arXiv subjects

Xudong Yang

Publications and source records attributed to Xudong Yang.

At least 19 recordsLinked to original sources

arXiv2026

LingDT-VL-OCR: Structure-Aware Document-Level Parsing with Fine-Grained Visual Reference

In this paper, we propose LingDT-VL-OCR, a document parsing system tailored to financial-domain documents, transforming ultra-long financial PDFs into semantically consistent, highly accurate, structured outputs with auditing-grade provenance. To address finance-specific challenges such as complex layouts, cross-page structural discontinuities, and cell-level referencing capability, LingDT-VL-OCR combines (1) a Cross-page Contents Consolidation algorithm to restore continuity across pages and a Document-level Heading Hierarchy Reconstruction (DHR) module to build a globally consistent Table of Contents (TOC) tree for structure-aware retrieval, and (2) a difficulty-adaptive curriculum learning training strategy for table parsing, together with a CellBBoxRegressor module that uses structural anchor tokens to localize table cells from decoder hidden states without external detectors. Experiments demonstrate that our model shows high performance on the Overall metric of OmniDocBench. To enable realistic evaluation in the financial vertical, we further introduce FinDocBench, a benchmark that includes six financial document categories with expert-verified annotations and evaluation metrics including Table of Contents edit-distance-based similarity (TocEDS), cross-page concatenated TEDS, and Table Cell Intersection over Union (C-IoU). We evaluate a wide range of state-of-the-art models on FinDocBench to assess their capabilities and remaining limitations on financial documents. Overall, LingDT-VL-OCR and FinDocBench provide a practical foundation for reliable downstream financial document applications.

cs.CV↗

arXiv2026

Tracing Copied Pixels and Regularizing Patch Affinity in Copy Detection

Image Copy Detection (ICD) aims to identify manipulated content between image pairs through robust feature representation learning. While self-supervised learning (SSL) has advanced ICD systems, existing view-level contrastive methods struggle with sophisticated edits due to insufficient fine-grained correspondence learning. We address this limitation by exploiting the inherent geometric traceability in edited content through two key innovations. First, we propose PixTrace - a pixel coordinate tracking module that maintains explicit spatial mappings across editing transformations. Second, we introduce CopyNCE, a geometrically-guided contrastive loss that regularizes patch affinity using overlap ratios derived from PixTrace's verified mappings. Our method bridges pixel-level traceability with patch-level similarity learning, suppressing supervision noise in SSL training. Extensive experiments demonstrate not only state-of-the-art performance (88.7% uAP / 83.9% RP90 for matcher, 72.6% uAP / 68.4% RP90 for descriptor on DISC21 dataset) but also better interpretability over existing methods.

cs.CV↗

arXiv2026

Compression Tells Intelligence: Visual Coding, Visual Token Technology, and the Unification

"Compression Tells Intelligence", is supported by research in artificial intelligence, particularly concerning (multimodal) large language models (LLMs/MLLMs), where compression efficiency often correlates with improved model performance and capabilities. For compression, classical visual coding based on traditional information theory has developed over decades, achieving great success with numerous international industrial standards widely applied in multimedia (e.g., image/video) systems. Except that, the recent emergingvisual token technology of generative multi-modal large models also shares a similar fundamental objective like visual coding: maximizing semantic information fidelity during the representation learning while minimizing computational cost. Therefore, this paper provides a comprehensive overview of two dominant technique families first -- Visual Coding and Vision Token Technology -- then we further unify them from the aspect of optimization, discussing the essence of compression efficiency and model performance trade-off behind. Next, based on the proposed unified formulation bridging visual coding andvisual token technology, we synthesize bidirectional insights of themselves and forecast the next-gen visual codec and token techniques. Last but not least, we experimentally show a large potential of the task-oriented token developments in the more practical tasks like multimodal LLMs (MLLMs), AI-generated content (AIGC), and embodied AI, as well as shedding light on the future possibility of standardizing a general token technology like the traditional codecs (e.g., H.264/265) with high efficiency for a wide range of intelligent tasks in a unified and effective manner.

cs.CV↗

arXiv2026

Federated Balanced Learning

Federated learning is a paradigm of joint learning in which clients collaborate by sharing model parameters instead of data. However, in the non-iid setting, the global model experiences client drift, which can seriously affect the final performance of the model. Previous methods tend to correct the global model that has already deviated based on the loss function or gradient, overlooking the impact of the client samples. In this paper, we rethink the role of the client side and propose Federated Balanced Learning, i.e., FBL, to prevent this issue from the beginning through sample balance on the client side. Technically, FBL allows unbalanced data on the client side to achieve sample balance through knowledge filling and knowledge sampling using edge-side generation models, under the limitation of a fixed number of data samples on clients. Furthermore, we design a Knowledge Alignment Strategy to bridge the gap between synthetic and real data, and a Knowledge Drop Strategy to regularize our method. Meanwhile, we scale our method to real and complex scenarios, allowing different clients to adopt various methods, and extend our framework to further improve performance. Numerous experiments show that our method outperforms state-of-the-art baselines. The code is released upon acceptance.

cs.CV↗

arXiv2025

KAPG: Adaptive Password Guessing via Knowledge-Augmented Generation

As the primary mechanism of digital authentication, user-created passwords exhibit common patterns and regularities that can be learned from leaked datasets. Password choices are profoundly shaped by external factors, including social contexts, cultural trends, and popular vocabulary. Prevailing password guessing models primarily emphasize patterns derived from leaked passwords, while neglecting these external influences -- a limitation that hampers their adaptability to emerging password trends and erodes their effectiveness over time. To address these challenges, we propose KAPG, a knowledge-augmented password guessing framework that adaptively integrates external lexical knowledge into the guessing process. KAPG couples internal statistical knowledge learned from leaked passwords with external information that reflects real-world trends. By using password prefixes as anchors for knowledge lookup, it dynamically injects relevant external cues during generation while preserving the structural regularities of authentic passwords. Experiments on twelve leaked datasets show that KnowGuess achieves average improvements of 36.5\% and 74.7\% over state-of-the-art models in intra-site and cross-site scenarios, respectively. Further analyses of password overlap and model efficiency highlight its robustness and computational efficiency. To counter these attacks, we further develop KAPSM, a trend-aware and site-specific password strength meter. Experiments demonstrate that KAPSM significantly outperforms existing tools in accuracy across diverse evaluation settings.

cs.CR↗

arXiv2025

Revisiting MLLM Token Technology through the Lens of Classical Visual Coding

Classical visual coding and Multimodal Large Language Model (MLLM) token technology share the core objective - maximizing information fidelity while minimizing computational cost. Therefore, this paper reexamines MLLM token technology, including tokenization, token compression, and token reasoning, through the established principles of long-developed visual coding area. From this perspective, we (1) establish a unified formulation bridging token technology and visual coding, enabling a systematic, module-by-module comparative analysis; (2) synthesize bidirectional insights, exploring how visual coding principles can enhance MLLM token techniques' efficiency and robustness, and conversely, how token technology paradigms can inform the design of next-generation semantic visual codecs; (3) prospect for promising future research directions and critical unsolved challenges. In summary, this study presents the first comprehensive and structured technology comparison of MLLM token and visual coding, paving the way for more efficient multimodal models and more powerful visual codecs simultaneously.

cs.CV↗

arXiv2025

Design of meta-surface lens integrated with pupil filter

Metasurface lenses are miniature flat lenses that can precisely control the phase, amplitude, and polarization of incident light by modulating the parameters of each unit on the substrate. Compared with conventional optical lenses, they have the advantages of small size, light weight, and high integration, and are the core components of photonic chips. Currently, the hot topics for metasurface lens are broadband and achromatic devices, and there is still less attention paid to the resolution improvement. To break through the diffraction limit and further improve the focusing performance and imaging resolution of metasurface lenses, we use unit cells to perform multi-dimensional modulation of the incident light field. Specifically, in this paper, we combine phase modulation of metasurface lens with a pupil filtering, which has been widely applied to traditional microscopy imaging and adaptive optics and has demonstrated powerful resolution enhancement effects. The integrating of these two technologies will continue to improve the imaging performance of metasurface lenses and thus expanding their application fields. This result preliminarily demonstrates the super-resolution performance of the integrated meta-surface lens. With the comprehensive regulation of multi-dimensional information, such as amplitude, polarization, and vortex, the integrated meta-surface optical lens will achieve more excellent super-resolution focusing and imaging performance, and will also be widely used in the fields of super-resolution imaging, virtual reality, and three-dimensional optical display, due to its characteristics of high resolution, high integration, and high miniaturization.

physics.optics↗

arXiv2025

RAMer: Reconstruction-based Adversarial Model for Multi-party Multi-modal Multi-label Emotion Recognition

Conventional Multi-modal multi-label emotion recognition (MMER) assumes complete access to visual, textual, and acoustic modalities. However, real-world multi-party settings often violate this assumption, as non-speakers frequently lack acoustic and textual inputs, leading to a significant degradation in model performance. Existing approaches also tend to unify heterogeneous modalities into a single representation, overlooking each modality's unique characteristics. To address these challenges, we propose RAMer (Reconstruction-based Adversarial Model for Emotion Recognition), which refines multi-modal representations by not only exploring modality commonality and specificity but crucially by leveraging reconstructed features, enhanced by contrastive learning, to overcome data incompleteness and enrich feature quality. RAMer also introduces a personality auxiliary task to complement missing modalities using modality-level attention, improving emotion reasoning. To further strengthen the model's ability to capture label and modality interdependency, we propose a stack shuffle strategy to enrich correlations between labels and modality-specific features. Experiments on three benchmarks, i.e., MEmoR, CMU-MOSEI, and $M^3ED$, demonstrate that RAMer achieves state-of-the-art performance in dyadic and multi-party MMER scenarios.

cs.CV↗

arXiv2025

Behavior Modeling Space Reconstruction for E-Commerce Search

Delivering superior search services is crucial for enhancing customer experience and driving revenue growth. Conventionally, search systems model user behaviors by combining user preference and query item relevance statically, often through a fixed logical 'and' relationship. This paper reexamines existing approaches through a unified lens using both causal graphs and Venn diagrams, uncovering two prevalent yet significant issues: entangled preference and relevance effects, and a collapsed modeling space. To surmount these challenges, our research introduces a novel framework, DRP, which enhances search accuracy through two components to reconstruct the behavior modeling space. Specifically, we implement preference editing to proactively remove the relevance effect from preference predictions, yielding untainted user preferences. Additionally, we employ adaptive fusion, which dynamically adjusts fusion criteria to align with the varying patterns of relevance and preference, facilitating more nuanced and tailored behavior predictions within the reconstructed modeling space. Empirical validation on two public datasets and a proprietary search dataset underscores the superiority of our proposed methodology, demonstrating marked improvements in performance over existing approaches.

cs.IR↗

arXiv2024

AskChart: Universal Chart Understanding through Textual Enhancement

Chart understanding tasks such as ChartQA and Chart-to-Text involve automatically extracting and interpreting key information from charts, enabling users to query or convert visual data into structured formats. State-of-the-art approaches primarily focus on visual cues from chart images, failing to explicitly incorporate rich textual information (e.g., data labels and axis labels) embedded within the charts. This textual information is vital for intuitive human comprehension and interpretation of charts. Moreover, existing models are often large and computationally intensive, limiting their practical applicability. In this paper, we introduce AskChart, a universal model that explicitly integrates both textual and visual cues from charts using a Mixture of Experts (MoE) architecture. AskChart facilitates the learning of enhanced visual-textual representations of charts for effectively handling multiple chart understanding tasks, while maintaining a smaller model size. To capture the synergy between visual and textual modalities, we curate a large-scale dataset named ChartBank with about 7.5M data samples, which helps align textual and visual information and facilitates the extraction of visual entities and text. To effectively train AskChart, we design a three-stage training strategy to align visual and textual modalities for learning robust visual-textual representations and optimizing the learning of the MoE layer. Extensive experiments across five datasets demonstrate the significant performance gains of AskChart in four chart understanding tasks. Remarkably, AskChart with 4.6B parameters outperforms state-of-the-art models with 13B parameters by 68.3% in Open-ended ChartQA and 49.2% in Chart-to-Text tasks, while achieving comparable performance in ChartQA and Chart-to-Table tasks.

cs.CV↗

arXiv2023

Learning Segment Similarity and Alignment in Large-Scale Content Based Video Retrieval

With the explosive growth of web videos in recent years, large-scale Content-Based Video Retrieval (CBVR) becomes increasingly essential in video filtering, recommendation, and copyright protection. Segment-level CBVR (S-CBVR) locates the start and end time of similar segments in finer granularity, which is beneficial for user browsing efficiency and infringement detection especially in long video scenarios. The challenge of S-CBVR task is how to achieve high temporal alignment accuracy with efficient computation and low storage consumption. In this paper, we propose a Segment Similarity and Alignment Network (SSAN) in dealing with the challenge which is firstly trained end-to-end in S-CBVR. SSAN is based on two newly proposed modules in video retrieval: (1) An efficient Self-supervised Keyframe Extraction (SKE) module to reduce redundant frame features, (2) A robust Similarity Pattern Detection (SPD) module for temporal alignment. In comparison with uniform frame extraction, SKE not only saves feature storage and search time, but also introduces comparable accuracy and limited extra computation time. In terms of temporal alignment, SPD localizes similar segments with higher accuracy and efficiency than existing deep learning methods. Furthermore, we jointly train SSAN with SKE and SPD and achieve an end-to-end improvement. Meanwhile, the two key modules SKE and SPD can also be effectively inserted into other video retrieval pipelines and gain considerable performance improvements. Experimental results on public datasets show that SSAN can obtain higher alignment accuracy while saving storage and online query computational cost compared to existing methods.

cs.CV↗

arXiv2023

Boundary-aware Backward-Compatible Representation via Adversarial Learning in Image Retrieval

Image retrieval plays an important role in the Internet world. Usually, the core parts of mainstream visual retrieval systems include an online service of the embedding model and a large-scale vector database. For traditional model upgrades, the old model will not be replaced by the new one until the embeddings of all the images in the database are re-computed by the new model, which takes days or weeks for a large amount of data. Recently, backward-compatible training (BCT) enables the new model to be immediately deployed online by making the new embeddings directly comparable to the old ones. For BCT, improving the compatibility of two models with less negative impact on retrieval performance is the key challenge. In this paper, we introduce AdvBCT, an Adversarial Backward-Compatible Training method with an elastic boundary constraint that takes both compatibility and discrimination into consideration. We first employ adversarial learning to minimize the distribution disparity between embeddings of the new model and the old model. Meanwhile, we add an elastic boundary constraint during training to improve compatibility and discrimination efficiently. Extensive experiments on GLDv2, Revisited Oxford (ROxford), and Revisited Paris (RParis) demonstrate that our method outperforms other BCT methods on both compatibility and discrimination. The implementation of AdvBCT will be publicly available at https://github.com/Ashespt/AdvBCT.

cs.CV↗

arXiv2022

TransVCL: Attention-enhanced Video Copy Localization Network with Flexible Supervision

Video copy localization aims to precisely localize all the copied segments within a pair of untrimmed videos in video retrieval applications. Previous methods typically start from frame-to-frame similarity matrix generated by cosine similarity between frame-level features of the input video pair, and then detect and refine the boundaries of copied segments on similarity matrix under temporal constraints. In this paper, we propose TransVCL: an attention-enhanced video copy localization network, which is optimized directly from initial frame-level features and trained end-to-end with three main components: a customized Transformer for feature enhancement, a correlation and softmax layer for similarity matrix generation, and a temporal alignment module for copied segments localization. In contrast to previous methods demanding the handcrafted similarity matrix, TransVCL incorporates long-range temporal information between feature sequence pair using self- and cross- attention layers. With the joint design and optimization of three components, the similarity matrix can be learned to present more discriminative copied patterns, leading to significant improvements over previous methods on segment-level labeled datasets (VCSL and VCDB). Besides the state-of-the-art performance in fully supervised setting, the attention architecture facilitates TransVCL to further exploit unlabeled or simply video-level labeled data. Additional experiments of supplementing video-level labeled datasets including SVD and FIVR reveal the high flexibility of TransVCL from full supervision to semi-supervision (with or without video-level annotation). Code is publicly available at https://github.com/transvcl/TransVCL.

cs.CV↗

arXiv2022

A Large-scale Comprehensive Dataset and Copy-overlap Aware Evaluation Protocol for Segment-level Video Copy Detection

In this paper, we introduce VCSL (Video Copy Segment Localization), a new comprehensive segment-level annotated video copy dataset. Compared with existing copy detection datasets restricted by either video-level annotation or small-scale, VCSL not only has two orders of magnitude more segment-level labelled data, with 160k realistic video copy pairs containing more than 280k localized copied segment pairs, but also covers a variety of video categories and a wide range of video duration. All the copied segments inside each collected video pair are manually extracted and accompanied by precisely annotated starting and ending timestamps. Alongside the dataset, we also propose a novel evaluation protocol that better measures the prediction accuracy of copy overlapping segments between a video pair and shows improved adaptability in different scenarios. By benchmarking several baseline and state-of-the-art segment-level video copy detection methods with the proposed dataset and evaluation metric, we provide a comprehensive analysis that uncovers the strengths and weaknesses of current approaches, hoping to open up promising directions for future works. The VCSL dataset, metric and benchmark codes are all publicly available at https://github.com/alipay/VCSL.

cs.CV↗

arXiv2014

Selective molecular capture mechanism in carbon nanotube networks

Recent air pollution issues have raised significant attention to develop efficient air filters, and one of the most promising candidates is that enabled by nanofibers. We explore here selective molecular capture mechanism for volatile organic compounds in carbon nanotube networks by performing atomistic simulations. The results are discussed with respect to the two key parameters that define the performance of nanofiltration, i.e. the capture efficiency and flow resistance, which validate the advantage of carbon nanotube networks with high surface-to-volume ratio and atomistically smooth surfaces. We also reveal the important roles of interfacial adhesion and diffusion that govern selective gas transport through the network.

cond-mat.mes-hall↗

arXiv2009

High-resolution Resonance Bragg-scattering spectroscopy of an atomic transition from a population difference grating in a vapor cell

The laser spectroscopy with a narrow linewidth and high signal to noise ratio (S/N) is very important in the precise measurement of optical frequencies. Here, we present a novel high-resolution backward resonance Bragg-scattering (RBS) spectroscopy from a population difference grating (PDG). The PDG is formed by a standing-wave (SW) pump field in thermal 87Rb vapor, which periodically modulates the space population distribution of two levels in the 87Rb D1 line. A probe beam, having the identical frequency and the orthogonal polarization with the SW pump field, is Bragg-scattered by the PDG. Such Bragg-scattered light becomes stronger at an atomic resonance transition, which forms the RBS spectrum with a high S/N and sub-natural linewidth. Using the scheme of the coherent superposition of the individual Rayleigh-scattered light emitted from the atomic dipole oscillators on the PDG, the experimentally observed RBS spectroscopy is theoretically explained.

physics.atom-ph↗

arXiv2008

Large Cross-phase Modulation Based on Double EIT in a Four-level Tripod Atomic System

We report the experimental observations on the simultaneous EIT effects for probe and trigger fields (double EIT) as well as the large cross-phase modulation (XPM) between the two fields in a four-level tripod EIT system of the D1 line of 87Rb atoms. The XPM coefficients (larger than 2*10-5cm2/W) and the accompanying transmissions (higher than 60%) are measured at slightly detuning of the probe field from the exact EIT resonance condition. The presented system can be applied in the recently proposed quantum information processing with weak cross-Kerr nonlinearities.

quant-ph↗

arXiv2006

Preparation and Determination of Spin-Polarized States in Multi-Zeeman-sublevel Atoms

We demonstrate a simple technique to prepare and determine the desired internal quantum states in multi-Zeeman-sublevel atoms. By choosing appropriate coupling and pumping laser beams, atoms can be easily prepared in a desired Zeeman sublevel with high purity or in any chosen ground-state population distributions. The population distributions or state purities of such prepared atomic states can be determined by using a weak, circularly-polarized probe beam due to differences in transition strengths among different Zeeman sublevels. Preparing well-defined internal quantum states in multi-Zeeman-sublevel atoms (or spin-polarized quantum-state engineering) will be very important in demonstrating many interesting effects in quantum information processing with multi-level atomic systems.

quant-ph↗