arXiv subjects

Yang Xu

Publications and source records attributed to Yang Xu.

At least 145 records · Page 8Linked to original sources

arXiv2025

MULTI: Multimodal Understanding Leaderboard with Text and Images

The rapid development of multimodal large language models (MLLMs) raises the question of how they compare to human performance. While existing datasets often feature synthetic or overly simplistic tasks, some models have already surpassed human expert baselines. In this paper, we present MULTI, a Chinese multimodal dataset derived from authentic examination questions. Comprising over 18,000 carefully selected and refined questions, MULTI evaluates models using real-world examination standards, encompassing image-text comprehension, complex reasoning, and knowledge recall. Additionally, We also introduce MULTI-Elite, a 500-question selected hard subset, and MULTI-Extend with more than 4,500 external knowledge context pieces for testing in-context learning capabilities. Our evaluation highlights substantial room for MLLM advancement, with Qwen2-VL-72B achieving a 76.9% accuracy on MULTI and 53.1% on MULTI-Elite leading 25 evaluated models, compared to human expert baselines of 86.1% and 73.1%. MULTI serves not only as a robust evaluation platform but also paves the way for the development of expert-level AI.

cs.CL↗

arXiv2025

DeepMMSearch-R1: Empowering Multimodal LLMs in Multimodal Web Search

Multimodal Large Language Models (MLLMs) in real-world applications require access to external knowledge sources and must remain responsive to the dynamic and ever-changing real-world information in order to address information-seeking and knowledge-intensive user queries. Existing approaches, such as retrieval augmented generation (RAG) methods, search agents, and search equipped MLLMs, often suffer from rigid pipelines, excessive search calls, and poorly constructed search queries, which result in inefficiencies and suboptimal outcomes. To address these limitations, we present DeepMMSearch-R1, the first multimodal LLM capable of performing on-demand, multi-turn web searches and dynamically crafting queries for both image and text search tools. Specifically, DeepMMSearch-R1 can initiate web searches based on relevant crops of the input image making the image search more effective, and can iteratively adapt text search queries based on retrieved information, thereby enabling self-reflection and self-correction. Our approach relies on a two-stage training pipeline: a cold start supervised finetuning phase followed by an online reinforcement learning optimization. For training, we introduce DeepMMSearchVQA, a novel multimodal VQA dataset created through an automated pipeline intermixed with real-world information from web search tools. This dataset contains diverse, multi-hop queries that integrate textual and visual information, teaching the model when to search, what to search for, which search tool to use and how to reason over the retrieved information. We conduct extensive experiments across a range of knowledge-intensive benchmarks to demonstrate the superiority of our approach. Finally, we analyze the results and provide insights that are valuable for advancing multimodal web-search.

cs.CV↗

arXiv2025

Extended Triangular Method: A Generalized Algorithm for Contradiction Separation Based Automated Deduction

Automated deduction lies at the core of Artificial Intelligence (AI), underpinning theorem proving, formal verification, and logical reasoning. Despite decades of progress, reconciling deductive completeness with computational efficiency remains an enduring challenge. Traditional reasoning calculi, grounded in binary resolution, restrict inference to pairwise clause interactions and thereby limit deductive synergy among multiple clauses. The Contradiction Separation Extension (CSE) framework, introduced in 2018, proposed a dynamic multi-clause reasoning theory that redefined logical inference as a process of contradiction separation rather than sequential resolution. While that work established the theoretical foundation, its algorithmic realization remained unformalized and unpublished. This work presents the Extended Triangular Method (ETM), a generalized contradiction-construction algorithm that formalizes and extends the internal mechanisms of contradiction separation. The ETM unifies multiple contradiction-building strategies, including the earlier Standard Extension method, within a triangular geometric framework that supports flexible clause interaction and dynamic synergy. ETM serves as the algorithmic core of several high-performance theorem provers, CSE, CSE-E, CSI-E, and CSI-Enig, whose competitive results in standard first-order benchmarks (TPTP problem sets and CASC 2018-2015) empirically validate the effectiveness and generality of the proposed approach. By bridging theoretical abstraction and operational implementation, ETM advances the contradiction separation paradigm into a generalized, scalable, and practically competitive model for automated reasoning, offering new directions for future research in logical inference and theorem proving.

cs.AI↗

arXiv2025

Team Networks with Partially Observed Links

This paper studies a linear production model in team networks with missing links. In the model, heterogeneous workers, represented as nodes, produce jointly and repeatedly within teams, represented as links. Links are omitted when their associated outcome variables fall below a threshold, resulting in partial observability of the network. To address this, I propose a Generalized Method of Moments estimator under normally distributed errors and develop a distribution-free test for detecting link truncation. Applied to academic publication data, the estimator reveals and corrects a substantial downward bias in the estimated scaling factor that aggregates individual fixed effects into team-specific fixed effects. This finding suggests that the collaboration premium may be systematically underestimated when missing links are not properly accounted for.

econ.EM↗

arXiv2025

Dynamic Automated Deduction by Contradiction Separation: The Standard Extension Algorithm

Automated deduction seeks to enable machines to reason with mathematical precision and logical completeness. Classical resolution-based systems, such as Prover9, E, and Vampire, rely on binary inference, which inherently limits multi-clause synergy during proof search. The Contradiction Separation Extension (CSE) framework, introduced by Xu et al. (2018), overcame this theoretical limitation by extending deduction beyond binary inference. However, the original work did not specify how contradictions are algorithmically constructed and extended in practice. This paper presents the Standard Extension algorithm, the first explicit procedural realization of contradiction separation reasoning. The proposed method dynamically constructs contradictions through complementary literal extension, thereby operationalizing the CSE theory within a unified algorithm for satisfiability and unsatisfiability checking. The algorithm's soundness and completeness are formally proven, and its effectiveness is supported indirectly through the performance of CSE-based systems, including CSE, CSE-E, CSI-E, and CSI-Enig in major automated reasoning competitions (CASC) in the last few years. These results confirm that the Standard Extension mechanism constitutes a robust and practically validated foundation for dynamic, multi-clause automated deduction.

cs.LO↗

arXiv2025

Structure-Preserving Margin Distribution Learning for High-Order Tensor Data with Low-Rank Decomposition

The Large Margin Distribution Machine (LMDM) is a recent advancement in classifier design that optimizes not just the minimum margin (as in SVM) but the entire margin distribution, thereby improving generalization. However, existing LMDM formulations are limited to vectorized inputs and struggle with high-dimensional tensor data due to the need for flattening, which destroys the data's inherent multi-mode structure and increases computational burden. In this paper, we propose a Structure-Preserving Margin Distribution Learning for High-Order Tensor Data with Low-Rank Decomposition (SPMD-LRT) that operates directly on tensor representations without vectorization. The SPMD-LRT preserves multi-dimensional spatial structure by incorporating first-order and second-order tensor statistics (margin mean and variance) into the objective, and it leverages low-rank tensor decomposition techniques including rank-1(CP), higher-rank CP, and Tucker decomposition to parameterize the weight tensor. An alternating optimization (double-gradient descent) algorithm is developed to efficiently solve the SPMD-LRT, iteratively updating factor matrices and core tensor. This approach enables SPMD-LRT to maintain the structural information of high-order data while optimizing margin distribution for improved classification. Extensive experiments on diverse datasets (including MNIST, images and fMRI neuroimaging) demonstrate that SPMD-LRT achieves superior classification accuracy compared to conventional SVM, vector-based LMDM, and prior tensor-based SVM extensions (Support Tensor Machines and Support Tucker Machines). Notably, SPMD-LRT with Tucker decomposition attains the highest accuracy, highlighting the benefit of structure preservation. These results confirm the effectiveness and robustness of SPMD-LRT in handling high-dimensional tensor data for classification.

cs.LG↗

arXiv2025

Reflexive Partitions Induced by Rank Support and Non-Reflexive Partitions Induced by Rank Weight

In this paper, we study partitions of finite modules induced by rank support and rank weight. First, we show that partitions induced by rank support are mutually dual with respect to suitable non-degenerate pairings, and hence are reflexive; moreover, we compute the associated generalized Krawtchouk matrices. Similar results are established for partitions induced by isomorphic relation of rank support. These results generalize counterpart results established for row space partitions and rank partitions of matrix spaces over finite fields. Next, we show that partitions of free modules over a finite chain ring $R$ induced by rank weight are non-reflexive provided that $R$ is not a field; moreover, we characterize the dual partitions explicitly. As a corollary, we show that rank partitions of matrix spaces over $R$ are reflexive if and only if $R$ is a field; moreover, two matrices belong to the same member of the dual partition if and only if their transposes are equivalent. In particular, we show that opposite to matrices over finite fields, rank metric does not induce an association scheme provided that $R$ is not a field, which further settles an open question proposed by Blanco-Chacón, Boix, Greferath and Hieta-Aho in \cite{2}.

cs.IT↗

arXiv2025

Contradictions

Trustworthy AI requires reasoning systems that are not only powerful but also transparent and reliable. Automated Theorem Proving (ATP) is central to formal reasoning, yet classical binary resolution remains limited, as each step involves only two clauses and eliminates at most two literals. To overcome this bottleneck, the concept of standard contradiction and the theory of contradiction-separation-based deduction were introduced in 2018. This paper advances that framework by focusing on the systematic construction of standard contradictions. Specially, this study investigates construction methods for two principal forms of standard contradiction: the maximum triangular standard contradiction and the triangular-type standard contradiction. Building on these structures, we propose a procedure for determining the satisfiability and unsatisfiability of clause sets via maximum standard contradiction. Furthermore, we derive formulas for computing the number of standard sub-contradictions embedded within both the maximum triangular standard contradiction and the triangular-type standard contradiction. The results presented herein furnish the methodological basis for advancing contradiction-separation-based dynamic multi-clause automated deduction, thereby extending the expressive and deductive capabilities of automated reasoning systems beyond the classical binary paradigm.

cs.LO↗

arXiv2025

Revisiting the diffusion equation derivation in Persson's theory of contact

In Persson's seminal work on tire-road interaction (Persson, J. Chem. Phys. {\bf 115}(8), 2001), he ingeniously derived a diffusion equation in Appendix B to characterize the evolution of contact pressure between a rigid rough indenter and an elastic half-space with spatial magnification, which constitutes the foundation of Persson's theory of contact. Persson's theory has been extensively validated and applied to investigate nearly all critical aspects of tribological problems. In contrast to the well-known Greenwood-Williamson (GW) model, Persson's theory receives relatively less attention within the tribology community. One contributing factor to this discrepancy is that the original derivation of the diffusion equation in Appendix B is not easily understandable to non-physicists. In this technical note, the authors provide supplementary information for each step of the derivation, aiming to clarify the conceptual foundation for researchers who encounter difficulties in understanding Persson's theory, thereby encouraging its broader application within and beyond tribology.

cond-mat.soft↗

arXiv2025

Discovery of nodal-line superconductivity in chiral crystals

Chiral crystals, whose key feature is the structural handedness, host exotic quantum phenomena driven by the interplay of band topology, spin-orbit coupling (SOC), and electronic correlations. Due to the limited availability of suitable chiral-crystal materials, their unconventional superconductivity (SC) remains largely unexplored. Here, we report the discovery of unconventional SC in the La(Rh,Ir)Si family of materials by combining muon-spin spectroscopy, band-structure calculations, and perturbation theory. This family, characterized by a double-helix chiral structure, hosts exotic multifold fermions that are absent in other topological chiral crystals. While LaRhSi behaves as a fully-gapped superconductor, the substitution of 4$d$-Rh by 5$d$-Ir significantly enhances the SOC and leads to the emergence of topological nodal-line SC in LaIrSi. The developed model shows that the nodal-line SC arises from an isotropic SOC with a specific strength. Such an exotic mechanism expands our conventional understanding of material candidates for unconventional SC, which typically rely on a significantly anisotropic SOC to promote the triplet pairing. Our work establishes a new type of phase diagram, which provides a comprehensive roadmap for identifying and engineering unconventional SC in chiral crystals. Furthermore, it calls for renewed investigations of unconventional SC in other widely studied superconductors with a chiral structure.

cond-mat.supr-con↗

arXiv2025

Towards Better Correctness and Efficiency in Code Generation

While code large language models have demonstrated remarkable progress in code generation, the generated code often exhibits poor runtime efficiency, limiting its practical application in performance-sensitive scenarios. To address this limitation, we propose an efficiency-oriented reinforcement learning framework guided by a novel performance reward. Based on this framework, we take a deeper dive into the code efficiency problem, identifying then proposing methods to overcome key bottlenecks: (1) Dynamic exploration overcomes the static data constraints of offline fine-tuning, enabling the discovery of more efficient code implementations. (2) The error-insensitive reinforcement learning method and high-contrast efficiency signals are crucial for mitigating systematic errors and achieving effective optimization. (3) Online exploration is most effective when starting from a high-correctness baseline, as this allows for efficiency improvements without sacrificing accuracy. With these discoveries, we finally propose a two-stage tuning method, which achieves high and balanced performance across correctness and efficiency. The results of experiments show the effectiveness of the method, which improves code correctness by 10.18\% and runtime efficiency by 7.75\% on a 7B model, achieving performance comparable to much larger model.

cs.SE↗

arXiv2025

Deep regularization networks for inverse problems with noisy operators

A supervised learning approach is proposed for regularization of large inverse problems where the main operator is built from noisy data. This is germane to superresolution imaging via the sampling indicators of the inverse scattering theory. We aim to accelerate the spatiotemporal regularization process for this class of inverse problems to enable real-time imaging. In this approach, a neural operator maps each pattern on the right-hand side of the scattering equation to its affiliated regularization parameter. The network is trained in two steps which entails: (1) training on low-resolution regularization maps furnished by the Morozov discrepancy principle with nonoptimal thresholds, and (2) optimizing network predictions through minimization of the Tikhonov loss function regulated by the validation loss. Step 2 allows for tailoring of the approximate maps of Step 1 toward construction of higher quality images. This approach enables direct learning from test data and dispenses with the need for a-priori knowledge of the optimal regularization maps. The network, trained on low-resolution data, quickly generates dense regularization maps for high-resolution imaging. We highlight the importance of the training loss function on the network's generalizability. In particular, we demonstrate that networks informed by the logic of discrepancy principle lead to images of higher contrast. In this case, the training process involves many-objective optimization. We propose a new method to adaptively select the appropriate loss weights during training without requiring an additional optimization process. The proposed approach is synthetically examined for imaging damage evolution in an elastic plate. The results indicate that the discrepancy-informed regularization networks not only accelerate the imaging process, but also remarkably enhance the image quality in complex environments.

math.NA↗

arXiv2025

D3FNet: A Differential Attention Fusion Network for Fine-Grained Road Structure Extraction in Remote Perception Systems

Extracting narrow roads from high-resolution remote sensing imagery remains a significant challenge due to their limited width, fragmented topology, and frequent occlusions. To address these issues, we propose D3FNet, a Dilated Dual-Stream Differential Attention Fusion Network designed for fine-grained road structure segmentation in remote perception systems. Built upon the encoder-decoder backbone of D-LinkNet, D3FNet introduces three key innovations:(1) a Differential Attention Dilation Extraction (DADE) module that enhances subtle road features while suppressing background noise at the bottleneck; (2) a Dual-stream Decoding Fusion Mechanism (DDFM) that integrates original and attention-modulated features to balance spatial precision with semantic context; and (3) a multi-scale dilation strategy (rates 1, 3, 5, 9) that mitigates gridding artifacts and improves continuity in narrow road prediction. Unlike conventional models that overfit to generic road widths, D3FNet specifically targets fine-grained, occluded, and low-contrast road segments. Extensive experiments on the DeepGlobe and CHN6-CUG benchmarks show that D3FNet achieves superior IoU and recall on challenging road regions, outperforming state-of-the-art baselines. Ablation studies further verify the complementary synergy of attention-guided encoding and dual-path decoding. These results confirm D3FNet as a robust solution for fine-grained narrow road extraction in complex remote and cooperative perception scenarios.

cs.CV↗

arXiv2025

Hybrid Deep Reconstruction for Vignetting-Free Upconversion Imaging through Scattering in ENZ Materials

Optical imaging through turbid or heterogeneous environments (collectively referred to as complex media) is fundamentally challenged by scattering, which scrambles structured spatial and phase information. To address this, we propose a hybrid-supervised deep learning framework to reconstruct high-fidelity images from nonlinear scattering measurements acquired with a time-gated epsilon-near-zero (ENZ) imaging system. The system leverages four-wave mixing (FWM) in subwavelength indium tin oxide (ITO) films to temporally isolate ballistic photons, thus rejecting multiply scattered light and enhancing contrast. To recover structured features from these signals, we introduce DeepTimeGate, a U-Net-based supervised model that performs initial reconstruction, followed by a Deep Image Prior (DIP) refinement stage using self-supervised learning. Our approach demonstrates strong performance across different imaging scenarios, including binary resolution patterns and complex vortex-phase masks, under varied scattering conditions. Compared to raw scattering inputs, it boosts average PSNR by 124%, SSIM by 231%, and achieves a 10 times improvement in intersection-over-union (IoU). Beyond enhancing fidelity, our method removes the vignetting effect and expands the effective field-of-view compared to the ENZ-based optical time gate output. These results suggest broad applicability in biomedical imaging, in-solution diagnostics, and other scenarios where conventional optical imaging fails due to scattering.

physics.optics↗

arXiv2025

Contrastive Multi-View Graph Hashing

Multi-view graph data, which both captures node attributes and rich relational information from diverse sources, is becoming increasingly prevalent in various domains. The effective and efficient retrieval of such data is an important task. Although multi-view hashing techniques have offered a paradigm for fusing diverse information into compact binary codes, they typically assume attributes-based inputs per view. This makes them unsuitable for multi-view graph data, where effectively encoding and fusing complex topological information from multiple heterogeneous graph views to generate unified binary embeddings remains a significant challenge. In this work, we propose Contrastive Multi-view Graph Hashing (CMGHash), a novel end-to-end framework designed to learn unified and discriminative binary embeddings from multi-view graph data. CMGHash learns a consensus node representation space using a contrastive multi-view graph loss, which aims to pull $k$-nearest neighbors from all graphs closer while pushing away negative pairs, i.e., non-neighbor nodes. Moreover, we impose binarization constraints on this consensus space, enabling its conversion to a corresponding binary embedding space at minimal cost. Extensive experiments on several benchmark datasets demonstrate that CMGHash significantly outperforms existing approaches in terms of retrieval accuracy.

cs.IR↗

arXiv2025

GRB 240825A: Early Reverse Shock and Its Physical Implications

Early multiwavelength observations offer crucial insights into the nature of the relativistic jets responsible for gamma-ray bursts and their interaction with the surrounding medium.We present data of GRB 240825A from 17 space- and ground-based telescopes/instruments, covering wavelengths from NIR/optical to X-ray and GeV, and spanning from the prompt emission to the afterglow phase triggered by Swift and Fermi. The early afterglow observations were carried out by SVOM/C-GFT, and spectroscopic observations of the afterglow by GTC, VLT, and TNG determined the redshift of the burst ($z = 0.659$) later.A comprehensive analysis of the prompt emission spectrum observed by Swift-BAT and Fermi-GBM/LAT reveals a rare and significant high-energy cutoff at ~76 MeV. Assuming this cutoff is due to $γγ$ absorption allows us to place an upper limit on the initial Lorentz factor, $Γ_0 < 245$. The optical/NIR and GeV afterglow light curves be described by the standard external shock model, with early-time emission dominated by a reverse shock (RS) and a subsequent transition to forward shock (FS) emission. Our afterglow modelling yields a consistent estimate of the initial Lorentz factor ($Γ_{\rm 0} \sim 234$). Furthermore, the RS-to-FS magnetic field ratio ($\mathcal{R}_B \sim 302$) indicates that the reverse shock region is significantly more magnetized than the FS region. An isotropic-equivalent kinetic energy of $E_{\text{k,iso}} = 5.25 \times 10^{54}$ erg is derived, and the corresponding $γ$-ray radiation efficiency is estimated to be $η_γ$ = 3.1%. On the other hand, the standard afterglow model can not reproduce the X-ray light curve of GRB 240825A, calling for improved models to characterize all multiwavelength data.

astro-ph.HE↗

arXiv2025

FLUX-Makeup: High-Fidelity, Identity-Consistent, and Robust Makeup Transfer via Diffusion Transformer

Makeup transfer aims to apply the makeup style from a reference face to a target face and has been increasingly adopted in practical applications. Existing GAN-based approaches typically rely on carefully designed loss functions to balance transfer quality and facial identity consistency, while diffusion-based methods often depend on additional face-control modules or algorithms to preserve identity. However, these auxiliary components tend to introduce extra errors, leading to suboptimal transfer results. To overcome these limitations, we propose FLUX-Makeup, a high-fidelity, identity-consistent, and robust makeup transfer framework that eliminates the need for any auxiliary face-control components. Instead, our method directly leverages source-reference image pairs to achieve superior transfer performance. Specifically, we build our framework upon FLUX-Kontext, using the source image as its native conditional input. Furthermore, we introduce RefLoRAInjector, a lightweight makeup feature injector that decouples the reference pathway from the backbone, enabling efficient and comprehensive extraction of makeup-related information. In parallel, we design a robust and scalable data generation pipeline to provide more accurate supervision during training. The paired makeup datasets produced by this pipeline significantly surpass the quality of all existing datasets. Extensive experiments demonstrate that FLUX-Makeup achieves state-of-the-art performance, exhibiting strong robustness across diverse scenarios.

cs.CV↗

arXiv2025

Voronoi Diagram Encoded Hashing

The goal of learning to hash (L2H) is to derive data-dependent hash functions from a given data distribution in order to map data from the input space to a binary coding space. Despite the success of L2H, two observations have cast doubt on the source of the power of L2H, i.e., learning. First, a recent study shows that even using a version of locality sensitive hashing functions without learning achieves binary representations that have comparable accuracy as those of L2H, but with less time cost. Second, existing L2H methods are constrained to three types of hash functions: thresholding, hyperspheres, and hyperplanes only. In this paper, we unveil the potential of Voronoi diagrams in hashing. Voronoi diagram is a suitable candidate because of its three properties. This discovery has led us to propose a simple and efficient no-learning binary hashing method, called Voronoi Diagram Encoded Hashing (VDeH), which constructs a set of hash functions through a data-dependent similarity measure and produces independent binary bits through encoded hashing. We demonstrate through experiments on several benchmark datasets that VDeH achieves superior performance and lower computational cost compared to existing state-of-the-art methods under the same bit length.

cs.IR↗