arXiv subjects

Yong Xia

Publications and source records attributed to Yong Xia.

At least 19 recordsLinked to original sources

arXiv2026

A Line-Search-Free Coordinate Proximal Predictor-Corrector Method for Monotone Absolute Value Equations

We consider the absolute value equation (AVE) $Ax-|x|=b$ under residual monotonicity. We characterize this property through the symmetric part of the coefficient matrix, thereby allowing nonsymmetry, and propose a coordinate proximal predictor-corrector (CPPC) method based on an AVE-specific forward-proximal decomposition. An exact scalar proximal update on the largest proximal-residual coordinate generates a predictor point, while a positive-alignment identity certifies the ensuing full-residual separating-hyperplane correction without backtracking. With the current matrix product cached, each iteration requires one new full matrix-vector product. For a nonempty solution set, we prove Fej\'er monotonicity, whole-sequence convergence, and an $O(K^{-1/2})$ best-iterate residual bound. A positive monotonicity margin further ensures unique solvability for every right-hand side and global linear convergence. Numerical results identify regimes in which the reduced per-iteration work yields shorter solution times.

math.OC↗

arXiv2026

Volumetric Radiology AI in the Era of Multimodal Large Language Models

Advances in multimodal large language models (MLLMs) are extending radiological artificial intelligence (AI) beyond task-specific image analysis toward multimodal understanding and reasoning. Volumetric radiology, however, presents a fundamental representational mismatch: clinical interpretation often requires full-volume spatial context and acquisition-dependent quantitative information, whereas current MLLMs are commonly conditioned on selected two-dimensional (2D) images, compressed visual representations, or report-derived text. Reliable volumetric radiology AI therefore requires representations that preserve task-relevant three-dimensional (3D) information and systems that can access, verify, and integrate this information across clinical workflows. In this Review, we examine more than 200 publications through July 2026. We organize the literature around volumetric representation and multimodal understanding at the model level, agentic orchestration at the system level, and their links to clinical applications and evaluation. We review volumetric foundation models, language alignment and compression strategies, and agentic systems that extend MLLMs through planning, tools, memory, and workflow interaction. We distinguish settings in which selected 2D views or report-mediated reasoning may suffice from those that warrant native volumetric modeling. We also introduce a Claim-Design-Validation framework to assess whether technical, workflow, and clinical claims are matched by appropriate design and validation. Across the literature, native volumetric modeling and agentic capabilities depend on the spatial, quantitative, contextual, and workflow requirements of the intended task. Clinical credibility requires faithful volumetric representation, traceable system behavior, claim-aligned validation, and clearly defined human oversight in realistic workflows.

cs.AI↗

arXiv2026

Learning Where and What to Lift for Bi-planar X-ray-to-CT Reconstruction

X-ray imaging can be approximately modeled as the projection of an underlying volumetric attenuation field, with each measurement recording the accumulated attenuation along a corresponding ray path. Reconstructing a CT volume from only a few X-ray views is therefore severely ill-posed, as the projections collapse depth information and leave 3D locations of anatomical regions and their corresponding intensity distributions highly entangled and ambiguous. We observe that once the spatial organization of anatomical regions is established, estimating their CT intensities becomes substantially more tractable. Motivated by this, we propose LiftXR, an interleaved, geometry-guided framework that explicitly incorporates spatial layout recovery into CT reconstruction. Specifically, a layout lifter first generates a 3D anatomical layout from bi-planar X-rays, providing spatial guidance for an intensity renderer to reconstruct a CT volume. An anatomical parser then performs volumetric perception on the reconstruction, exploiting its spatially resolved boundary and intensity cues to recover a refined anatomical layout. This transition from projection-conditioned layout generation to reconstruction-conditioned anatomical perception allows the parsed layout to provide feedback for region-specific intensity calibration. Extensive experiments on two public datasets demonstrate that LiftXR consistently outperforms recent X-ray-to-CT reconstruction methods, establishing a new state of the art. Moreover, the reconstructed CT achieves superior performance in external downstream segmentation, indicating improved anatomical fidelity. Code will be released.

cs.CV↗

arXiv2026

Super-Generalist: Towards Comprehensive and Accurate Medical Image Understanding via Generalist-Specialist Synergy

Medical images require comprehensive and accurate interpretation to support the diagnosis of diverse clincial conditions. Recent vision-language generalist models offer broad task coverage and promising zero-shot capabilities, yet often lack fine-grained anatomical and lesion awareness for reliable diagnosis and spatial interpretability. In contrast, supervised specialist models achieve strong performance on specific tasks but typically lack generalization across diseases and anatomies. In this work, we present SuG, a Super-Generalist framework that unifies generalist vision-language learning with specialist objectives, enabling both broad generalization and specialist-level diagnostic capability. We perform specialist-enhanced vision-language alignment in SuG by incorporating spatial priors from multiple segmentation experts, including anatomy, class-specific lesion and class-agnostic lesion segmentors that captures lesions beyond anatomies annotated during training. To improve lesion grounding capability, we leverage lesion masks as spatial priors to calibrate text-conditioned visual attention, encouraging disease-related semantics to focus on clinically relevant regions. We evaluate SuG on extensive chest and abdominal CT benchmarks, including CT-RATE, Merlin, MedVL-CT69K, and several in-house tumor datasets. SuG achieves state-of-the-art performance across a wide range of disease diagnosis tasks and surpasses specialist models on several critical tumor diagnosis benchmarks. Furthermore, SuG demonstrates strong lesion grounding capability, including robust generalization to lesion types lacking class-specific supervision.

cs.CV↗

arXiv2026

The Continuous Relaxation of Sparse PCA is NP-hard

Maximizing a symmetric quadratic form under simultaneous L1 norm inequality and L2 norm equality constraints is a standard and widely used continuous relaxation for Sparse Principal Component Analysis (SPCA). This paper settles the computational complexity of this continuous formulation by proving it is NP-hard. Furthermore, the variant with both L1 and L2 norm inequalities is also shown to be NP-hard.

math.OC↗

arXiv2026

Global optimization of quadratic root-difference minimization under elliptic annulus constraints

This paper studies the nonconvex quadratic root-difference minimization under elliptic annulus constraints {\rm (QR)}. We first establish the Annulus Brickman theorem and equivalently reformulate {\rm (QR)} as a 2-dimensional convex problem {\rm (HP)} with hidden variables. We employ the Frank-Wolfe algorithm to globally solve {\rm (HP)}. A key finding is that the solutions of the Frank-Wolfe subproblems, which are traditionally viewed as mere auxiliary updates, are proven to be $O(1/\sqrt{k})$-approximate solutions of the original problem {\rm (QR)}. This transforms an algorithmic by-product into the primary output and completely bypasses the need to solve the computationally expensive quadratic system required for solution recovery. Leveraging this recovery-free property, we develop the efficient Iterative Minimum Generalized Eigenpair (IMGE) algorithm for globally solving {\rm (QR)}. Numerical experiments confirm that IMGE converges rapidly and significantly outperforms conventional methods, especially for large-scale problems.

math.OC↗

arXiv2026

InViC: Intent-aware Visual Cues for Medical Visual Question Answering

Medical visual question answering (Med-VQA) aims to answer clinically relevant questions grounded in medical images. However, existing multimodal large language models (MLLMs) often exhibit shortcut answering, producing plausible responses by exploiting language priors or dataset biases while insufficiently attending to visual evidence. This behavior undermines clinical reliability, especially when subtle imaging findings are decisive. We propose a lightweight plug-in framework, termed Intent-aware Visual Cues (InViC), to explicitly enhance image-based answer generation in medical VQA. InViC introduces a Cue Tokens Extraction (CTE) module that distills dense visual tokens into a compact set of K question-conditioned cue tokens, which serve as structured visual intermediaries injected into the LLM decoder to promote intent-aligned visual evidence. To discourage bypassing of visual information, we further design a two-stage fine-tuning strategy with a cue-bottleneck attention mask. In Stage I, we employ an attention mask to block the LLM's direct view of raw visual features, thereby funneling all visual evidence through the cue pathway. In Stage II, standard causal attention is restored to train the LLM to jointly exploit the visual and cue tokens. We evaluate InViC on three public Med-VQA benchmarks (VQA-RAD, SLAKE, and ImageCLEF VQA-Med 2019) across multiple representative MLLMs. InViC consistently improves over zero-shot inference and standard LoRA fine-tuning, demonstrating that intent-aware visual cues with bottlenecked training is a practical and effective strategy for improving trustworthy Med-VQA.

cs.CV↗

arXiv2026

Upper Generalization Bounds for Neural Oscillators

Neural oscillators that originate from second-order ordinary differential equations (ODEs) have shown competitive performance in learning mappings between dynamic loads and responses of complex nonlinear structural systems. Despite this empirical success, theoretically quantifying the generalization capacities of their neural network architectures remains undeveloped. In this study, the neural oscillator consisting of a second-order ODE followed by a multilayer perceptron (MLP) is considered. Its upper probably approximately correct (PAC) generalization bound for approximating causal and uniformly continuous operators between continuous temporal function spaces and that for approximating the uniformly asymptotically incrementally stable second-order dynamical systems are derived by leveraging the Rademacher complexity framework. These bounds are further extended to the squared Wasserstein-1 distances between the probability measures of quantities of interest calculated from target causal operators and the corresponding learned neural oscillators. The theoretical results show that the estimation errors grow polynomially with respect to both MLP sizes and the time length, thereby avoiding the curse of parametric complexity. Furthermore, the derived error bounds demonstrate that constraining the Lipschitz constants of the MLPs via loss function regularization can improve the generalization ability of the neural oscillator. Numerical studies considering a Bouc-Wen nonlinear system under stochastic seismic excitation validates the theoretically predicted power laws of the estimation errors with respect to the sample size and time length, and confirms the effectiveness of constraining MLPs' matrix and vector norms in enhancing the performance of the neural oscillator under limited training data.

cs.LG↗

arXiv2026

Rethinking the Efficiency and Effectiveness of Reinforcement Learning for Radiology Report Generation

Radiologists highly desire fully automated AI for radiology report generation (R2G), yet existing approaches fall short in clinical utility. Reinforcement learning (RL) holds potential to address these shortcomings, but its adoption in this task remains underexplored. In this paper, we revisit RL in terms of data efficiency and optimization effectiveness for R2G tasks. First, we explore the impact of data quantity and quality on the performance of RL in medical contexts, revealing that data quality plays a more critical role than quantity. To this end, we propose a diagnostic diversity-based data sampling strategy that enables comparable performance with fewer samples. Second, we observe that the majority of tokens in radiology reports are template-like and diagnostically uninformative, whereas the low frequency of clinically critical tokens heightens the risk of being overlooked during optimization. To tackle this, we introduce Diagnostic Token-weighted Policy Optimization (DiTPO), which directly optimizes for clinical accuracy by using a diagnostic F1 score as the reward signal. Unlike standard RL approaches that treat all tokens equally, DiTPO explicitly models the varying importance of different tokens through rule- or gradient-based mechanisms to prioritize clinically relevant content. Extensive experiments on the MIMIC-CXR, IU-Xray, and CheXpert Plus datasets demonstrate that our framework achieves state-of-the-art (SOTA) performance while requiring substantially fewer training samples in RL. Notably, on MIMIC-CXR, our framework attains an F1 score of 0.516 using only 20% of the RL training samples.

cs.CV↗

arXiv2026

Subgradient Gliding Method for Nonsmooth Convex Optimization

We identify and analyze a fundamental limitation of the classical projected subgradient method in nonsmooth convex optimization: the inevitable failure caused by the absence of valid subgradients at boundary points. We show that, under standard step sizes for both convex and strongly convex objectives, the method can fail after a single iteration with probability arbitrarily close to one, even on simple problem instances. To overcome this limitation, we propose a novel alternative termed the \textit{subgradient gliding method}, which remains well defined without boundary subgradients and avoids premature termination. Beyond resolving this foundational issue, the proposed framework encompasses the classical projected subgradient method as a special case and substantially enlarges its admissible step-size design space, providing greater flexibility for algorithmic design. We establish optimal ergodic convergence rates, $\mathcal{O}(1/\sqrt{t})$ for convex problems and $\mathcal{O}(1/t)$ for strongly convex problems, and further extend the framework to stochastic settings. Notably, our analysis does not rely on global Lipschitz continuity of the objective function, requiring only mild control on subgradient growth. Numerical experiments demonstrate that, in scenarios where the classical projected subgradient method fails completely, the proposed method converges reliably with a $100\%$ success rate and achieves orders-of-magnitude improvements in accuracy and convergence speed. These results substantially expand the scope of subgradient-based optimization methods to non-Lipschitz nonsmooth convex problems.

math.OC↗

arXiv2026

SegRap2025: A Benchmark of Gross Tumor Volume and Lymph Node Clinical Target Volume Segmentation for Radiotherapy Planning of Nasopharyngeal Carcinoma

Accurate delineation of Gross Tumor Volume (GTV), Lymph Node Clinical Target Volume (LN CTV), and Organ-at-Risk (OAR) from Computed Tomography (CT) scans is essential for precise radiotherapy planning in Nasopharyngeal Carcinoma (NPC). Building upon SegRap2023, which focused on OAR and GTV segmentation using single-center paired non-contrast CT (ncCT) and contrast-enhanced CT (ceCT) scans, the SegRap2025 challenge aims to enhance the generalizability and robustness of segmentation models across imaging centers and modalities. SegRap2025 comprises two tasks: Task01 addresses GTV segmentation using paired CT from the SegRap2023 dataset, with an additional external testing set to evaluate cross-center generalization, and Task02 focuses on LN CTV segmentation using multi-center training data and an unseen external testing set, where each case contains paired CT scans or a single modality, emphasizing both cross-center and cross-modality robustness. This paper presents the challenge setup and provides a comprehensive analysis of the solutions submitted by ten participating teams. For GTV segmentation task, the top-performing models achieved average Dice Similarity Coefficient (DSC) of 74.61% and 56.79% on the internal and external testing cohorts, respectively. For LN CTV segmentation task, the highest average DSC values reached 60.24%, 60.50%, and 57.23% on paired CT, ceCT-only, and ncCT-only subsets, respectively. SegRap2025 establishes a large-scale multi-center, multi-modality benchmark for evaluating the generalization and robustness in radiotherapy target segmentation, providing valuable insights toward clinically applicable automated radiotherapy planning systems. The benchmark is available at: https://hilab-git.github.io/SegRap2025_Challenge.

eess.IV↗

arXiv2026

V-Loop: Visual Logical Loop Verification for Hallucination Detection in Medical Visual Question Answering

Multimodal Large Language Models (MLLMs) have shown remarkable capability in assisting disease diagnosis in medical visual question answering (VQA). However, their outputs remain vulnerable to hallucinations (i.e., responses that contradict visual facts), posing significant risks in high-stakes medical scenarios. Recent introspective detection methods, particularly uncertainty-based approaches, offer computational efficiency but are fundamentally indirect, as they estimate predictive uncertainty for an image-question pair rather than verifying the factual correctness of a specific answer. To address this limitation, we propose Visual Logical Loop Verification (V-Loop), a training-free and plug-and-play framework for hallucination detection in medical VQA. V-Loop introduces a bidirectional reasoning process that forms a visually grounded logical loop to verify factual correctness. Given an input, the MLLM produces an answer for the primary input pair. V-Loop extracts semantic units from the primary QA pair, generates a verification question by conditioning on the answer unit to re-query the question unit, and enforces visual attention consistency to ensure answering both primary question and verification question rely on the same image evidence. If the verification answer matches the expected semantic content, the logical loop closes, indicating factual grounding; otherwise, the primary answer is flagged as hallucinated. Extensive experiments on multiple medical VQA benchmarks and MLLMs show that V-Loop consistently outperforms existing introspective methods, remains highly efficient, and further boosts uncertainty-based approaches when used in combination.

cs.CV↗

arXiv2026

PAINT: Pathology-Aware Integrated Next-Scale Transformation for Virtual Immunohistochemistry

Virtual immunohistochemistry (IHC) aims to computationally synthesize molecular staining patterns from routine Hematoxylin and Eosin (H\&E) images, offering a cost-effective and tissue-efficient alternative to traditional physical staining. However, this task is particularly challenging: H\&E morphology provides ambiguous cues about protein expression, and similar tissue structures may correspond to distinct molecular states. Most existing methods focus on direct appearance synthesis to implicitly achieve cross-modal generation, often resulting in semantic inconsistencies due to insufficient structural priors. In this paper, we propose Pathology-Aware Integrated Next-Scale Transformation (PAINT), a visual autoregressive framework that reformulates the synthesis process as a structure-first conditional generation task. Unlike direct image translation, PAINT enforces a causal order by resolving molecular details conditioned on a global structural layout. Central to this approach is the introduction of a Spatial Structural Start Map (3S-Map), which grounds the autoregressive initialization in observed morphology, ensuring deterministic, spatially aligned synthesis. Experiments on the IHC4BC and MIST datasets demonstrate that PAINT outperforms state-of-the-art methods in structural fidelity and clinical downstream tasks, validating the potential of structure-guided autoregressive modeling.

cs.CV↗

arXiv2026

Upper limits on microhertz gravitational waves from supermassive black-hole binaries using PSR J1909-3744 data from the second IPTA data release

We present the results of a search for gravitational waves (GWs) from individual sources using high-cadence observations of PSR J1909$-$3744 obtained during an intensive observing campaign with the International Pulsar Timing Array second data release (IPTA-DR2) between July 2010 and November 2012. The observations, conducted at three different radio frequencies with the Nan\c{c}ay Radio Telescope (NRT) and Parkes Telescope (PKS) and five frequencies with the Green Bank Telescope (GBT), enabled precise corrections for dispersion measure effects and scattering variations. After these corrections, the timing residuals showed an unmodeled periodic noise component with an amplitude of 340 ns. Our analysis yields upper limits on the GW strain from individual sources, constraining it to be below $1.9 \times 10^{-14}$ at 71 nHz and $2.3 \times 10^{-13}$ at 1 \textmu Hz for average sky locations, while for optimal source locations the limits improve to $6.2 \times 10^{-15}$ and $8.9 \times 10^{-14}$ at the same frequencies, respectively. Our new limits are about a factor of 1.52 more stringent than those of Perera et al. based on an earlier EPTA data.

astro-ph.HE↗

arXiv2026

FedBiCross: Personalized One-Shot Federated Learning on Medical Images

Data-free knowledge distillation-based one-shot federated learning (OSFL) trains a model in a single communication round without sharing raw data, making OSFL attractive for privacy-sensitive medical applications. However, existing methods aggregate predictions from all clients to form a global teacher. Under non-IID data, conflicting predictions dilute each other during averaging, yielding less informative soft labels that weaken distillation. We propose FedBiCross, a personalized OSFL framework with three stages: (1) clustering clients by model output similarity to form coherent sub-ensembles, (2) bi-level cross-cluster optimization that learns adaptive weights to selectively leverage beneficial cross-cluster knowledge while suppressing negative transfer, and (3) personalized distillation for client-specific adaptation. Experiments on four medical image datasets demonstrate that FedBiCross consistently outperforms state-of-the-art baselines across different non-IID degrees.

cs.LG↗

arXiv2025

Upper Approximation Bounds for Neural Oscillators

Neural oscillators, originating from second-order ordinary differential equations (ODEs), have demonstrated strong performance in stably learning causal mappings between long-term sequences or continuous temporal functions, as well as in accurately approximating physical systems. However, theoretically quantifying the capacities of their neural network architectures remains a significant challenge. In this study, the neural oscillator consisting of a second-order ODE followed by a multilayer perceptron (MLP) is considered. Its upper approximation bound for approximating causal and uniformly continuous operators between continuous temporal function spaces and that for approximating uniformly asymptotically incrementally stable second-order dynamical systems are derived. The established proof method of the approximation bound for approximating the causal continuous operators can also be directly applied to state-space models consisting of a linear time-continuous complex recurrent neural network followed by an MLP. Theoretical results reveal that the approximation error of the neural oscillator for approximating the second-order dynamical systems scales polynomially with the reciprocals of the widths of two utilized MLPs, thus overcoming the curse of parametric complexity. The convergence rates of two established approximation error bounds are validated through four numerical cases. These results provide a robust theoretical foundation for the effective application of the neural oscillator in science and engineering.

cs.LG↗

arXiv2025

Mini-Extragradient Methods

The Extragradient (EG) method stands as a cornerstone algorithm for solving monotone nonlinear equations but faces two important unresolved challenges: (i) how to select stepsizes without relying on the global Lipschitz constant or expensive line-search procedures, and (ii) how to reduce the two full evaluations of the mapping required per iteration to effectively one, without compromising convergence guarantees or computational efficiency. To address the first challenge, we propose the Greedy Mini-Extragradient (Mini-EG) method, which updates only the coordinate associated with the dominant component of the mapping at each extragradient step. This design capitalizes on componentwise Lipschitz constants that are far easier to estimate than the classical global Lipschitz constant. To further lower computational cost, we introduce a Random Mini-EG variant that replaces full mapping evaluations by sampling only a single coordinate per extragradient step. Although this resolves the second challenge from a theoretical standpoint, its practical efficiency remains limited. To bridge this gap, we develop the Watchdog-Max strategy, motivated by the slow decay of dominant component magnitudes. Instead of evaluating the full mapping, Watchdog-Max identifies and tracks only two coordinates at each extragradient step, dramatically reducing per-iteration cost while retaining strong practical performance. We establish convergence guarantees and rate analyses for all proposed methods. In particular, Greedy Mini-EG achieves enhanced convergence rates that surpass the classical guarantees of the vanilla EG method in several standard application settings. Numerical experiments on regularized decentralized logistic regression and compressed sensing show speedups exceeding $13\times$ compared with the classical EG method on both synthetic and real datasets.

math.OC↗

arXiv2025

MIRROR: Multi-Modal Pathological Self-Supervised Representation Learning via Modality Alignment and Retention

Histopathology and transcriptomics are fundamental modalities in oncology, encapsulating the morphological and molecular aspects of the disease. Multi-modal self-supervised learning has demonstrated remarkable potential in learning pathological representations by integrating diverse data sources. Conventional multi-modal integration methods primarily emphasize modality alignment, while paying insufficient attention to retaining the modality-specific structures. However, unlike conventional scenarios where multi-modal inputs share highly overlapping features, histopathology and transcriptomics exhibit pronounced heterogeneity, offering orthogonal yet complementary insights. Histopathology provides morphological and spatial context, elucidating tissue architecture and cellular topology, whereas transcriptomics delineates molecular signatures through gene expression patterns. This inherent disparity introduces a major challenge in aligning them while maintaining modality-specific fidelity. To address these challenges, we present MIRROR, a novel multi-modal representation learning method designed to foster both modality alignment and retention. MIRROR employs dedicated encoders to extract comprehensive features for each modality, which is further complemented by a modality alignment module to achieve seamless integration between phenotype patterns and molecular profiles. Furthermore, a modality retention module safeguards unique attributes from each modality, while a style clustering module mitigates redundancy and enhances disease-relevant information by modeling and aligning consistent pathological signatures within a clustering space. Extensive evaluations on TCGA cohorts for cancer subtyping and survival analysis highlight MIRROR's superior performance, demonstrating its effectiveness in constructing comprehensive oncological feature representations and benefiting the cancer diagnosis.

cs.CV↗