arXiv subjects

Shang Gao

Publications and source records attributed to Shang Gao.

At least 19 recordsLinked to original sources

arXiv2026

E2S-Pruner: Progressive Two-Stage Evidence Fusion for Visual Token Pruning in Vision-Language Models

Vision-language models typically encode an image into hundreds of visual tokens, incurring substantial inference latency and GPU memory overhead. Existing pruning methods largely rely on attention scores and directly aggregate outputs across attention heads and network layers, making it difficult to characterize evidential uncertainty and conflict. We propose E2S-Pruner, a progressive two-stage evidence-fusion framework for visual token pruning that requires no auxiliary model, trainable parameters, or fine-tuning. In the first stage, E2S-Pruner treats each attention head as an independent evidence source, estimates its reliability from evidence clarity and inter-head consistency, and represents each visual token using three states: important, unimportant, and uncertain. In the second stage, Dempster--Shafer evidence theory is used to quantify inter-layer conflict and fuse complementary evidence from multiple network layers. We further introduce a spatial novelty constraint that promotes coverage of distinct image regions and prevents the retained tokens from concentrating in a few locally salient areas. On LLaVA-1.5-7B, E2S-Pruner retains 98.0%, 96.8%, and 90.6% of the aggregate performance when the average numbers of retained visual tokens are 192, 128, and 64, respectively, while improving throughput by 1.96x and 2.09x under the 128-token and 64-token settings. Experiments on Qwen2-VL-7B further demonstrate cross-model generalization. Code is available at https://github.com/taoyu-qian/E2S-Pruner.git.

cs.CV↗

arXiv2026

Elementary magnons and interacting multi-magnon quasiparticles in the effective spin-$\frac{1}{2}$ kagome-staircase magnet Co$_{3}$V$_{2}$O$_{8}$

The excitation spectrum of an anisotropic magnet provides a direct link between its microscopic Hamiltonian and interaction-driven quasiparticles. Here we use high-resolution time-domain terahertz spectroscopy to map the magnetic excitations of the three-dimensional kagome-staircase compound Co$_{3}$V$_{2}$O$_{8}$ as functions of temperature and magnetic field. At low energies, polarization-resolved spectra identify magnetic-dipole-active one-magnon modes and track their evolution across the ferromagnetic and spin-density-wave phases. Combining their field dependence with previously reported inelastic-neutron-scattering dispersions, we determine an effective spin-$\frac{1}{2}$ Hamiltonian with strongly anisotropic exchange that quantitatively reproduces the one-magnon spectrum. This model provides a noninteracting benchmark for the high-energy response, where we observe sharp branches with field slopes that are two to four times those of the one-magnon modes, together with anticrossings between branches of different magnon numbers. Their sharpness, polarization dependence, and departure from the calculated multi-magnon continua identify them as interacting multi-magnon quasiparticles that can be stabilized by strong exchange anisotropy.

cond-mat.str-el↗

arXiv2026

Tremerity-Fi: Non-Contact Daily-Life Tremor Severity Assessment by Commercial mmWave Radar

Tremor is a common symptom of neurological diseases. The regular assessment of daily tremors facilitates the evaluation of disease progression and assists clinicians in optimizing treatment strategies. However, current home monitoring solutions have difficulty in dealing with user cooperation, privacy concerns, environmental interference, and system generalization, leading to feasibility concerns in activities of daily living (ADL). To this end, we propose Tremerity-Fi, a non-contact and privacy-friendly tremor severity assessment system based on mmWave radar. To realize Tremerity-Fi, we first design an adaptive beamforming algorithm to accurately identify useful but weak signals from numerous reflections captured in the environment. Second, unlike primary reflections commonly used in mmWave sensing, we leverage multipath reflections that carry useful information about the target's motion, even though they are generally considered harmful, to help reconstruct hand signals and improve sensing performance. Furthermore, we propose an unsupervised domain adaptation algorithm to improve the ability to adapt to unseen environments and users. We collect a diverse dataset of 5 patients and 25 healthy subjects in 3 scenarios, such as offices, homes, and hospitals. Extensive experiments show that our system achieves 94.51% accuracy in tremor detection, about 5 higher than the SOTA mmWave radar method, and 89.13% in tremor severity assessment, demonstrating its sufficient potential as a tremor monitoring assistant for patients with neurological diseases.

eess.SP↗

arXiv2026

Strongly frustrated 2D magnetism in a 3D hexagonal perovskite

Exotic quantum phenomena are often found to occur in spin systems that exhibit low-dimensional magnetism. By combining nuclear magnetic resonance, neutron scattering, and muon-spin spectroscopy ($\mu$SR) techniques, we report a rare instance of strongly frustrated two-dimensional (2D) magnetism in a three-dimensional (3D) hexagonal perovskite. Here, Ba$_2$La$_2$MnTe$_2$O$_{12}$, a triangular-lattice magnet, is shown to undergo a magnetic transition at $T_\mathrm{N} \approx$ 4.4 K, below which the manganese moments form a 120$^{\circ}$ AFM order within the $ab$-plane, while staying disordered along the $c$-axis. This exotic ground state, which exhibits ideal 2D magnetism, is highly consistent with the persistently strong spin fluctuations and the large internal field distributions revealed by zero-field $\mu$SR. Further, the 2D magnetism also leads to a significant frustration, much larger than that of most known magnetically-ordered frustrated systems. Our work on Ba$_2$La$_2$MnTe$_2$O$_{12}$ not only challenges the interpretations of magnetic order in other 3D hexagonal perovskites, but it also provides insight into how the dimensionality affects the exotic magnetic states.

cond-mat.str-el↗

arXiv2026

TRACER: Training-Free Closed-Loop Structured Inference for Traffic Accident Reconstruction

Traffic accident reconstruction is a forensic inverse problem that requires recovering physically consistent motion from sparse and heterogeneous evidence. Existing learning-based approaches predominantly optimize for semantic plausibility or visual realism, rather than quantitative agreement with measurable geometry and dynamics. Here, we present TRACER, a training-free framework that formulates reconstruction as a closed-loop structured inference process. Instead of directly generating dense trajectories, our framework constructs and iteratively refines event-anchored motion hypotheses under geometric, kinematic, and interaction constraints, guided by structured case memory and consistency-driven diagnosis. This design enables incremental, interpretable corrections when evidence is insufficient, making the accident reconstruction process more aligned with the workflow of human experts. Experiments on real-world accident data show that TRACER achieves improved geometric fidelity, velocity consistency, and collision accuracy over both data-driven and physics-based baselines.

cs.LG↗

arXiv2026

Noise-Aware Visual Representation Learning for Medical Visual Question Answering

Medical visual question answering (Med-VQA) has strong potential for clinical decision support by enabling AI models to interpret medical images and answer clinically relevant queries. Recent approaches typically connect off-the-shelf vision encoders with large language models (LLMs) through lightweight mapping networks to reduce computational cost. However, these methods often overlook the importance of handling noise and small irrelevant changes in visual representations. To address these challenges, we propose a noise-aware Med-VQA framework that incorporates a denoising autoencoder before visual embeddings are mapped into the input space of an LLM. The denoising autoencoder is pretrained to reconstruct clean visual embeddings from corrupted inputs, encouraging the model to learn robust visual representations that are less sensitive to noise. The resulting embeddings are then projected into the language model embedding space using a multi-layer perceptron (MLP), forming visual prefix tokens that provide image information to the LLM. To enable efficient adaptation without full retraining, we employ parameter-efficient fine-tuning using low-rank adaptation (LoRA). The proposed method is evaluated on the SLAKE and PathVQA benchmarks. Experimental results show improved robustness to noisy input embeddings while maintaining competitive clean performance across multiple evaluation criteria. These findings suggest that learning more robust visual representations can enhance Med-VQA performance and robustness.

cs.CV↗

arXiv2026

Emergent Vortex Ordering in a Multiflavor Pyrochlore-Lattice Compound GeCo$_2$O$_4$

Entangled spin and orbital degrees of freedom provide a multiflavor route to novel magnetic states inaccessible in conventional spin systems. Here, we report the experimental identification of an emergent vortex lattice in the multiflavor pyrochlore-lattice compound GeCo$_2$O$_4$. By combining comprehensive neutron scattering experiments with a regularized regression framework, we identify substantial Kitaev interactions among the nearest-neighboring Co$^{2+}$ pseudospins, which cooperate with geometric frustration to stabilize the vortex order. These results reveal an unexpected route to vortex-lattice order in a three-dimensional Kitaev-frustrated magnet and demonstrate a regularized protocol for Hamiltonian determination in frustrated quantum materials.

cond-mat.str-el↗

arXiv2026

DichroGAN: Towards Restoration of in-air Colours of Seafloor from Satellite Imagery

Recovering the in-air colours of seafloor from satellite imagery is a challenging task due to the exponential attenuation of light with depth in the water column. In this study, we present DichroGAN, a conditional generative adversarial network (cGAN) designed for this purpose. DichroGAN employs a two-steps simultaneous training: first, two generators utilise a hyperspectral image cube to estimate diffuse and specular reflections, thereby obtaining atmospheric scene radiance. Next, a third generator receives as input the generated scene radiance containing the features of each spectral band, while a fourth generator estimates the underwater light transmission. These generators work together to remove the effects of light absorption and scattering, restoring the in-air colours of seafloor based on the underwater image formation equation. DichroGAN is trained on a compact dataset derived from PRISMA satellite imagery, comprising RGB images paired with their corresponding spectral bands and masks. Extensive experiments on both satellite and underwater datasets demonstrate that DichroGAN achieves competitive performance compared to state-of-the-art underwater restoration techniques.

cs.CV↗

arXiv2025

GCA-ResUNet: Medical Image Segmentation Using Grouped Coordinate Attention

Accurate segmentation of heterogeneous anatomical structures is pivotal for computer-aided diagnosis and subsequent clinical decision-making. Although U-Net based convolutional neural networks have achieved remarkable progress, their intrinsic locality and largely homogeneous attention formulations often limit the modeling of long-range contextual dependencies, especially in multi-organ scenarios and low-contrast regions. Transformer-based architectures mitigate this issue by leveraging global self-attention, but they usually require higher computational resources and larger training data, which may impede deployment in resource-constrained clinical environments.In this paper, we propose GCA-ResUNet, an efficient medical image segmentation framework equipped with a lightweight and plug-and-play Grouped Coordinate Attention (GCA) module. The proposed GCA decouples channel-wise context modeling into multiple groups to explicitly account for semantic heterogeneity across channels, and integrates direction-aware coordinate encoding to capture structured spatial dependencies along horizontal and vertical axes. This design enhances global representation capability while preserving the efficiency advantages of CNN backbones. Extensive experiments on two widely used benchmarks, Synapse and ACDC, demonstrate that GCA-ResUNet achieves Dice scores of 86.11% and 92.64%, respectively, outperforming a range of representative CNN and Transformer-based methods, including Swin-UNet and TransUNet. In particular, GCA-ResUNet yields consistent improvements in delineating small anatomical structures with complex boundaries. These results indicate that the proposed approach provides a favorable trade-off between segmentation accuracy and computational efficiency, offering a practical and scalable solution for clinical deployment.

cs.CV↗

arXiv2025

Skyrmion and Meron Crystals in Intermetallic Gd$_3$Ru$_4$Al$_{12}$: Microscopic Model Insights into Chiral Phases

Topological spin textures in frustrated intermetallics hold great promise for spintronics applications. However, understanding their origin and properties remains a significant challenge due to competing and often long-range interactions mediated by conduction electrons. Here, by combining neutron scattering experiments with theoretical modeling via unprecedented multi-target fits that further incorporate the ferromagnentic resonance data and magnetization curve, we construct a realistic microscopic model for the prototypical intermetallic skyrmion host \text{Gd}$_3$\text{Ru}$_4$\text{Al}$_{12}$. Beyond magnetic frustration, we identify the competition between dipolar interactions and easy-plane single-ion anisotropy as a key ingredient for stabilizing the rich chiral magnetic phases observed in this compound -- including a hexagonal skyrmion crystal and two distinct meron crystals. Remarkably, the meron crystal in lower field is revealed to be commensurate with the underlying lattice, and its unique three-meron-one-antimeron spin texture is verified by the polarized x-ray diffraction data. At elevated temperatures, the short-range spin correlations in \text{Gd}$_3$\text{Ru}$_4$\text{Al}$_{12}$ are well described by a codimension-two spiral spin-liquid. Perturbations from staggered Dzyaloshinskii-Moriya interactions give rise to chiral fluctuations that account for the temperature and field dependence of the anomalous Hall response. Our results highlight the unique power of neutron scattering, especially when combined with complementary experimental techniques, to unravel complex magnetic phase transitions and provide new insights into the rich variety of topological spin textures in frustrated systems.

cond-mat.str-el↗

arXiv2025

GCA-ResUNet:Image segmentation in medical images using grouped coordinate attention

Medical image segmentation underpins computer-aided diagnosis and therapy by supporting clinical diagnosis, preoperative planning, and disease monitoring. While U-Net style convolutional neural networks perform well due to their encoder-decoder structures with skip connections, they struggle to capture long-range dependencies. Transformer-based variants address global context but often require heavy computation and large training datasets. This paper proposes GCA-ResUNet, an efficient segmentation network that integrates Grouped Coordinate Attention (GCA) into ResNet-50 residual blocks. GCA uses grouped coordinate modeling to jointly encode global dependencies across channels and spatial locations, strengthening feature representation and boundary delineation while adding minimal parameter and FLOP overhead compared with self-attention. On the Synapse dataset, GCA-ResUNet achieves a Dice score of 86.11%, and on the ACDC dataset, it reaches 92.64%, surpassing several state-of-the-art baselines while maintaining fast inference and favorable computational efficiency. These results indicate that GCA offers a practical way to enhance convolutional architectures with global modeling capability, enabling high-accuracy and resource-efficient medical image segmentation.

cs.CV↗

arXiv2025

Backdoor Attacks and Defenses in Computer Vision Domain: A Survey

Backdoor (trojan) attacks embed hidden, controllable behaviors into machine-learning models so that models behave normally on benign inputs but produce attacker-chosen outputs when a trigger is present. This survey reviews the rapidly growing literature on backdoor attacks and defenses in the computer-vision domain. We introduce a multi-dimensional taxonomy that organizes attacks and defenses by injection stage (dataset poisoning, model/parameter modification, inference-time injection), trigger type (patch, blended/frequency, semantic, transformation), labeling strategy (dirty-label vs. clean-label / feature-collision), representation stage (instance-specific, manifold/class-level, neuron/parameter hijacking, distributed encodings), and target task (classification, detection, segmentation, video, multimodal). For each axis we summarize representative methods, highlight evaluation practices, and discuss where defenses succeed or fail. For example, many classical sanitization and reverse-engineering tools are effective against reusable patch attacks but struggle with input-aware, sample-specific, or parameter-space backdoors and with transfer via compromised pre-trained encoders or hardware bit-flips. We synthesize trends, identify persistent gaps (supply-chain and hardware threats, certifiable defenses, cross-task benchmarks), and propose practical guidelines for threat-aware evaluation and layered defenses. This survey aims to orient researchers and practitioners to the current threat landscape and pressing research directions in secure computer vision.

cs.CR↗

arXiv2025

CoEmoGen: Towards Semantically-Coherent and Scalable Emotional Image Content Generation

Emotional Image Content Generation (EICG) aims to generate semantically clear and emotionally faithful images based on given emotion categories, with broad application prospects. While recent text-to-image diffusion models excel at generating concrete concepts, they struggle with the complexity of abstract emotions. There have also emerged methods specifically designed for EICG, but they excessively rely on word-level attribute labels for guidance, which suffer from semantic incoherence, ambiguity, and limited scalability. To address these challenges, we propose CoEmoGen, a novel pipeline notable for its semantic coherence and high scalability. Specifically, leveraging multimodal large language models (MLLMs), we construct high-quality captions focused on emotion-triggering content for context-rich semantic guidance. Furthermore, inspired by psychological insights, we design a Hierarchical Low-Rank Adaptation (HiLoRA) module to cohesively model both polarity-shared low-level features and emotion-specific high-level semantics. Extensive experiments demonstrate CoEmoGen's superiority in emotional faithfulness and semantic coherence from quantitative, qualitative, and user study perspectives. To intuitively showcase scalability, we curate EmoArt, a large-scale dataset of emotionally evocative artistic images, providing endless inspiration for emotion-driven artistic creation. The dataset and code are available at https://github.com/yuankaishen2001/CoEmoGen.

cs.CV↗

arXiv2025

Unlocking Excellence: The Impact of Voucher Incentives on Cybersecurity Education

While voucher incentives have been popular for primary and secondary schools, they are less used in higher education. In this study, we leverage industry voucher incentives to inspire students in cybersecurity education (CSE). We adopt a 100% portfolio-based assessment strategy, where students can freely select their target grades in the investigated unit. We purposely design one of the high distinction (HD) tasks to be obtaining an industry certificate and provide vouchers to those who can accomplish a predefined set of tasks before a midpoint. The voucher recipients will use the voucher to access the industry certificate training materials and sit the certificate exam for free. Passing the certificate exam is one of the conditions for gaining an HD grade. Our survey and interviews reveal a substantial influence of voucher incentives on students' career aspirations. In light of the findings, recommendations on adopting voucher incentives in CSE or broader ICT education are offered for institutions and researchers.

cs.HC↗

arXiv2025

Can human clinical rationales improve the performance and explainability of clinical text classification models?

AI-driven clinical text classification is vital for explainable automated retrieval of population-level health information. This work investigates whether human-based clinical rationales can serve as additional supervision to improve both performance and explainability of transformer-based models that automatically encode clinical documents. We analyzed 99,125 human-based clinical rationales that provide plausible explanations for primary cancer site diagnoses, using them as additional training samples alongside 128,649 electronic pathology reports to evaluate transformer-based models for extracting primary cancer sites. We also investigated sufficiency as a way to measure rationale quality for pre-selecting rationales. Our results showed that clinical rationales as additional training data can improve model performance in high-resource scenarios but produce inconsistent behavior when resources are limited. Using sufficiency as an automatic metric to preselect rationales also leads to inconsistent results. Importantly, models trained on rationales were consistently outperformed by models trained on additional reports instead. This suggests that clinical rationales don't consistently improve model performance and are outperformed by simply using more reports. Therefore, if the goal is optimizing accuracy, annotation efforts should focus on labeling more reports rather than creating rationales. However, if explainability is the priority, training models on rationale-supplemented data may help them better identify rationale-like features. We conclude that using clinical rationales as additional training data results in smaller performance improvements and only slightly better explainability (measured as average token-level rationale coverage) compared to training on additional reports.

cs.CL↗

arXiv2025

Regularizing Subspace Redundancy of Low-Rank Adaptation

Low-Rank Adaptation (LoRA) and its variants have delivered strong capability in Parameter-Efficient Transfer Learning (PETL) by minimizing trainable parameters and benefiting from reparameterization. However, their projection matrices remain unrestricted during training, causing high representation redundancy and diminishing the effectiveness of feature adaptation in the resulting subspaces. While existing methods mitigate this by manually adjusting the rank or implicitly applying channel-wise masks, they lack flexibility and generalize poorly across various datasets and architectures. Hence, we propose ReSoRA, a method that explicitly models redundancy between mapping subspaces and adaptively Regularizes Subspace redundancy of Low-Rank Adaptation. Specifically, it theoretically decomposes the low-rank submatrices into multiple equivalent subspaces and systematically applies de-redundancy constraints to the feature distributions across different projections. Extensive experiments validate that our proposed method consistently facilitates existing state-of-the-art PETL methods across various backbones and datasets in vision-language retrieval and standard visual classification benchmarks. Besides, as a training supervision, ReSoRA can be seamlessly integrated into existing approaches in a plug-and-play manner, with no additional inference costs. Code is publicly available at: https://github.com/Lucenova/ReSoRA.

cs.CV↗

arXiv2025

ConSeg: Contextual Backdoor Attack Against Semantic Segmentation

Despite significant advancements in computer vision, semantic segmentation models may be susceptible to backdoor attacks. These attacks, involving hidden triggers, aim to cause the models to misclassify instances of the victim class as the target class when triggers are present, posing serious threats to the reliability of these models. To further explore the field of backdoor attacks against semantic segmentation, in this paper, we propose a simple yet effective backdoor attack called Contextual Segmentation Backdoor Attack (ConSeg). ConSeg leverages the contextual information inherent in semantic segmentation models to enhance backdoor performance. Our method is motivated by an intriguing observation, i.e., when the target class is set as the `co-occurring' class of the victim class, the victim class can be more easily `mis-segmented'. Building upon this insight, ConSeg mimics the contextual information of the target class and rebuilds it in the victim region to establish the contextual relationship between the target class and the victim class, making the attack easier. Our experiments reveal that ConSeg achieves improvements in Attack Success Rate (ASR) with increases of 15.55\%, compared to existing methods, while exhibiting resilience against state-of-the-art backdoor defenses.

cs.CR↗

arXiv2025

Dual Semantic-Aware Network for Noise Suppressed Ultrasound Video Segmentation

Ultrasound imaging is a prevalent diagnostic tool known for its simplicity and non-invasiveness. However, its inherent characteristics often introduce substantial noise, posing considerable challenges for automated lesion or organ segmentation in ultrasound video sequences. To address these limitations, we propose the Dual Semantic-Aware Network (DSANet), a novel framework designed to enhance noise robustness in ultrasound video segmentation by fostering mutual semantic awareness between local and global features. Specifically, we introduce an Adjacent-Frame Semantic-Aware (AFSA) module, which constructs a channel-wise similarity matrix to guide feature fusion across adjacent frames, effectively mitigating the impact of random noise without relying on pixel-level relationships. Additionally, we propose a Local-and-Global Semantic-Aware (LGSA) module that reorganizes and fuses temporal unconditional local features, which capture spatial details independently at each frame, with conditional global features that incorporate temporal context from adjacent frames. This integration facilitates multi-level semantic representation, significantly improving the model's resilience to noise interference. Extensive evaluations on four benchmark datasets demonstrate that DSANet substantially outperforms state-of-the-art methods in segmentation accuracy. Moreover, since our model avoids pixel-level feature dependencies, it achieves significantly higher inference FPS than video-based methods, and even surpasses some image-based models. Code can be found in \href{https://github.com/ZhouL2001/DSANet}{DSANet}

cs.CV↗