arXiv subjects

Xingyu Wang

Publications and source records attributed to Xingyu Wang.

At least 19 recordsLinked to original sources

arXiv2026

Hull First, Wake Second: Wake-Reliance Suppression for Robust Maritime Vessel Detection

Maritime vessel detectors often face scenes where hulls are small, low-contrast, or blurred, while wakes are longer and easier to detect. This creates a wake-reliance problem: detectors may miss slow or stationary vessels with weak wakes, or produce false positives on wake-like water clutter. We propose HullWake, a hull-first wake-second framework for robust maritime vessel detection. HullWake separates proposal-centered hull evidence from directional wake context, extracts wake cues with bidirectional proposal-anchored corridors, and suppresses wake-dominant predictions through wake response supervision, wake-attenuated consistency, wake-only confidence suppression, and hull--wake decorrelation. We also introduce a wake-oriented evaluation protocol covering weak/no-wake vessels, wake-like hard negatives, worst-group AP, and confidence drop after wake attenuation. Experiments are conducted on Curated-Wake, a wake-oriented maritime dataset of about 10,000 images curated from Ships/Vessels in Aerial Images, the SMD benchmark, and SeaDronesSee, with newly added detection- and segmentation-level wake annotations. Compared with box-only detectors and mask-supervised segmentation baselines, HullWake improves overall AP, weak/no-wake robustness, wake-like false positives, worst-group AP, and confidence stability after wake attenuation.

cs.CV↗

arXiv2026

JuZhou 1.0 Technical Report: The First Edge-Native Text-to-Image Foundation Model Trained Entirely on China-Developed AI Accelerators

Text-to-image (T2I) diffusion models typically require substantial computational resources and cloud infrastructure, posing significant challenges for edge deployment in terms of latency, cost, and user privacy. We present JuZhou 1.0, an ultra-lightweight T2I foundation model designed for fully offline, on-device execution. JuZhou 1.0 achieves its efficiency through four key designs: (1) a compact image-generation backbone consisting of a 0.385B-parameter denoising U-Net and a 1.90M-parameter distilled decoder, totaling approximately 0.387B parameters; (2) Rectified Flow training combined with DMD2 distillation, reducing inference to 4 sampling steps; (3) Chinese semantic alignment trained on 9M curated image-text pairs, enabling direct Chinese prompting without external translation at inference time; and (4) a training and distillation pipeline completed on domestically developed Sugon K100 AI accelerators without relying on NVIDIA GPUs for training or distillation. Despite its compact scale, the 28-step base model of JuZhou 1.0 achieves an overall GenEval score of 0.69, outperforming published baselines including SDXL (2.6B, 0.55), SD3-Medium (2B, 0.62), and IF-XL (4.3B, 0.61). We further validate the full poetry-to-image pipeline on Android and the core CLIP-U-Net-VAE generation branch on iOS. On a smartphone powered by the Snapdragon 8 Elite Gen 5 Mobile Platform, the 4-step U-Net denoising branch runs in approximately 1.6 seconds, while the full Android poetry-to-image pipeline takes 4.5 seconds with on-device prompt refinement on Xiaomi 17 Pro Max. These results position JuZhou 1.0 as a practical approach to mobile text-to-image generation and provide a concrete reference for Chinese-native generation, domestic-compute training, and fully offline on-device deployment after one-time installation.

cs.CV↗

arXiv2026

Primal-Dual Halpern-PAGE Algorithm for Constrained Stochastic Weakly Convex Optimization

We tackle the challenging problem of stochastic weakly convex optimization subject to mixed (equality and inequality) expected-value constraints. While optimal $\mathcal{O}(\epsilon^{-3})$ sample complexity algorithms exist for unconstrained weakly convex problems, dealing with complex functional constraints typically requires cumbersome multi-loop penalty or augmented Lagrangian methods, which suffer from high inner-loop complexity and sensitive parameter tuning. To bridge this fundamental gap, we propose the primal-dual Halpern-PAGE (PD-HP) algorithm. As a purely single-loop method, PD-HP completely bypasses the computational burden of nested iterations. At each step, it merely requires solving a simple strongly convex surrogate subproblem alongside a straightforward dual projection, making it exceptionally efficient and convenient to implement. Crucially, we prove that this computationally lightweight algorithm achieves the optimal $\mathcal{O}(\epsilon^{-3})$ sample complexity for mixed-constrained stochastic weakly convex problems, successfully matching the theoretical lower bounds. Furthermore, when the primal domain is a compact polyhedral convex set, we establish the deterministic stability of the dual multipliers by exploiting the generalized Mangasarian-Fromovitz constraint qualification (MFCQ) alongside Hoffman's error bound. This ensures that our optimal complexity bound holds strictly under the standard, unbounded KKT residual metric without any theoretical gaps or artificial residual truncations.

math.OC↗

arXiv2026

UniScale: Adaptive Unified Inference Scaling via Online Joint Optimization of Model Routing and Test-Time Scaling

In real-world deployments of large language models (LLMs), balancing inference quality and computational cost has become a central challenge. Existing approaches tackle this trade-off along two largely independent dimensions: model routing, which switches among models of different scales to match request complexity, and test-time scaling (TTS), which adjusts inference-time compute within a fixed model for fine-grained control. However, this decoupled design introduces inherent limitations. Model routing yields coarse-grained, discrete performance changes due to the sparse set of model scales, while single-model TTS often encounters capacity ceilings and exhibits diminishing returns as compute increases. Moreover, treating the two mechanisms separately restricts adaptability in dynamic inference environments. To overcome these limitations, we introduce Unified Inference Scaling (UIS), which unifies model routing and TTS in a single optimization space. Building on this formulation, we propose UniScale, an online framework that models adaptive UIS as a contextual multi-armed bandit problem and learns inference policies via LinUCB. The framework incorporates efficiency-aware learning and cost modeling to ensure stable and scalable optimization over high-dimensional action spaces. Evaluation shows that UniScale effectively exploits the synergy in the UIS space to deliver a fine-grained and consistently better quality-cost trade-off across diverse, dynamic inference scenarios.

cs.AI↗

arXiv2026

CUBic: Coordinated Unified Bimanual Perception and Control Framework

Recent advances in visuomotor policy learning have enabled robots to perform control directly from visual inputs. Yet, extending such end-to-end learning from single-arm to bimanual manipulation remains challenging due to the need for both independent perception and coordinated interaction between arms. Existing methods typically favor one side -- either decoupling the two arms to avoid interference or enforcing strong cross-arm coupling for coordination -- thus lacking a unified treatment. We propose CUBic, a Coordinated and Unified framework for Bimanual perception and control that reformulates bimanual coordination as a unified perceptual modeling problem. CUBic learns a shared tokenized representation bridging perception and control, where independence and coordination emerge intrinsically from structure rather than from hand-crafted coupling. Our approach integrates three components: unidirectional perception aggregation, bidirectional perception coordination through two codebooks with shared mapping, and a unified perception-to-control diffusion policy. Extensive experiments on the RoboTwin benchmark show that CUBic consistently surpasses standard baselines, achieving marked improvements in coordination accuracy and task success rates over state-of-the-art visuomotor baselines.

cs.RO↗

arXiv2026

Prox-PEP: A Proximal Partial Exact Penalty Algorithm for Weakly Convex Stochastic Nonlinear Programming

This paper considers stochastic optimization problems with weakly convex objective and constraint functions. We propose Prox-PEP, a proximal method equipped with quadratic subproblems. To handle nonlinear equality constraints, we employ an exact penalty approach, transforming them into inequality constraints with auxiliary slack variables. At each iteration, we construct quadratic approximations for both the objective and the constraint functions to facilitate efficient subproblem computation. By carefully designing the second-order approximation matrices, the subproblem constructed via the augmented Lagrangian function is strictly guaranteed to be strongly convex. Furthermore, we adopt a dynamic strategy for the equality penalty parameter: it monotonically increases up to a predefined threshold and remains constant thereafter. Building upon this algorithmic framework, we establish comprehensive asymptotic complexities. We prove that Prox-PEP achieves an $\mathcal{O}(T^{-1/4})$ average expected oracle complexity for $\epsilon$-KKT stationarity, specifically bounding the squared norm of the gradient of the Moreau envelope of the Lagrangian function, alongside constraint violations and complementarity conditions. Additionally, under standard light-tailed martingale noise assumptions, we derive an $\mathcal{O}(T^{-1/8})$ high-probability convergence bound for the norm of the gradient of the Lagrangian's Moreau envelope, as well as $\mathcal{O}(T^{-1/4})$ high-probability bounds for both constraint violations and complementarity conditions.

math.OC↗

arXiv2026

Semantics Over Syntax: Uncovering Pre-Authentication 5G Baseband Vulnerabilities

Modern 5G user equipment (UE) processes Radio Resource Control (RRC) configuration messages during early control-plane exchanges, before authentication and integrity protection are established. Prior work for testing 5G UEs has largely focused on constructing syntactically invalid inputs. In contrast, we show that syntactically valid but semantically inconsistent messages, which violate specification-level field constraints or cross-field dependencies, can drive baseband implementations into invalid states, triggering assertion failures or modem crashes. These findings reveal semantic inconsistencies in pre-authentication signaling as a critical yet underexplored attack surface in 5G UE implementations. To address this gap, we present Constraint-Guided Semantic Testing (ConSeT), a framework that systematically extracts specification-level constraints and leverages them to generate targeted semantic violations for testing 5G UEs. ConSeT decodes RRC messages into structured fields, derives schema-based rules, infers cross-field dependencies using a Large Language Model (LLM) in an evidence-bounded manner, and produces syntactically valid test cases that intentionally violate semantic constraints. We evaluate ConSeT on both commercial and open-source 5G UEs. On commercial smartphones, it uncovers 7 previously unknown vulnerabilities through responsible disclosure, including 3 high-severity CVEs, affecting 64 chipset models and over 542 commercially available smartphone models. On the open-source OAI UE, ConSeT additionally triggers 29 distinct crash sites.

cs.CR↗

arXiv2026

FOZO: Forward-Only Zeroth-Order Prompt Optimization for Test-Time Adaptation

Test-Time Adaptation (TTA) is essential for enabling deep learning models to handle real-world data distribution shifts. However, current approaches face significant limitations: backpropagation-based methods are not suitable for low-end deployment devices, due to their high computation and memory requirements, as well as their tendency to modify model weights during adaptation; while traditional backpropagation-free techniques exhibit constrained adaptation capabilities. In this work, we propose Forward-Only Zeroth-Order Optimization (FOZO), a novel and practical backpropagation-free paradigm for TTA. FOZO leverages a memory-efficient zeroth-order prompt optimization, which is led by objectives optimizing both intermediate feature statistics and prediction entropy. To ensure efficient and stable adaptation over the out-of-distribution data stream, we introduce a dynamically decaying perturbation scale during zeroth-order gradient estimation and theoretically prove its convergence under the TTA data stream assumption. Extensive continual adaptation experiments on ImageNet-C, ImageNet-R, and ImageNet-Sketch demonstrate FOZO's superior performance, achieving 59.52% Top-1 accuracy on ImageNet-C (5K, level 5) and outperforming main gradient-based methods and SOTA forward-only FOA (58.13%). Furthermore, FOZO exhibits strong generalization on quantized (INT8) models. These findings demonstrate that FOZO is a highly competitive solution for TTA deployment in resource-limited scenarios.

cs.CV↗

arXiv2026

The sharp-interface limit of the matrix-valued Allen--Cahn equation

We study the sharp-interface limit of a matrix-valued Allen--Cahn equation with the Saint Venant--Kirchhoff potential \[ F(\mathbf{A})=\frac14\|{\mathbf{A}\mathbf{A}^\top-\mathbf{I}}\|^2 . \] The zero set of this potential is the orthogonal group $\mathbb{O}_n=\mathbb{O}_n^+\cup\mathbb{O}_n^-$, and the corresponding limiting problem combines mean-curvature motion of the interface with harmonic-map heat flow in the two bulk phases. The proof combines a modulated-energy argument with compactness estimates obtained from two skew-symmetric commutator formulations of the equation. The method avoids the spectral analysis of linearized operators around quasi-minimal connecting orbits and the construction of high-order matched asymptotic expansions. In particular, the limiting maps satisfy the minimal-pair condition on the moving interface and the weak transmission identities which, for smooth limits, are equivalent to the Neumann-type jump condition of the sharp-interface system.

math.AP↗

arXiv2026

First-Exit Time Analysis for Truncated Heavy-Tailed Dynamical Systems

In this paper, we study the first-exit time of stochastic difference equation $X^\eta_{j+1}(x) = X^\eta_{j}(x) + \eta a\big( X^\eta_{j}(x)\big) + \eta \sigma\big( X^\eta_{j}(x)\big)Z_{j+1}$ and its truncated variant $X^{\eta|b}_{j+1}(x) = X^{\eta|b}_{j}( x) + \varphi_b\big(\eta a\big( X^{\eta|b}_{j}( x)\big) + \eta \sigma\big( X^{\eta|b}_{j}( x)\big) Z_{j+1}\big)$, where $\varphi_b(x) = (x/|x|)\min\{|x|, b\}$ and the law of the noise $Z_t$ is multivariate regularly varying. The truncation operator $\varphi_b(\cdot)$ is often introduced as a modulation mechanism in heavy-tailed systems, such as stochastic gradient descent algorithms in deep learning. By developing a framework that connects large deviations with metastability, we leverage the locally uniform sample-path large deviations for both processes in Wang and Rhee (2024) to obtain precise characterizations of the joint distributions of the first exit times and exit locations. The resulting limit theorem unveils a discrete hierarchy of phase transitions (i.e., exit times) as the truncation threshold $b$ varies, and manifests the catastrophe principle, whereby key events or metastable behaviors in heavy-tailed systems are driven by catastrophic behavior in a few components while the rest of the system behaves nominally. These developments lead to a comprehensive heavy-tailed counterpart of the classical Freidlin-Wentzell theory.

math.PR↗

arXiv2025

Uncovering bistability phenomena in two-layer Couette flow experiments using nonlocal evolution equations

This paper investigates the stability of interfacial long waves in two-layer plane Couette flow using a nonlinear, nonlocal asymptotic model derived from the Navier-Stokes equations and valid for thin upper layers. Nonlocality enters through a coupling of the thin and main layers, and crucial inertial effects are retained. The models generically support bistability phenomena observed in experiments where two stable travelling waves, one unimodal and the other bimodal, are recorded at the same lid velocity. In direct comparisons with experiments, the models show remarkable agreement, both qualitatively and quantitatively. The two stable travelling waves are identified and their basins of attraction characterised via large-time computations for different initial conditions. We also identify a new symmetry-breaking travelling-wave branch bifurcating from the bimodal family, compute higher-wavenumber travelling-wave branches, and present time-periodic orbits arising via Hopf bifurcation.

physics.flu-dyn↗

arXiv2025

Global Dynamics of Heavy-Tailed SGDs in Nonconvex Loss Landscape: Characterization and Control

Stochastic gradient descent (SGD) and its variants enable modern artificial intelligence. However, theoretical understanding lags far behind their empirical success. It is widely believed that SGD has a curious ability to avoid sharp local minima in the loss landscape, which are associated with poor generalization. To unravel this mystery and further enhance such capability of SGDs, it is imperative to go beyond the traditional local convergence analysis and obtain a comprehensive understanding of SGDs' global dynamics. In this paper, we develop a set of technical machinery based on the recent large deviations and metastability analysis in Wang and Rhee (2023) and obtain sharp characterization of the global dynamics of heavy-tailed SGDs. In particular, we reveal a fascinating phenomenon in deep learning: by injecting and then truncating heavy-tailed noises during the training phase, SGD can almost completely avoid sharp minima and achieve better generalization performance for the test data. Simulation and deep learning experiments confirm our theoretical prediction that heavy-tailed SGD with gradient clipping finds local minima with a more flat geometry and achieves better generalization performance.

cs.LG↗

arXiv2025

Affine web of type Q

We introduce a new diagrammatic $\Bbbk$-linear monoidal supercategory $QWeb^\bullet$, the affine web supercategory of type $Q$, where $\Bbbk$ is a commutative ring of characteristic not two. This category is the affinization of the web category of type $Q$, originally introduced by Brown and Kujawa. It serves as the type $Q$ analog of the affine web category introduced by Davidson, Kujawa, Muth and Zhu, and independently by Wang and one of the authors. We obtain diagrammatic integral bases for the Hom-spaces of this category. We show that $QWeb^\bullet$ provides a combinatorial model for a natural monoidal supercategory of endosuperfunctors for Lie superalgebras of type $Q$. .

math.RT↗

arXiv2025

The vector-valued Allen-Cahn equation with potentials of high-dimensional double-wells under Robin boundary conditions

This work investigates the vector-valued Allen-Cahn equation with potentials of high-dimensional double-wells under Robin boundary conditions. We establish local-in-time convergence of solutions to mean curvature flow with a fixed contact angle $0<\alpha\leq 90^\circ$, for a broad class of boundary energy densities and well-prepared initial data. The limiting sharp-interface system is derived, comprising harmonic heat flows in the bulk and minimal pair conditions at phase boundaries. The analysis combines the relative entropy method with gradient flow calibrations and weak convergence techniques. These results extend prior works on the analysis of the vector-valued case without boundary effects (Comm. Pure Appl. Math., 78:1199-1247, 2025) and the scalar-valued case with boundary contact energy (Calc. Var. Partial Differ. Equ., 61:201, 2022).

math.AP↗

arXiv2025

Chain-of-Talkers (CoTalk): Fast Human Annotation of Dense Image Captions

While densely annotated image captions significantly facilitate the learning of robust vision-language alignment, methodologies for systematically optimizing human annotation efforts remain underexplored. We introduce Chain-of-Talkers (CoTalk), an AI-in-the-loop methodology designed to maximize the number of annotated samples and improve their comprehensiveness under fixed budget constraints (e.g., total human annotation time). The framework is built upon two key insights. First, sequential annotation reduces redundant workload compared to conventional parallel annotation, as subsequent annotators only need to annotate the ``residual'' -- the missing visual information that previous annotations have not covered. Second, humans process textual input faster by reading while outputting annotations with much higher throughput via talking; thus a multimodal interface enables optimized efficiency. We evaluate our framework from two aspects: intrinsic evaluations that assess the comprehensiveness of semantic units, obtained by parsing detailed captions into object-attribute trees and analyzing their effective connections; extrinsic evaluation measures the practical usage of the annotated captions in facilitating vision-language alignment. Experiments with eight participants show our Chain-of-Talkers (CoTalk) improves annotation speed (0.42 vs. 0.30 units/sec) and retrieval performance (41.13% vs. 40.52%) over the parallel method.

cs.CL↗

arXiv2025

HF-VTON: High-Fidelity Virtual Try-On via Consistent Geometric and Semantic Alignment

Virtual try-on technology has become increasingly important in the fashion and retail industries, enabling the generation of high-fidelity garment images that adapt seamlessly to target human models. While existing methods have achieved notable progress, they still face significant challenges in maintaining consistency across different poses. Specifically, geometric distortions lead to a lack of spatial consistency, mismatches in garment structure and texture across poses result in semantic inconsistency, and the loss or distortion of fine-grained details diminishes visual fidelity. To address these challenges, we propose HF-VTON, a novel framework that ensures high-fidelity virtual try-on performance across diverse poses. HF-VTON consists of three key modules: (1) the Appearance-Preserving Warp Alignment Module (APWAM), which aligns garments to human poses, addressing geometric deformations and ensuring spatial consistency; (2) the Semantic Representation and Comprehension Module (SRCM), which captures fine-grained garment attributes and multi-pose data to enhance semantic representation, maintaining structural, textural, and pattern consistency; and (3) the Multimodal Prior-Guided Appearance Generation Module (MPAGM), which integrates multimodal features and prior knowledge from pre-trained models to optimize appearance generation, ensuring both semantic and geometric consistency. Additionally, to overcome data limitations in existing benchmarks, we introduce the SAMP-VTONS dataset, featuring multi-pose pairs and rich textual annotations for a more comprehensive evaluation. Experimental results demonstrate that HF-VTON outperforms state-of-the-art methods on both VITON-HD and SAMP-VTONS, excelling in visual fidelity, semantic consistency, and detail preservation.

cs.CV↗

arXiv2025

DocMMIR: A Framework for Document Multi-modal Information Retrieval

The rapid advancement of unsupervised representation learning and large-scale pre-trained vision-language models has significantly improved cross-modal retrieval tasks. However, existing multi-modal information retrieval (MMIR) studies lack a comprehensive exploration of document-level retrieval and suffer from the absence of cross-domain datasets at this granularity. To address this limitation, we introduce DocMMIR, a novel multi-modal document retrieval framework designed explicitly to unify diverse document formats and domains, including Wikipedia articles, scientific papers (arXiv), and presentation slides, within a comprehensive retrieval scenario. We construct a large-scale cross-domain multimodal benchmark, comprising 450K samples, which systematically integrates textual and visual information. Our comprehensive experimental analysis reveals substantial limitations in current state-of-the-art MLLMs (CLIP, BLIP2, SigLIP-2, ALIGN) when applied to our tasks, with only CLIP demonstrating reasonable zero-shot performance. Furthermore, we conduct a systematic investigation of training strategies, including cross-modal fusion methods and loss functions, and develop a tailored approach to train CLIP on our benchmark. This results in a +31% improvement in MRR@10 compared to the zero-shot baseline. All our data and code are released in https://github.com/J1mL1/DocMMIR.

cs.IR↗

arXiv2025

Understanding and Detecting Peer Dependency Resolving Loop in npm Ecosystem

As the default package manager for Node.js, npm has become one of the largest package management systems in the world. To facilitate dependency management for developers, npm supports a special type of dependency, Peer Dependency, whose installation and usage differ from regular dependencies. However, conflicts between peer dependencies can trap the npm client into infinite loops, leading to resource exhaustion and system crashes. We name this problem PeerSpin. Although PeerSpin poses a severe risk to ecosystems, it was overlooked by previous studies, and its impacts have not been explored. To bridge this gap, this paper conducts the first in-depth study to understand and detect PeerSpin in the npm ecosystem. First, by systematically analyzing the npm dependency resolution, we identify the root cause of PeerSpin and characterize two peer dependency patterns to guide detection. Second, we propose a novel technique called Node-Replacement-Conflict based PeerSpin Detection, which leverages the state of the directory tree during dependency resolution to achieve accurate and efficient PeerSpin detection. Based on this technique, we developed a tool called PeerChecker to detect PeerSpin. Finally, we apply PeerChecker to the entire NPM ecosystem and find that 5,662 packages, totaling 72,968 versions, suffer from PeerSpin. Up until now, we confirmed 28 real PeerSpin problems by reporting them to the package maintainer. We also open source all PeerSpin analysis implementations, tools, and data sets to the public to help the community detect PeerSpin issues and enhance the reliability of the npm ecosystem.

cs.SE↗