arXiv subjects

Zihao Zhao

Publications and source records attributed to Zihao Zhao.

At least 37 records · Page 2Linked to original sources

arXiv2025

Evaluating Large Language Models for Radiology Natural Language Processing

The rise of large language models (LLMs) has marked a pivotal shift in the field of natural language processing (NLP). LLMs have revolutionized a multitude of domains, and they have made a significant impact in the medical field. Large language models are now more abundant than ever, and many of these models exhibit bilingual capabilities, proficient in both English and Chinese. However, a comprehensive evaluation of these models remains to be conducted. This lack of assessment is especially apparent within the context of radiology NLP. This study seeks to bridge this gap by critically evaluating thirty two LLMs in interpreting radiology reports, a crucial component of radiology NLP. Specifically, the ability to derive impressions from radiologic findings is assessed. The outcomes of this evaluation provide key insights into the performance, strengths, and weaknesses of these LLMs, informing their practical applications within the medical domain.

cs.CL↗

arXiv2025

SynthTextEval: Synthetic Text Data Generation and Evaluation for High-Stakes Domains

We present SynthTextEval, a toolkit for conducting comprehensive evaluations of synthetic text. The fluency of large language model (LLM) outputs has made synthetic text potentially viable for numerous applications, such as reducing the risks of privacy violations in the development and deployment of AI systems in high-stakes domains. Realizing this potential, however, requires principled consistent evaluations of synthetic data across multiple dimensions: its utility in downstream systems, the fairness of these systems, the risk of privacy leakage, general distributional differences from the source text, and qualitative feedback from domain experts. SynthTextEval allows users to conduct evaluations along all of these dimensions over synthetic data that they upload or generate using the toolkit's generation module. While our toolkit can be run over any data, we highlight its functionality and effectiveness over datasets from two high-stakes domains: healthcare and law. By consolidating and standardizing evaluation metrics, we aim to improve the viability of synthetic text, and in-turn, privacy-preservation in AI development.

cs.CL↗

arXiv2025

VisionCAD: An Integration-Free Radiology Copilot Framework

Widespread clinical deployment of computer-aided diagnosis (CAD) systems is hindered by the challenge of integrating with existing hospital IT infrastructure. Here, we introduce VisionCAD, a vision-based radiological assistance framework that circumvents this barrier by capturing medical images directly from displays using a camera system. The framework operates through an automated pipeline that detects, restores, and analyzes on-screen medical images, transforming camera-captured visual data into diagnostic-quality images suitable for automated analysis and report generation. We validated VisionCAD across diverse medical imaging datasets, demonstrating that our modular architecture can flexibly utilize state-of-the-art diagnostic models for specific tasks. The system achieves diagnostic performance comparable to conventional CAD systems operating on original digital images, with an F1-score degradation typically less than 2\% across classification tasks, while natural language generation metrics for automated reports remain within 1\% of those derived from original images. By requiring only a camera device and standard computing resources, VisionCAD offers an accessible approach for AI-assisted diagnosis, enabling the deployment of diagnostic capabilities in diverse clinical settings without modifications to existing infrastructure.

cs.CV↗

arXiv2025

Diffusion-DFL: Decision-focused Diffusion Models for Stochastic Optimization

Decision-focused learning (DFL) integrates predictive modeling and optimization by training predictors to optimize the downstream decision target rather than merely minimizing prediction error. To date, existing DFL methods typically rely on deterministic point predictions, which are often insufficient to capture the intrinsic stochasticity of real-world environments. To address this challenge, we propose the first diffusion-based DFL approach, which trains a diffusion model to represent the distribution of uncertain parameters and optimizes the decision by solving a stochastic optimization with samples drawn from the diffusion model. Our contributions are twofold. First, we formulate diffusion DFL using the reparameterization trick, enabling end-to-end training through diffusion. While effective, it is memory and compute-intensive due to the need to differentiate through the diffusion sampling process. Second, we propose a lightweight score function estimator that uses only several forward diffusion passes and avoids backpropagation through the sampling. This follows from our results that backpropagating through stochastic optimization can be approximated by a weighted score function formulation. We empirically show that our diffusion DFL approach consistently outperforms strong baselines in decision quality. The source code for all experiments is available at the project repository: https://github.com/GT-KOALA/Diffusion_DFL.

cs.LG↗

arXiv2025

Controlled Generation for Private Synthetic Text

Text anonymization is essential for responsibly developing and deploying AI in high-stakes domains such as healthcare, social services, and law. In this work, we propose a novel methodology for privacy-preserving synthetic text generation that leverages the principles of de-identification and the Hiding In Plain Sight (HIPS) theory. Our approach introduces entity-aware control codes to guide controllable generation using either in-context learning (ICL) or prefix tuning. The ICL variant ensures privacy levels consistent with the underlying de-identification system, while the prefix tuning variant incorporates a custom masking strategy and loss function to support scalable, high-quality generation. Experiments on legal and clinical datasets demonstrate that our method achieves a strong balance between privacy protection and utility, offering a practical and effective solution for synthetic text generation in sensitive domains.

cs.CL↗

arXiv2025

Improving Alignment in LVLMs with Debiased Self-Judgment

The rapid advancements in Large Language Models (LLMs) and Large Visual-Language Models (LVLMs) have opened up new opportunities for integrating visual and linguistic modalities. However, effectively aligning these modalities remains challenging, often leading to hallucinations--where generated outputs are not grounded in the visual input--and raising safety concerns across various domains. Existing alignment methods, such as instruction tuning and preference tuning, often rely on external datasets, human annotations, or complex post-processing, which limit scalability and increase costs. To address these challenges, we propose a novel approach that generates the debiased self-judgment score, a self-evaluation metric created internally by the model without relying on external resources. This enables the model to autonomously improve alignment. Our method enhances both decoding strategies and preference tuning processes, resulting in reduced hallucinations, enhanced safety, and improved overall capability. Empirical results show that our approach significantly outperforms traditional methods, offering a more effective solution for aligning LVLMs.

cs.CV↗

arXiv2025

Fine-grained Alignment of Large Language Models for General Medication Recommendation without Overprescription

Large language models (LLMs) holds significant promise in achieving general medication recommendation systems owing to their comprehensive interpretation of clinical notes and flexibility to medication encoding. We evaluated both general-purpose and medical-specific LLMs for medication recommendations, showing their unsatisfactory precision and severe overprescription. To address this, we introduce Language-Assisted Medication Recommendation, which tailors LLMs for medication recommendation in a medication-aware manner, improving the usage of clinical notes. Fine-tuning LLMs with this framework can outperform existing methods by more than 10% in internal validation and generalize across temporal and external validations. Furthermore, the model maintains high accuracy when encountering out-of-distribution medication.

cs.IR↗

arXiv2025

GLIMPSE: Do Large Vision-Language Models Truly Think With Videos or Just Glimpse at Them?

Existing video benchmarks often resemble image-based benchmarks, with question types like "What actions does the person perform throughout the video?" or "What color is the woman's dress in the video?" For these, models can often answer by scanning just a few key frames, without deep temporal reasoning. This limits our ability to assess whether large vision-language models (LVLMs) can truly think with videos rather than perform superficial frame-level analysis. To address this, we introduce GLIMPSE, a benchmark specifically designed to evaluate whether LVLMs can genuinely think with videos. Unlike prior benchmarks, GLIMPSE emphasizes comprehensive video understanding beyond static image cues. It consists of 3,269 videos and over 4,342 highly visual-centric questions across 11 categories, including Trajectory Analysis, Temporal Reasoning, and Forensics Detection. All questions are carefully crafted by human annotators and require watching the entire video and reasoning over full video context-this is what we mean by thinking with video. These questions cannot be answered by scanning selected frames or relying on text alone. In human evaluations, GLIMPSE achieves 94.82% accuracy, but current LVLMs face significant challenges. Even the best-performing model, GPT-o3, reaches only 66.43%, highlighting that LVLMs still struggle to move beyond surface-level reasoning to truly think with videos.

cs.CV↗

arXiv2025

Med-LEGO: Editing and Adapting toward Generalist Medical Image Diagnosis

The adoption of visual foundation models has become a common practice in computer-aided diagnosis (CAD). While these foundation models provide a viable solution for creating generalist medical AI, privacy concerns make it difficult to pre-train or continuously update such models across multiple domains and datasets, leading many studies to focus on specialist models. To address this challenge, we propose Med-LEGO, a training-free framework that enables the seamless integration or updating of a generalist CAD model by combining multiple specialist models, similar to assembling LEGO bricks. Med-LEGO enhances LoRA (low-rank adaptation) by incorporating singular value decomposition (SVD) to efficiently capture the domain expertise of each specialist model with minimal additional parameters. By combining these adapted weights through simple operations, Med-LEGO allows for the easy integration or modification of specific diagnostic capabilities without the need for original data or retraining. Finally, the combined model can be further adapted to new diagnostic tasks, making it a versatile generalist model. Our extensive experiments demonstrate that Med-LEGO outperforms existing methods in both cross-domain and in-domain medical tasks while using only 0.18% of full model parameters. These merged models show better convergence and generalization to new tasks, providing an effective path toward generalist medical AI.

cs.CV↗

arXiv2025

Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning

Foundation models have achieved great success in natural language processing (NLP) and computer vision (CV). Their success largely stems from the ability to integrate multi-domain knowledge in pre-training and transfer it to target domains. Considering graph data, especially graphs without textual features, is ubiquitous in real-world applications such as social networks and recommendation systems, some researchers have attempted to extend this paradigm to the graph field, aiming to construct graph foundation models. However, unlike CV and NLP, there are huge gaps among the semantics and properties of graphs in different domains, while current works still adopt traditional contrastive pre-training strategies designed in the single-domain scenario, which regard contrastive samples from different domains as equivalent. From experimental investigations, we discovered that inherent domain-specific differences prevent these strategies from effectively absorbing knowledge from different domains to generate informative representations. In this paper, we propose a novel multi-domain pre-training and cross-domain transfer framework, namely MDGCL.In the pre-training stage, we design a contrastive learning strategy to substantially recognize and capture domain differences, and introduce domain tokens to encode domain-level global information. In the downstream stage, we introduce a domain attention mechanism to enable fine-grained domain knowledge transfer. Extensive experiments on five benchmark datasets have demonstrated that our method outperforms state-of-the-art significantly, with the maximum improvement of 19.33\% on accuracy and 19.13\% on Macro-F1 score.

cs.CL↗

arXiv2025

UniCAD: Efficient and Extendable Architecture for Multi-Task Computer-Aided Diagnosis System

The growing complexity and scale of visual model pre-training have made developing and deploying multi-task computer-aided diagnosis (CAD) systems increasingly challenging and resource-intensive. Furthermore, the medical imaging community lacks an open-source CAD platform to enable the rapid creation of efficient and extendable diagnostic models. To address these issues, we propose UniCAD, a unified architecture that leverages the robust capabilities of pre-trained vision foundation models to seamlessly handle both 2D and 3D medical images while requiring only minimal task-specific parameters. UniCAD introduces two key innovations: (1) Efficiency: A low-rank adaptation strategy is employed to adapt a pre-trained visual model to the medical image domain, achieving performance on par with fully fine-tuned counterparts while introducing only 0.17% trainable parameters. (2) Plug-and-Play: A modular architecture that combines a frozen foundation model with multiple plug-and-play experts, enabling diverse tasks and seamless functionality expansion. Building on this unified CAD architecture, we establish an open-source platform where researchers can share and access lightweight CAD experts, fostering a more equitable and efficient research ecosystem. Comprehensive experiments across 12 diverse medical datasets demonstrate that UniCAD consistently outperforms existing methods in both accuracy and deployment efficiency. The source code and project page are available at https://mii-laboratory.github.io/UniCAD/.

cs.CV↗

arXiv2025

Fermi-LAT and FAST observation of the gamma-ray binary HESS J0632+057

Using 15 years of data from the Fermi Large Area Telescope (Fermi-LAT), we performed a comprehensive analysis on the gamma-ray binary HESS J0632+057. Its spectrum in 0.1-300 GeV band is well described by a power law model with an index of $2.40\pm0.16$, leading to an energy flux of (5.5$\pm$1.6$)\times$ 10$^{-12}$ erg cm$^{-2}$ s$^{-1}$. The GeV Spectral Energy Distribution (SED) of HESS J0632+057 hints for a spectral turn-over between $\sim$10-100 GeV. Orbital analysis reveals a flux enhancement during the phase range of 0.2-0.4, consistent with the X-ray and TeV light curves, indicating an origin of a common particle population. We carried out six deep radio observations on HESS J0632+057 with the Five-hundred-meter Aperture Spherical Telescope (FAST), evenly distributed across its orbit, reaching a detection sensitivity of 2$μ$Jy. However, no radio pulsation was detected within these observations. The absence of radio pulsation may be attributed to the dense stellar wind environment of HESS J0632+057.

astro-ph.HE↗

arXiv2025

CLIP in Medical Imaging: A Survey

Contrastive Language-Image Pre-training (CLIP), a simple yet effective pre-training paradigm, successfully introduces text supervision to vision models. It has shown promising results across various tasks due to its generalizability and interpretability. The use of CLIP has recently gained increasing interest in the medical imaging domain, serving as a pre-training paradigm for image-text alignment, or a critical component in diverse clinical tasks. With the aim of facilitating a deeper understanding of this promising direction, this survey offers an in-depth exploration of the CLIP within the domain of medical imaging, regarding both refined CLIP pre-training and CLIP-driven applications. In this paper, we (1) first start with a brief introduction to the fundamentals of CLIP methodology; (2) then investigate the adaptation of CLIP pre-training in the medical imaging domain, focusing on how to optimize CLIP given characteristics of medical images and reports; (3) further explore practical utilization of CLIP pre-trained models in various tasks, including classification, dense prediction, and cross-modal tasks; and (4) finally discuss existing limitations of CLIP in the context of medical imaging, and propose forward-looking directions to address the demands of medical imaging domain. Studies featuring technical and practical value are both investigated. We expect this survey will provide researchers with a holistic understanding of the CLIP paradigm and its potential implications. The project page of this survey can also be found on https://github.com/zhaozh10/Awesome-CLIP-in-Medical-Imaging.

cs.CV↗

arXiv2025

Upper limits on the gamma-ray emission from the microquasar V4641 Sgr

Following a recent detection of TeV radiation by the Large High Altitude Air Shower Observatory (LHAASO) and the High-Altitude Water Cherenkov Observatory (HAWC), coincident with the direction of the microquasar V4641 Sgr, we search for possible GeV emission from this source. We explored the morphology and temporal features of the source as well as two nearby unassociated point sources which could be a part of extended structure of V4641 Sgr, and compared results with corresponding X-ray and TeV emissions. The 95% confidence level upper limits for the flux from the source, assuming both point and extended source models were 5.38$\times$ 10$^{-13}$ erg cm$^{-2}$ s$^{-1}$ and 1.12$\times$ 10$^{-12}$ erg cm$^{-2}$ s$^{-1}$, respectively. Additionally, no correlation between gamma-ray light curve and X-ray outbursts was observed.

astro-ph.HE↗

arXiv2025

Privacy-Preserving Hybrid Ensemble Model for Network Anomaly Detection: Balancing Security and Data Protection

Privacy-preserving network anomaly detection has become an essential area of research due to growing concerns over the protection of sensitive data. Traditional anomaly detection models often prioritize accuracy while neglecting the critical aspect of privacy. In this work, we propose a hybrid ensemble model that incorporates privacy-preserving techniques to address both detection accuracy and data protection. Our model combines the strengths of several machine learning algorithms, including K-Nearest Neighbors (KNN), Support Vector Machines (SVM), XGBoost, and Artificial Neural Networks (ANN), to create a robust system capable of identifying network anomalies while ensuring privacy. The proposed approach integrates advanced preprocessing techniques that enhance data quality and address the challenges of small sample sizes and imbalanced datasets. By embedding privacy measures into the model design, our solution offers a significant advancement over existing methods, ensuring both enhanced detection performance and strong privacy safeguards.

cs.LG↗

arXiv2025

Sensitivity adjustable in-line high-temperature sensor based on metal microwire optical Fabry-Perot interferometer

The optical fiber Fabry-Perot interferometer (FPI) has been widely investigated as a potential temperature sensor. To function as a temperature sensor, the cavity of the FPI is typically constructed from either silica fibers or polymers. The silica cavity FPIs can function at temperatures exceeding 1000°C. However, its temperature sensitivity is constrained by its relatively low thermal optical coefficient and thermal expansion of silica materials. Although the polymer cavity FPI exhibits a high temperature sensitivity, its cavity is susceptible to deterioration in high-temperature environments. Here, to overcome this challenge and achieve high-sensitivity temperature sensing in a high-temperature environment, we propose a new type of temperature FPI sensor by inserting and sealing a section of Cr20Ni80 metal microwire inside a section of silica hollow core fiber (HCF) spliced to standard single-mode fiber (SMF). The FPIs exhibit a high degree of temperature sensitivity due to the high thermal expansion of the Cr20Ni80 metal microwire. Since the Cr20Ni80 metal has a high melting temperature of 1400°C, such FPIs can function in high-temperature environments. Moreover, the temperature sensitivity of this FPI can be modified without affecting its reflection spectrum by changing the length of the metallic microwire situated within the hollow core fiber. The experimental results indicate that the proposed FPIs exhibit a temperature sensitivity greater than -0.35nm/°C within the temperature range of 50°C to 440°C. Our proposed metal microwire-based FPIs are economical, robust, simple to fabricate, and capable of functioning in high-temperature environments, rendering them appealing options for practical applications

physics.app-ph↗

arXiv2024

Artistic Neural Style Transfer Algorithms with Activation Smoothing

The works of Gatys et al. demonstrated the capability of Convolutional Neural Networks (CNNs) in creating artistic style images. This process of transferring content images in different styles is called Neural Style Transfer (NST). In this paper, we re-implement image-based NST, fast NST, and arbitrary NST. We also explore to utilize ResNet with activation smoothing in NST. Extensive experimental results demonstrate that smoothing transformation can greatly improve the quality of stylization results.

cs.CV↗

arXiv2024

A hybrid single quantum dot coupled cavity on a CMOS-compatible SiC photonic chip for Purcell-enhanced deterministic single-photon emission

The ability to control nonclassical light emission from a single quantum emitter by an integrated cavity may unleash new perspectives for integrated photonic quantum applications. However, coupling a single quantum emitter to cavity within photonic circuitry towards creation of the Purcell-enhanced single-photon emission is elusive due to the complexity of integrating active devices in low-loss photonic circuits. Here we demonstrate a hybrid micro-ring resonator (HMRR) coupled with self-assembled quantum dots (QDs) for cavity-enhanced deterministic single-photon emission. The HMRR cavity supports whispering-gallery modes with quality factors up to 7800. By further introducing a micro-heater, we show that the photon emission of QDs can be locally and dynamically tuned over one free spectral ranges of the HMRR (~4 nm). This allows precise tuning of individual QDs in resonance with the cavity modes, thereby enhancing single-photon emission with a Purcell factor of about 4.9. Our results on the hybrid integrated cavities coupled with two-level quantum emitters emerge as promising devices for chip-based scalable photonic quantum applications.

quant-ph↗