arXiv subjects

Hui Tang

Publications and source records attributed to Hui Tang.

At least 19 recordsLinked to original sources

arXiv2026

VCC-DSA: A Novel Vascular Consistency Constrained DSA Imaging Model for Motion Artifact Suppression

Digital Subtraction Angiography (DSA) is a clinically significant imaging technique for diagnosing cerebrovascular disease, as gold-standard. However, the artifacts caused by motion of high-attenuation tissues such as bones, teeth, and catheters, seriously reduce the visibility of blood vessels. This paper presents a novel Vascular Consistency Constrained DSA Imaging Model (VCC-DSA) for robust motion suppression and precise vascular imaging with the following designs: 1) We specially design a Learning-based Subtraction Mapping Paradigm, so that the ill-posed problem of existing learning-based methods can be solved to enhance the stability of the algorithm. 2) Our model effectively develops Residual Dense Blocks and details-shortcut to improve the performance under complex structures, such as moving bones overlapping with blood vessels, and small features, like peripheral vessels. 3) An innovative Vascular Consistency Strategy is proposed to extract intrinsically consistency from the various relative motions in mask-live images, so that spontaneously distils the vascular structure with contrast-agent development and robustly suppress motion artifacts, and also naturally alleviates the high matching requirements of data. 4) We creatively design a Mixup-based Data Self-evolution Strategy for data-intra self-enhancement in training loop, so that the training data gains dynamically optimized to promote model better learning the vascular features, and excluding the irrelevant structures in live/mask image and even the inevitable-artifacts/fake-structure in label. Prospectively, to further evaluate practical value, an actual general anesthesia animal experiment is specially conducted, besides the assessment on human clinical data. Compared with other method, our model improves the PSNR and SSIM by 73.4% and 8.56%, respectively.

eess.IV↗

arXiv2026

MBD: A Model-Based Debiasing Framework Across User, Content, and Model Dimensions

Modern recommendation systems rank candidates by aggregating multiple behavioral signals through a value model. However, many commonly used signals are inherently affected by heterogeneous biases. For example, watch time naturally favors long-form content, loop rate favors short - form content, and comment probability favors videos over images. Such biases introduce two critical issues: (1) value model scores may be systematically misaligned with users' relative preferences - for instance, a seemingly low absolute like probability may represent exceptionally strong interest for a user who rarely engages; and (2) changes in value modeling rules can trigger abrupt and undesirable ecosystem shifts. In this work, we ask a fundamental question: can biased behavioral signals be systematically transformed into unbiased signals, under a user - defined notion of ``unbiasedness'', that are both personalized and adaptive? We propose a general, model-based debiasing (MBD) framework that addresses this challenge by augmenting it with distributional modeling. By conditioning on a flexible subset of features (partial feature set), we explicitly estimate the contextual mean and variance of the engagement distribution for arbitrary cohorts (e.g., specific video lengths or user regions) directly alongside the main prediction. This integration allows the framework to convert biased raw signals into unbiased representations, enabling the construction of higher-level, calibrated signals (such as percentiles or z - scores) suitable for the value model. Importantly, the definition of unbiasedness is flexible and controllable, allowing the system to adapt to different personalization objectives and modeling preferences. Crucially, this is implemented as a lightweight, built-in branch of the existing MTML ranking model, requiring no separate serving infrastructure.

cs.LG↗

arXiv2026

Forgetting-Resistant and Lesion-Aware Source-Free Domain Adaptive Fundus Image Analysis with Vision-Language Model

Source-free domain adaptation (SFDA) aims to adapt a model trained in the source domain to perform well in the target domain, with only unlabeled target domain data and the source model. Taking into account that conventional SFDA methods are inevitably error-prone under domain shift, recently greater attention has been directed to SFDA assisted with off-the-shelf foundation models, e.g., vision-language (ViL) models. However, existing works of leveraging ViL models for SFDA confront two issues: (i) Although mutual information is exploited to consider the joint distribution between the predictions of ViL model and the target model, we argue that the forgetting of some superior predictions of the target model still occurs, as indicated by the decline of the accuracies of certain classes during adaptation; (ii) Prior research disregards the rich, fine-grained knowledge embedded in the ViL model, which offers detailed grounding for fundus image diagnosis. In this paper, we introduce a novel forgetting-resistant and lesion-aware (FRLA) method for SFDA of fundus image diagnosis with ViL model. Specifically, a forgetting-resistant adaptation module explicitly preserves the confident predictions of the target model, and a lesion-aware adaptation module yields patch-wise predictions from ViL model and employs them to help the target model be aware of the lesion areas and leverage the ViL model's fine-grained knowledge. Extensive experiments show that our method not only significantly outperforms the vision-language model, but also achieves consistent improvements over the state-of-the-art methods. Our code will be released.

cs.CV↗

arXiv2026

Quantum reinforcement learning-based active flow control

Active flow control remains a significant challenge due to the high-dimensional, nonlinear nature of fluid dynamics. Quantum machine learning may prove effective in addressing these issues, given that quantum computing possesses superiority over traditional computing in some extend. Thus, this study developed a quantum reinforcement learning (QRL) based active flow control framework, integrating variational quantum circuits (VQCs) with the proximal policy optimization (PPO) algorithm to learn a real time controller. Firstly, we tested the QRL in a CartPole problem. The QRL shows parameter efficiency and enhanced learning capability, indicating VQC acts as promising candidates for advancing RL, particularly in scenarios requiring both computational efficiency and robust performance. The active control of flow past a square circular cylinder at a Reynolds number of 100 was tested via QRL. Our hybrid architecture encodes high-dimensional flow states into a quantum policy network, which generates continuous blowing/suction actions on the cylinder surface, and thus suppress the vortex shedding to achieve drag reduction. Numerical simulations demonstrate the QRL successfully reduces the mean drag and attenuates lift oscillations. Flow field analysis confirms that QRL control effectively suppresses large-scale vortex shedding, leading to a narrower wake compared to the uncontrolled baseline. These results validate the potential of quantum-enhanced learning for tackling complex fluid dynamics problems. The proposed QRL framework establishes a promising blueprint for quantum-AI accelerated solutions in aerospace design, energy-efficient turbomachinery, and other applications involving sophisticated fluid-structure interactions.

physics.flu-dyn↗

arXiv2025

Structure of the mean-field yrast spectrum of a two-component Bose gas in a ring: role of interaction asymmetry

The mean-field yrast spectrum of an SU(2)-symmetric two-component Bose gas confined to a ring geometry is known to exhibit an intricate nonanalytic structure that is absent in single-component systems. In particular, due to the interplay between the species concentration and the atomic interactions, a sequence of plane-wave states can emerge as yrast states at fractional values of the angular momentum per particle. This behavior stands in sharp contrast to the single-component case, where plane-wave states occur only at integer angular momenta. In this paper, we investigate how the structure of the yrast spectrum in a two-component Bose gas is modified by interaction asymmetry. By numerically solving the coupled Gross-Pitaevskii equations for propagating soliton states, we compute the mean-field yrast spectrum and, in particular, determine the critical curves associated with the emergence of various plane-wave yrast states. We find that both the behavior of these critical curves and the mechanisms by which plane-wave yrast states arise depend sensitively on the relative strengths of the inter- and intra-component interactions. When the intra-component interaction is weaker, the plane-wave yrast states replace soliton states through a continuous evolution, as in the SU(2)-symmetric case, although the conditions for their existence become more restrictive. In contrast, when the intra-component interaction is stronger, plane-wave yrast states may emerge by overtaking soliton states via branch crossings, and their stability is significantly enhanced. Our results have important implications for the existence and stability of persistent currents in asymmetric, two-component Bose gases.

cond-mat.quant-gas↗

arXiv2025

A Specialized Large Language Model for Clinical Reasoning and Diagnosis in Rare Diseases

Rare diseases affect hundreds of millions worldwide, yet diagnosis often spans years. Convectional pipelines decouple noisy evidence extraction from downstream inferential diagnosis, and general/medical large language models (LLMs) face scarce real world electronic health records (EHRs), stale domain knowledge, and hallucinations. We assemble a large, domain specialized clinical corpus and a clinician validated reasoning set, and develop RareSeek R1 via staged instruction tuning, chain of thought learning, and graph grounded retrieval. Across multicenter EHR narratives and public benchmarks, RareSeek R1 attains state of the art accuracy, robust generalization, and stability under noisy or overlapping phenotypes. Augmented retrieval yields the largest gains when narratives pair with prioritized variants by resolving ambiguity and aligning candidates to mechanisms. Human studies show performance on par with experienced physicians and consistent gains in assistive use. Notably, transparent reasoning highlights decisive non phenotypic evidence (median 23.1%, such as imaging, interventions, functional tests) underpinning many correct diagnoses. This work advances a narrative first, knowledge integrated reasoning paradigm that shortens the diagnostic odyssey and enables auditable, clinically translatable decision support.

cs.CL↗

arXiv2025

Grounded by Experience: Generative Healthcare Prediction Augmented with Hierarchical Agentic Retrieval

Accurate healthcare prediction is critical for improving patient outcomes and reducing operational costs. Bolstered by growing reasoning capabilities, large language models (LLMs) offer a promising path to enhance healthcare predictions by drawing on their rich parametric knowledge. However, LLMs are prone to factual inaccuracies due to limitations in the reliability and coverage of their embedded knowledge. While retrieval-augmented generation (RAG) frameworks, such as GraphRAG and its variants, have been proposed to mitigate these issues by incorporating external knowledge, they face two key challenges in the healthcare scenario: (1) identifying the clinical necessity to activate the retrieval mechanism, and (2) achieving synergy between the retriever and the generator to craft contextually appropriate retrievals. To address these challenges, we propose GHAR, a \underline{g}enerative \underline{h}ierarchical \underline{a}gentic \underline{R}AG framework that simultaneously resolves when to retrieve and how to optimize the collaboration between submodules in healthcare. Specifically, for the first challenge, we design a dual-agent architecture comprising Agent-Top and Agent-Low. Agent-Top acts as the primary physician, iteratively deciding whether to rely on parametric knowledge or to initiate retrieval, while Agent-Low acts as the consulting service, summarising all task-relevant knowledge once retrieval was triggered. To tackle the second challenge, we innovatively unify the optimization of both agents within a formal Markov Decision Process, designing diverse rewards to align their shared goal of accurate prediction while preserving their distinct roles. Extensive experiments on three benchmark datasets across three popular tasks demonstrate our superiority over state-of-the-art baselines, highlighting the potential of hierarchical agentic RAG in advancing healthcare systems.

cs.AI↗

arXiv2025

Advancing resistivity-chargeability modeling for complex subsurface characterization using machine learning and deep learning

Subsurface lithological heterogeneity presents challenges for traditional geophysical methods, particularly in resolving nonlinear electrical resistivity and induced polarization (IP) relationships. This study introduces a data-driven machine learning and deep learning (ML/DL) framework for predicting 2D IP chargeability models from resistivity, depth, and station distance, reducing reliance on field IP surveys. The framework integrates ensemble regressors with a one-dimensional convolutional neural network (1D CNN) enhanced by global average pooling. Among the tested models, CatBoost achieved the highest prediction accuracy (R^2 = 0.942 training, 0.945 testing), closely followed by random forest, while the stacked ML/DL ensemble further improved performance, particularly for complex resistivity-IP behaviors. Overall accuracy ranged from R^2 = 0.882 to 0.947 with RMSE < 0.04. Integration with k-means clustering enhanced lithological discrimination, effectively delineating sandy silt, silty sand, and weathered granite influenced by saturation, clay content, and fracturing. This scalable approach provides a rapid solution for subsurface modeling in exploration, geotechnical, and environmental applications.

physics.geo-ph↗

arXiv2025

4D Virtual Imaging Platform for Dynamic Joint Assessment via Uni-Plane X-ray and 2D-3D Registration

Conventional computed tomography (CT) lacks the ability to capture dynamic, weight-bearing joint motion. Functional evaluation, particularly after surgical intervention, requires four-dimensional (4D) imaging, but current methods are limited by excessive radiation exposure or incomplete spatial information from 2D techniques. We propose an integrated 4D joint analysis platform that combines: (1) a dual robotic arm cone-beam CT (CBCT) system with a programmable, gantry-free trajectory optimized for upright scanning; (2) a hybrid imaging pipeline that fuses static 3D CBCT with dynamic 2D X-rays using deep learning-based preprocessing, 3D-2D projection, and iterative optimization; and (3) a clinically validated framework for quantitative kinematic assessment. In simulation studies, the method achieved sub-voxel accuracy (0.235 mm) with a 99.18 percent success rate, outperforming conventional and state-of-the-art registration approaches. Clinical evaluation further demonstrated accurate quantification of tibial plateau motion and medial-lateral variance in post-total knee arthroplasty (TKA) patients. This 4D CBCT platform enables fast, accurate, and low-dose dynamic joint imaging, offering new opportunities for biomechanical research, precision diagnostics, and personalized orthopedic care.

cs.CV↗

arXiv2025

Anti-Sisyphus driving in a matter-wave swing

Dilute-gas Bose-Einstein condensates are an exceptionally versatile testbed for the investigation of physics phenomenon especially the well-known classical system. Here we use a degenerate Bose gas of sodium atoms confined in an optical dipole trap to simulate the matter-wave on the swing. Under the driving of Anti-Sisyphus process, the swing was excited successfully. Moreover, the spin echo like behavior and collective-mode excitation appear during the oscillation of matter-wave swing, manifesting the quantum nature of the system beyond its classical counterpart. Our work lays the foundation for matter-wave on the swing and more generally points to a future of practical applications for the motional quantum states linked with quantum information science.

cond-mat.quant-gas↗

arXiv2025

Microgravity-assisted off-axis spin vortex in a $^{87}$Rb dipolar spinor Bose-Einstein condensate

The generation of the ground state of a spin vortex in a $^{87}$Rb Bose-Einstein condensate with the assistance of an optical plug has been studied. However, gravity is everywhere, and this potential linear dependence on the spatial position will destroy the axisymmetric structure of the system with the optical plug. In this case, the question of whether the spin vortex ground state still exists remains unresolved. The present study aims to explore the impact of microgravity on the formation of the spin vortex state with the assistance of an optical plug. To this end, a simple model has been employed to provide a comprehensive understanding of the phenomenon. The Gross-Pitaevskii equations are solved by setting the optical plug intensity, adjusting the optical plug width, and adjusting the microgravity strength. This process results in the phase diagram for the single-mode state and spin vortex state. Under microgravity situations, we observe an off-axis structure of the spin vortex state. Our calculations offer a reliable approach to generating spin vortex states in a microgravity environment.

cond-mat.quant-gas↗

arXiv2025

Generalized Onsager reciprocal relations of charge and spin transport

In spin-orbit-coupled systems the charge and spin transport are generally coupled to each other, namely a charge current will induce a spin current and vice versa. In the presence of time-reversal symmetry $T$, the cross-coupling transport coefficients describing how one process affects the other are constrained by the famous Onsager reciprocal relations. In this paper, we generalize the Onsager reciprocal relations of charge and spin transport to systems that break the time-reversal symmetry but preserve a combined symmetry of $T$ and some other symmetry operation $O$. We show that the symmetry or antisymmetry of the cross-coupling transport coefficients remains in place provided that the operator $O$ meets certain conditions. Among many candidate systems where our generalized Onsager relations apply, we focus on a conceptually simple and experimentally realized model in cold atomic systems for explicit demonstration and use these relations to predict highly non-trivial transport phenomena that can be readily verified experimentally.

cond-mat.quant-gas↗

arXiv2025

LT-PINN: Lagrangian Topology-conscious Physics-informed Neural Network for Boundary-focused Engineering Optimization

Physics-informed neural networks (PINNs) have emerged as a powerful meshless tool for topology optimization, capable of simultaneously determining optimal topologies and physical solutions. However, conventional PINNs rely on density-based topology descriptions, which necessitate manual interpolation and limit their applicability to complex geometries. To address this, we propose Lagrangian topology-conscious PINNs (LT-PINNs), a novel framework for boundary-focused engineering optimization. By parameterizing the control variables of topology boundary curves as learnable parameters, LT-PINNs eliminate the need for manual interpolation and enable precise boundary determination. We further introduce specialized boundary condition loss function and topology loss function to ensure sharp and accurate boundary representations, even for intricate topologies. The accuracy and robustness of LT-PINNs are validated via two types of partial differential equations (PDEs), including elastic equation with Dirichlet boundary conditions and Laplace's equation with Neumann boundary conditions. Furthermore, we demonstrate effectiveness of LT-PINNs on more complex time-dependent and time-independent flow problems without relying on measurement data, and showcase their engineering application potential in flow velocity rearrangement, transforming a uniform upstream velocity into a sine-shaped downstream profile. The results demonstrate (1) LT-PINNs achieve substantial reductions in relative L2 errors compared with the state-of-art density topology-oriented PINNs (DT-PINNs), (2) LT-PINNs can handle arbitrary boundary conditions, making them suitable for a wide range of PDEs, and (3) LT-PINNs can infer clear topology boundaries without manual interpolation, especially for complex topologies.

cs.LG↗

arXiv2025

Diffmv: A Unified Diffusion Framework for Healthcare Predictions with Random Missing Views and View Laziness

Advanced healthcare predictions offer significant improvements in patient outcomes by leveraging predictive analytics. Existing works primarily utilize various views of Electronic Health Record (EHR) data, such as diagnoses, lab tests, or clinical notes, for model training. These methods typically assume the availability of complete EHR views and that the designed model could fully leverage the potential of each view. However, in practice, random missing views and view laziness present two significant challenges that hinder further improvements in multi-view utilization. To address these challenges, we introduce Diffmv, an innovative diffusion-based generative framework designed to advance the exploitation of multiple views of EHR data. Specifically, to address random missing views, we integrate various views of EHR data into a unified diffusion-denoising framework, enriched with diverse contextual conditions to facilitate progressive alignment and view transformation. To mitigate view laziness, we propose a novel reweighting strategy that assesses the relative advantages of each view, promoting a balanced utilization of various data views within the model. Our proposed strategy achieves superior performance across multiple health prediction tasks derived from three popular datasets, including multi-view and multi-modality scenarios.

cs.LG↗

arXiv2025

Leveraging Segment Anything Model for Source-Free Domain Adaptation via Dual Feature Guided Auto-Prompting

Source-free domain adaptation (SFDA) for segmentation aims at adapting a model trained in the source domain to perform well in the target domain with only the source model and unlabeled target data. Inspired by the recent success of Segment Anything Model (SAM) which exhibits the generality of segmenting images of various modalities and in different domains given human-annotated prompts like bounding boxes or points, we for the first time explore the potentials of Segment Anything Model for SFDA via automatedly finding an accurate bounding box prompt. We find that the bounding boxes directly generated with existing SFDA approaches are defective due to the domain gap. To tackle this issue, we propose a novel Dual Feature Guided (DFG) auto-prompting approach to search for the box prompt. Specifically, the source model is first trained in a feature aggregation phase, which not only preliminarily adapts the source model to the target domain but also builds a feature distribution well-prepared for box prompt search. In the second phase, based on two feature distribution observations, we gradually expand the box prompt with the guidance of the target model feature and the SAM feature to handle the class-wise clustered target features and the class-wise dispersed target features, respectively. To remove the potentially enlarged false positive regions caused by the over-confident prediction of the target model, the refined pseudo-labels produced by SAM are further postprocessed based on connectivity analysis. Experiments on 3D and 2D datasets indicate that our approach yields superior performance compared to conventional methods. Code is available at https://github.com/xmed-lab/DFG.

cs.CV↗

arXiv2025

Concept-Based Unsupervised Domain Adaptation

Concept Bottleneck Models (CBMs) enhance interpretability by explaining predictions through human-understandable concepts but typically assume that training and test data share the same distribution. This assumption often fails under domain shifts, leading to degraded performance and poor generalization. To address these limitations and improve the robustness of CBMs, we propose the Concept-based Unsupervised Domain Adaptation (CUDA) framework. CUDA is designed to: (1) align concept representations across domains using adversarial training, (2) introduce a relaxation threshold to allow minor domain-specific differences in concept distributions, thereby preventing performance drop due to over-constraints of these distributions, (3) infer concepts directly in the target domain without requiring labeled concept data, enabling CBMs to adapt to diverse domains, and (4) integrate concept learning into conventional domain adaptation (DA) with theoretical guarantees, improving interpretability and establishing new benchmarks for DA. Experiments demonstrate that our approach significantly outperforms the state-of-the-art CBM and DA methods on real-world datasets.

cs.LG↗

arXiv2025

DDaTR: Dynamic Difference-aware Temporal Residual Network for Longitudinal Radiology Report Generation

Radiology Report Generation (RRG) automates the creation of radiology reports from medical imaging, enhancing the efficiency of the reporting process. Longitudinal Radiology Report Generation (LRRG) extends RRG by incorporating the ability to compare current and prior exams, facilitating the tracking of temporal changes in clinical findings. Existing LRRG approaches only extract features from prior and current images using a visual pre-trained encoder, which are then concatenated to generate the final report. However, these methods struggle to effectively capture both spatial and temporal correlations during the feature extraction process. Consequently, the extracted features inadequately capture the information of difference across exams and thus underrepresent the expected progressions, leading to sub-optimal performance in LRRG. To address this, we develop a novel dynamic difference-aware temporal residual network (DDaTR). In DDaTR, we introduce two modules at each stage of the visual encoder to capture multi-level spatial correlations. The Dynamic Feature Alignment Module (DFAM) is designed to align prior features across modalities for the integrity of prior clinical information. Prompted by the enriched prior features, the dynamic difference-aware module (DDAM) captures favorable difference information by identifying relationships across exams. Furthermore, our DDaTR employs the dynamic residual network to unidirectionally transmit longitudinal information, effectively modelling temporal correlations. Extensive experiments demonstrated superior performance over existing methods on three benchmarks, proving its efficacy in both RRG and LRRG tasks.

cs.CV↗

arXiv2025

Efficient Masked Image Compression with Position-Indexed Self-Attention

In recent years, image compression for high-level vision tasks has attracted considerable attention from researchers. Given that object information in images plays a far more crucial role in downstream tasks than background information, some studies have proposed semantically structuring the bitstream to selectively transmit and reconstruct only the information required by these tasks. However, such methods structure the bitstream after encoding, meaning that the coding process still relies on the entire image, even though much of the encoded information will not be transmitted. This leads to redundant computations. Traditional image compression methods require a two-dimensional image as input, and even if the unimportant regions of the image are set to zero by applying a semantic mask, these regions still participate in subsequent computations as part of the image. To address such limitations, we propose an image compression method based on a position-indexed self-attention mechanism that encodes and decodes only the visible parts of the masked image. Compared to existing semantic-structured compression methods, our approach can significantly reduce computational costs.

cs.CV↗