arXiv subjects

Ping Zhang

Publications and source records attributed to Ping Zhang.

At least 127 records · Page 7Linked to original sources

arXiv2025

Foundation Model in Biomedicine

Foundation models, first introduced in 2021, refer to large-scale pretrained models (e.g., large language models (LLMs) and vision-language models (VLMs)) that learn from extensive unlabeled datasets through unsupervised methods, enabling them to excel in diverse downstream tasks. These models, like GPT, can be adapted to various applications such as question answering and visual understanding, outperforming task-specific AI models and earning their name due to broad applicability across fields. The development of biomedical foundation models marks a significant milestone in the use of artificial intelligence (AI) to understand complex biological phenomena and advance medical research and practice. This survey explores the potential of foundation models in diverse domains within biomedical fields, including computational biology, drug discovery and development, clinical informatics, medical imaging, and public health. The purpose of this survey is to inspire ongoing research in the application of foundation models to health science.

cs.LG↗

arXiv2025

Achieving Fairness Without Harm via Selective Demographic Experts

As machine learning systems become increasingly integrated into human-centered domains such as healthcare, ensuring fairness while maintaining high predictive performance is critical. Existing bias mitigation techniques often impose a trade-off between fairness and accuracy, inadvertently degrading performance for certain demographic groups. In high-stakes domains like clinical diagnosis, such trade-offs are ethically and practically unacceptable. In this study, we propose a fairness-without-harm approach by learning distinct representations for different demographic groups and selectively applying demographic experts consisting of group-specific representations and personalized classifiers through a no-harm constrained selection. We evaluate our approach on three real-world medical datasets -- covering eye disease, skin cancer, and X-ray diagnosis -- as well as two face datasets. Extensive empirical results demonstrate the effectiveness of our approach in achieving fairness without harm.

cs.LG↗

arXiv2025

Overview of CHIP 2025 Shared Task 2: Discharge Medication Recommendation for Metabolic Diseases Based on Chinese Electronic Health Records

Discharge medication recommendation plays a critical role in ensuring treatment continuity, preventing readmission, and improving long-term management for patients with chronic metabolic diseases. This paper present an overview of the CHIP 2025 Shared Task 2 competition, which aimed to develop state-of-the-art approaches for automatically recommending appro-priate discharge medications using real-world Chinese EHR data. For this task, we constructed CDrugRed, a high-quality dataset consisting of 5,894 de-identified hospitalization records from 3,190 patients in China. This task is challenging due to multi-label nature of medication recommendation, het-erogeneous clinical text, and patient-specific variability in treatment plans. A total of 526 teams registered, with 167 and 95 teams submitting valid results to the Phase A and Phase B leaderboards, respectively. The top-performing team achieved the highest overall performance on the final test set, with a Jaccard score of 0.5102, F1 score of 0.6267, demonstrating the potential of advanced large language model (LLM)-based ensemble systems. These re-sults highlight both the promise and remaining challenges of applying LLMs to medication recommendation in Chinese EHRs. The post-evaluation phase remains open at https://tianchi.aliyun.com/competition/entrance/532411/.

cs.CL↗

arXiv2025

An Unusual Dresselhaus Spin-Orbit Contribution of Even Order in Momentum

The spin-orbit (SO) coupling is conventionally known to manifest as \emph{odd} functions of momentum. Here, through both model calculations and symmetry analysis along with the method of invariants, we reveal that, in ordinary semiconductor heterostructures, a \emph{quadratic} Dresselhaus SO term -- inheriting from its bulk crystal form -- emerges via the interband effect, while complying with time-reversal and spatial symmetries. Furthermore, we observe that this unusual SO term gives rise to a range of striking quantum phenomena, including hybridized swirling texture, anisotropic energy dispersion, avoided band crossing, longitudinal \emph{Zitterbewegung}, and opposite spin evolution between different bands in quantum dynamics. These stand in stark contrast to those associated with the usual \emph{linear} SO terms. Our findings uncover a previously overlooked route for exploiting interband effects and open new avenues for spintronic functionalities that leverage unusual SO terms of \emph{even} orders in momentum.

cond-mat.mes-hall↗

arXiv2025

Revisiting semi-supervised learning in the era of foundation models

Semi-supervised learning (SSL) leverages abundant unlabeled data alongside limited labeled data to enhance learning. As vision foundation models (VFMs) increasingly serve as the backbone of vision applications, it remains unclear how SSL interacts with these pre-trained models. To address this gap, we develop new SSL benchmark datasets where frozen VFMs underperform and systematically evaluate representative SSL methods. We make a surprising observation: parameter-efficient fine-tuning (PEFT) using only labeled data often matches SSL performance, even without leveraging unlabeled data. This motivates us to revisit self-training, a conceptually simple SSL baseline, where we use the supervised PEFT model to pseudo-label unlabeled data for further training. To overcome the notorious issue of noisy pseudo-labels, we propose ensembling multiple PEFT approaches and VFM backbones to produce more robust pseudo-labels. Empirical results validate the effectiveness of this simple yet powerful approach, providing actionable insights into SSL with VFMs and paving the way for more scalable and practical semi-supervised learning in the era of foundation models.

cs.LG↗

arXiv2025

SecDiff: Diffusion-Aided Secure Deep Joint Source-Channel Coding Against Adversarial Attacks

Deep joint source-channel coding (JSCC) has emerged as a promising paradigm for semantic communication, delivering significant performance gains over conventional separate coding schemes. However, existing JSCC frameworks remain vulnerable to physical-layer adversarial threats, such as pilot spoofing and subcarrier jamming, compromising semantic fidelity. In this paper, we propose SecDiff, a plug-and-play, diffusion-aided decoding framework that significantly enhances the security and robustness of deep JSCC under adversarial wireless environments. Different from prior diffusion-guided JSCC methods that suffer from high inference latency, SecDiff employs pseudoinverse-guided sampling and adaptive guidance weighting, enabling flexible step-size control and efficient semantic reconstruction. To counter jamming attacks, we introduce a power-based subcarrier masking strategy and recast recovery as a masked inpainting problem, solved via diffusion guidance. For pilot spoofing, we formulate channel estimation as a blind inverse problem and develop an expectation-minimization (EM)-driven reconstruction algorithm, guided jointly by reconstruction loss and a channel operator. Notably, our method alternates between pilot recovery and channel estimation, enabling joint refinement of both variables throughout the diffusion process. Extensive experiments over orthogonal frequency-division multiplexing (OFDM) channels under adversarial conditions show that SecDiff outperforms existing secure and generative JSCC baselines by achieving a favorable trade-off between reconstruction quality and computational cost. This balance makes SecDiff a promising step toward practical, low-latency, and attack-resilient semantic communications.

cs.CV↗

arXiv2025

Neutron source-based event reconstruction algorithm in large liquid scintillator detectors

We developed an event reconstruction algorithm, applicable to large liquid scintillator detectors, built primarily upon neutron calibration data. We employ a likelihood method using photon detection time and charge information from individual photomultiplier tubes. Detector response tables in the likelihood function were derived from americium-carbon neutron source events, 2.2~MeV $γ$-ray events from cosmic-ray muon spallation neutrons, and laser calibration events. This algorithm can reconstruct the event position, energy, and also has capability to differentiate particle types for events within the energy range of reactor neutrinos. Using the detector simulation of the Jiangmen Underground Neutrino Observatory (JUNO) experiment as a large liquid scintillator detector example, we demonstrate that the presented reconstruction algorithm has a reconstructed position accuracy within $\pm$4~cm, and a reconstructed energy non-uniformity under 0.5\% throughout the central detector volume. The vertex resolution for positron events at 1~MeV is estimated to be around 9~cm, and the energy resolution is confirmed to be comparable to that in the JUNO official publication. Furthermore, the algorithm can eliminate 80\% (45\%) of $α$-particle (fast-neutron) events while maintaining a positron event selection efficiency of approximately 99\%.

physics.ins-det↗

arXiv2025

Multiwavelength spectroscopic observations of a quiescent prominence

In this paper we focus on the analysis of the multiwavelength spectroscopic observations of a quiescent prominence. The spectral and geometrical parameters in the prominence were derived and used to constrain the NLTE radiative transfer models. Applying this method with multiwavelength observations provides a good opportunity to reduce the large range of thermodynamic parameters in solar prominences. We used time-slice and optical flow methods in order to derive the plane-of-sky (POS) velocities, and used gravity center and peak position methods on Mg II h&k and H I Ly-alpha profiles to compute the line-of-sight (LOS) velocities. We used the integrated intensities and FWHM values of the H-alpha, Ca II H, and Mg II h&k lines to compare with the NLTE radiative transfer computations. Ionization degree and thickness of the prominence plasma could be further derived. Opposite flows are observed along two strands between prominence barbs. The POS velocity can reach 20 km/s and the largest LOS velocity is > 90 km/s. The derived electron densities range from 6.5e9 cm-3 to 2.7e10 cm-3, and the derived total hydrogen densities range from 7.4e9 cm-3 to 6.6e10 cm-3. The temperature ranges from 7 000 to 14 000 K. The ionization degree of hydrogen is in the range of 0.40 to 0.91. The comparison between averaged and modeled profiles of Mg II and Ly-alpha lines shows that macro-velocities of 15 km/s and 20 km/s are required, respectively. The bulk motions among prominence barbs indicate that the prominence plasma is not confined within magnetic dips but exhibits a large-scale behavior. The presence of high-speed cool plasma flows, along with a wide range of plasma densities and temperatures, suggests that the prominence plasma is far from thermodynamic equilibrium and is inherently dynamic in nature.

astro-ph.SR↗

arXiv2025

The Boundaries of Fair AI in Medical Image Prognosis: A Causal Perspective

As machine learning (ML) algorithms are increasingly used in medical image analysis, concerns have emerged about their potential biases against certain social groups. Although many approaches have been proposed to ensure the fairness of ML models, most existing works focus only on medical image diagnosis tasks, such as image classification and segmentation, and overlooked prognosis scenarios, which involve predicting the likely outcome or progression of a medical condition over time. To address this gap, we introduce FairTTE, the first comprehensive framework for assessing fairness in time-to-event (TTE) prediction in medical imaging. FairTTE encompasses a diverse range of imaging modalities and TTE outcomes, integrating cutting-edge TTE prediction and fairness algorithms to enable systematic and fine-grained analysis of fairness in medical image prognosis. Leveraging causal analysis techniques, FairTTE uncovers and quantifies distinct sources of bias embedded within medical imaging datasets. Our large-scale evaluation reveals that bias is pervasive across different imaging modalities and that current fairness methods offer limited mitigation. We further demonstrate a strong association between underlying bias sources and model disparities, emphasizing the need for holistic approaches that target all forms of bias. Notably, we find that fairness becomes increasingly difficult to maintain under distribution shifts, underscoring the limitations of existing solutions and the pressing need for more robust, equitable prognostic models.

cs.LG↗

arXiv2025

Long time evolution of a pair of 2D viscous point vortices

This paper studies the long-time evolution of two point vortices under the 2D Navier-Stokes tokes equations. Starting from initial data given by a pair of Dirac measures, we derive an asymptotic expansion for the vorticity over time scales significantly longer than the advection time, yet shorter than the diffusion time. Building on previous works \cite{GS24-1, DG24}, we construct suitable approximate solutions $Ω_a$ and employ Arnold's method to define a nonlinear energy functional $E_\ve[\om]$, with respect to which the linearized operator $Λ^{E,\star}$ around $Ω_a$ is nearly skew-adjoint. A key innovation in this work is the introduction of ``pseudo-momenta'': $\varrho^e_a, \varrho^o_a,\varrho^{te}_a, \varrho^{to}_a$, which correspond to eigenfunctions or other nontrivial elements in invariant subspaces of $Λ^E$, derived from the Lie structure of the 2D Euler equations.

math.AP↗

arXiv2025

Generative AI for Data Augmentation in Wireless Networks: Analysis, Applications, and Case Study

Data augmentation as a technique can mitigate data scarcity in machine learning. However, owing to fundamental differences in wireless data structures, traditional data augmentation techniques may not be suitable for wireless data. Fortunately, Generative Artificial Intelligence (GenAI) can be an effective solution to wireless data augmentation due to its excellent data generation capability. This article systematically explores the potential and effectiveness of generative data augmentation in wireless networks. We first briefly review data augmentation techniques, discuss their limitations in wireless networks, and introduce generative data augmentation, including reviewing GenAI models and their applications in data augmentation. We then explore the application prospects of generative data augmentation in wireless networks from the physical, network, and application layers, providing a generative data augmentation architecture for each application. Subsequently, we propose a general generative data augmentation framework for Wi-Fi gesture recognition. Specifically, we leverage transformer-based diffusion models to generate high-quality channel state information data. To evaluate the effectiveness of the proposed framework, we conduct a case study using the Widar 3.0 dataset, which employs a residual network model for Wi-Fi gesture recognition. Simulation results demonstrate that the proposed framework can enhance the performance of Wi-Fi gesture recognition. Finally, we discuss research directions for generative data augmentation.

cs.NI↗

arXiv2025

6G Channel Modeling: Requirement, Measurement, Methodology and Simulator

Sixth-generation (6G) mobile communications have attracted substantial attention in the global research community of information and communication technologies (ICTs). 6G systems are expected to support not only extended 5G usage scenarios but also new usage scenarios, such as integrated sensing and communication (ISAC), integrated artificial intelligence (AI) and communication, and communication and ubiquitous connectivity. To achieve this goal, channel characteristics must be comprehensively studied and properly exploited to promote the design, standardization, and optimization of 6G systems. In this paper, we first summarize the requirements and challenges in 6G channel research. Our focus is on channels for six promising technologies enabling 6G, including ISAC, extremely large-scale MIMO (XL-MIMO), mid-band and terahertz (THz) technologies, reconfigurable intelligent surfaces (RISs), and space-air-ground integrated networks (SAGINs). A survey of the progress in 6G channel research regarding the above six promising technologies is presented in terms of the latest measurement campaigns, new characteristics, modeling methods, and research prospects. To support testing, optimization and evaluation, existing 6G channel simulators are summarized. Then, BUPTCMCCCMG-IMT2030 is introduced as an example of a simulator that was developed on the basis of the ITU/3GPP 3D geometry-based stochastic model (GBSM) methodology. We also address open issues covering standardization activities, AI-enabled methods, and system performance analysis in the context of 6G channel research. This paper offers in-depth, hands-on insights into the best practices of channel measurements, modeling, and simulations for the evaluation of 6G technologies, the development of 6G standards, and the implementation and optimization of 6G systems.

eess.SP↗

arXiv2025

A Superposition Code-Based Semantic Communication Approach with Quantifiable and Controllable Security

This paper addresses the challenge of achieving security in semantic communication (SemCom) over a wiretap channel, where a legitimate receiver coexists with an eavesdropper experiencing a poorer channel condition. Despite previous efforts to secure SemCom against eavesdroppers, guarantee of approximately zero information leakage remains an open issue. In this work, we propose a secure SemCom approach based on superposition code, aiming to provide quantifiable and controllable security for digital SemCom systems. The proposed method employs a double-layered constellation map, where semantic information is associated with satellite constellation points and cloud center constellation points are randomly selected. By carefully allocating power between these two layers of constellation, we ensure that the symbol error probability (SEP) of the eavesdropper when decoding satellite constellation points is nearly equivalent to random guessing, while maintaining a low SEP for the legitimate receiver to successfully decode the semantic information. Simulation results demonstrate that the peak signal-to-noise ratio (PSNR) and mean squared error (MSE) of the eavesdropper's reconstructed data, under the proposed method, can range from decoding Gaussian-distributed random noise to approaching the variance of the data. This validates the effectiveness of our method in nearly achieving the experimental upper bound of security for digital SemCom systems when both eavesdroppers and legitimate users utilize identical decoding schemes. Furthermore, the proposed method consistently outperforms benchmark techniques, showcasing superior data security and robustness against eavesdropping. The implementation code is publicly available at: https://github.com/1weixuanchen/ A-Superposition-Code-Based-Semantic-Communication.

cs.IT↗

arXiv2025

Know What, Know Why: Semantic Hazard Communication for Intelligent V2X Systems

In current vehicle-to-everything (V2X) communication systems, roadside units (RSUs) broadcast brief warning messages that alert nearby vehicles to avoid potential hazards. However, these messages lack contextual information on why a warning is issued, leading to excessive caution or inefficient driving behaviors. To avoid such a situation, we propose a semantic-enhanced and explainable V2X (SEE-V2X) system. In the proposed system, RSUs equipped with smart cameras detect obstructions and transmit context-aware messages to vehicles. By understanding both what the hazard is and why it occurs, drivers can make more intelligent decisions based on their specific driving situation. Furthermore, through a real-field demonstration, we show the new "see-through" feature in the proposed system, which enables drivers to visualize hidden pedestrians behind obstacles. We also perform simulations to compare traditional V2X with SEE-V2X under different traffic conditions. The results show that SEE-V2X significantly improves traffic efficiency and reduces unnecessary deceleration.

eess.SP↗

arXiv2025

Explicit Semantic-Base-Empowered Communications for 6G Mobile Networks

Increasing demands for massive data transmission pose significant challenges to communication systems. Compared with traditional communication systems that focus on the accurate reconstruction of bit sequences, SemComs, which aim to deliver information connotation, are regarded as a key technology for 6G mobile networks. Most current SemComs utilize an end-to-end trained NN for semantic extraction and interpretation, which lacks interpretability for further optimization. Moreover, NN-based SemComs assume that the application and physical layers of the protocol stack can be jointly trained, which is incompatible with current digital communication systems. To overcome those drawbacks, we propose a SemCom system that employs explicit semantic bases (Sebs) as the basic units to represent semantic connotations. First, a mathematical model of Sebs is proposed to build an explicit KB. Then, the Seb-based SemCom architecture is proposed, including both a communication mode and a KB update mode to enable the evolution of communication systems. Sem-codec and channel codec modules are designed specifically, with the assistance of an explicit KB for the efficient and robust transmission of semantics. Moreover, UEP is strategically implemented, considering communication intent and the importance of Sebs, thereby ensuring the reliability of critical semantics. In addition, a Seb-based SemCom protocol stack that is compatible with the 5G protocol stack is proposed. To assess the effectiveness and compatibility of the proposed Seb-based SemComs, a case study focusing on an image-transmission task is conducted. The simulations show that our Seb-based SemComs outperform state-of-the-art works in LPIPS by over 20% under varying communication intents and exhibit robustness under fluctuating channel conditions, highlighting the advantages of the interpretability and flexibility afforded by explicit Sebs.

eess.SP↗

arXiv2025

SemHARQ: Semantic-Aware Hybrid Automatic Repeat Request for Multi-Task Semantic Communications

Intelligent task-oriented semantic communications~(SemComs) have witnessed great progress with the development of deep learning~(DL), where multi-task SemComs that perform multiple tasks simultaneously attach great importance due to its high efficiency. However, the study of robust multi-task-oriented semantics transmission is still in early stages. In this paper, we propose a semantic-aware hybrid automatic repeat request~(SemHARQ) framework for the robust and efficient transmissions of multi-task semantic features. First, to improve the robustness and effectiveness of semantic coding, a multi-task semantic encoder is proposed. Meanwhile, a feature importance ranking~(FIR) method is investigated to ensure the important features delivery under limited channel resources. Then, to accurately detect the possible transmission errors, a novel feature distortion evaluation~(FDE) network is designed to identify the distortion level of each feature, based on which an efficient HARQ method is proposed. Specifically, the corrupted features are retransmitted, where the remaining channel resources are used for incremental transmissions. The system performance is evaluated under different channel conditions in multi-task scenarios in the Internet of Vehicles. Extensive experiments show that the proposed framework outperforms state-of-the-art works by more than $20\%$ in rank-1 accuracy for vehicle re-identification, and $10\%$ in vehicle color classification accuracy in the low signal-to-noise ratio regime.

eess.SP↗

arXiv2025

Secure Multi-LLM Agentic AI and Agentification for Edge General Intelligence by Zero-Trust: A Survey

Agentification serves as a critical enabler of Edge General Intelligence (EGI), transforming massive edge devices into cognitive agents through integrating Large Language Models (LLMs) and perception, reasoning, and acting modules. These agents collaborate across heterogeneous edge infrastructures, forming multi-LLM agentic AI systems that leverage collective intelligence and specialized capabilities to tackle complex, multi-step tasks. However, the collaborative nature of multi-LLM systems introduces critical security vulnerabilities, including insecure inter-LLM communications, expanded attack surfaces, and cross-domain data leakage that traditional perimeter-based security cannot adequately address. To this end, this survey introduces zero-trust security of multi-LLM in EGI, a paradigmatic shift following the ``never trust, always verify'' principle. We begin by systematically analyzing the security risks in multi-LLM systems within EGI contexts. Subsequently, we present the vision of a zero-trust multi-LLM framework in EGI. We then survey key technical progress to facilitate zero-trust multi-LLM systems in EGI. Particularly, we categorize zero-trust security mechanisms into model- and system-level approaches. The former and latter include strong identification, context-aware access control, etc., and proactive maintenance, blockchain-based management, etc., respectively. Finally, we identify critical research directions. This survey serves as the first systematic treatment of zero-trust applied to multi-LLM systems, providing both theoretical foundations and practical strategies.

cs.NI↗

arXiv2025

SurgWound-Bench: A Benchmark for Surgical Wound Diagnosis

Surgical site infection (SSI) is one of the most common and costly healthcare-associated infections and and surgical wound care remains a significant clinical challenge in preventing SSIs and improving patient outcomes. While recent studies have explored the use of deep learning for preliminary surgical wound screening, progress has been hindered by concerns over data privacy and the high costs associated with expert annotation. Currently, no publicly available dataset or benchmark encompasses various types of surgical wounds, resulting in the absence of an open-source Surgical-Wound screening tool. To address this gap: (1) we present SurgWound, the first open-source dataset featuring a diverse array of surgical wound types. It contains 697 surgical wound images annotated by 3 professional surgeons with eight fine-grained clinical attributes. (2) Based on SurgWound, we introduce the first benchmark for surgical wound diagnosis, which includes visual question answering (VQA) and report generation tasks to comprehensively evaluate model performance. (3) Furthermore, we propose a three-stage learning framework, WoundQwen, for surgical wound diagnosis. In the first stage, we employ five independent MLLMs to accurately predict specific surgical wound characteristics. In the second stage, these predictions serve as additional knowledge inputs to two MLLMs responsible for diagnosing outcomes, which assess infection risk and guide subsequent interventions. In the third stage, we train a MLLM that integrates the diagnostic results from the previous two stages to produce a comprehensive report. This three-stage framework can analyze detailed surgical wound characteristics and provide subsequent instructions to patients based on surgical images, paving the way for personalized wound care, timely intervention, and improved patient outcomes.

cs.AI↗