference shielding, and composites) and other important topics (computational discovery of novel materials, commercialization and standardization). This roadmap focuses on the current research landscape, future challenges and scientific and technological advances required to address, with the intent to provide useful references for promoting the development of 2D materials.

cond-mat.mtrl-sci↗

arXiv2025

Predicting Methane Adsorption in Metal-Substituted MOFs: A Comparative Study between Density Functional Theory and Machine Learning

Metal-organic frameworks (MOFs) are promising materials for methane capture due to their high surface area and tunable properties. Metal substitution represents a powerful strategy to enhance MOF performance, yet systematic exploration of the vast chemical space remains challenging. In this work, we compare density functional theory (DFT) and machine learning (ML) in predicting methane adsorption properties in metal-substituted variants of three high-performing MOFs: M-HKUST-1, M-ATC, and M-ZIF-8 (M = Cu, Zn). DFT calculations reveal significant differences in methane binding energies between Cu and Zn variants of all three MOFs. On the other hand, we fine-tuned a pretrained multimodal ML model, PMTransformer, on a curated subset of hypothetical MOF (hMOF) structures to predict macroscopic adsorption properties. While the fine-tuned heat of adsorption model and uptake model qualitatively predict adsorption properties for original unaltered MOFs, they fail to distinguish between metal variants despite their different binding energetics identified by DFT. We trace this limitation to the hMOF training data generated using Grand Canonical Monte Carlo (GCMC) simulations based on classical force fields (UFF/TraPPE). Our study highlights a key challenge in ML-based MOF screening: ML models inherit the limitations of their training data, particularly when electronic effects at open metal sites significantly impact adsorption behaviors. Our findings emphasize the need for improved force fields or hybrid GCMC/DFT datasets to incorporate both geometric and electronic factors for accurate prediction of adsorption properties in metal-substituted MOFs.

cond-mat.mtrl-sci↗

arXiv2025

4D Multimodal Co-attention Fusion Network with Latent Contrastive Alignment for Alzheimer's Diagnosis

Multimodal neuroimaging provides complementary structural and functional insights into both human brain organization and disease-related dynamics. Recent studies demonstrate enhanced diagnostic sensitivity for Alzheimer's disease (AD) through synergistic integration of neuroimaging data (e.g., sMRI, fMRI) with behavioral cognitive scores tabular data biomarkers. However, the intrinsic heterogeneity across modalities (e.g., 4D spatiotemporal fMRI dynamics vs. 3D anatomical sMRI structure) presents critical challenges for discriminative feature fusion. To bridge this gap, we propose M2M-AlignNet: a geometry-aware multimodal co-attention network with latent alignment for early AD diagnosis using sMRI and fMRI. At the core of our approach is a multi-patch-to-multi-patch (M2M) contrastive loss function that quantifies and reduces representational discrepancies via geometry-weighted patch correspondence, explicitly aligning fMRI components across brain regions with their sMRI structural substrates without one-to-one constraints. Additionally, we propose a latent-as-query co-attention module to autonomously discover fusion patterns, circumventing modality prioritization biases while minimizing feature redundancy. We conduct extensive experiments to confirm the effectiveness of our method and highlight the correspondance between fMRI and sMRI as AD biomarkers.

cs.MM↗

arXiv2025

Beyond Boundaries: Learning a Universal Entity Taxonomy across Datasets and Languages for Open Named Entity Recognition

Open Named Entity Recognition (NER), which involves identifying arbitrary types of entities from arbitrary domains, remains challenging for Large Language Models (LLMs). Recent studies suggest that fine-tuning LLMs on extensive NER data can boost their performance. However, training directly on existing datasets neglects their inconsistent entity definitions and redundant data, limiting LLMs to dataset-specific learning and hindering out-of-domain adaptation. To address this, we present B2NERD, a compact dataset designed to guide LLMs' generalization in Open NER under a universal entity taxonomy. B2NERD is refined from 54 existing English and Chinese datasets using a two-step process. First, we detect inconsistent entity definitions across datasets and clarify them by distinguishable label names to construct a universal taxonomy of 400+ entity types. Second, we address redundancy using a data pruning strategy that selects fewer samples with greater category and semantic diversity. Comprehensive evaluation shows that B2NERD significantly enhances LLMs' Open NER capabilities. Our B2NER models, trained on B2NERD, outperform GPT-4 by 6.8-12.0 F1 points and surpass previous methods in 3 out-of-domain benchmarks across 15 datasets and 6 languages. The data, models, and code are publicly available at https://github.com/UmeanNever/B2NER.

cs.CL↗