arXiv subjects

Hui Xu

Publications and source records attributed to Hui Xu.

At least 55 records · Page 3Linked to original sources

arXiv2025

LOCO: A Low-Cost SNU-Self-Resilient Latch Using an Output-Split C-Element

As the CMOS technology enters nanometer scales, integrated circuits (ICs) become increasingly sensitive to radiation-induced soft errors, which can corrupt the state of storage elements and cause severe reliability issues. Many hardened designs have been proposed to mitigate soft errors by using filtering elements. However, existing filtering elements only protect their inputs against soft errors and leave their outputs unprotected. Therefore, additional filtering elements must be added to protect outputs, resulting in extra overhead. In this paper, we first propose a novel Output-Split C-element (OSC) to protect both its input and output nodes, and then a novel LOw-COst single-node-upset (SNU) self-resilient latch (LOCO) to use OSCs to achieve both soft error resilience and low overhead. The usage of OSCs effectively reduce the short-circuit current of the LOCO latch during switching activities. Furthermore, the usage of clock gating and high-speed path reduces power consumption and delay, respectively. Compared with state-of-the-art SNU-resilient hardened designs, the LOCO latch achieves 19% fewer transistors, 63.58% lower power, 74% less delay, and 92% lower power-delay-product (PDP) on average. In addition, the LOCO latch exhibits better stability under variations in PVT (Process, Voltage, and Temperature).

cs.GT↗

arXiv2025

From Classical Machine Learning to Emerging Foundation Models: Review on Multimodal Data Integration for Cancer Research

Cancer research is increasingly driven by the integration of diverse data modalities, spanning from genomics and proteomics to imaging and clinical factors. However, extracting actionable insights from these vast and heterogeneous datasets remains a key challenge. The rise of foundation models (FMs) -- large deep-learning models pretrained on extensive amounts of data serving as a backbone for a wide range of downstream tasks -- offers new avenues for discovering biomarkers, improving diagnosis, and personalizing treatment. This paper presents a comprehensive review of widely adopted integration strategies of multimodal data to assist advance the computational approaches for data-driven discoveries in oncology. We examine emerging trends in machine learning (ML) and deep learning (DL), including methodological frameworks, validation protocols, and open-source resources targeting cancer subtype classification, biomarker discovery, treatment guidance, and outcome prediction. This study also comprehensively covers the shift from traditional ML to FMs for multimodal integration. We present a holistic view of recent FMs advancements and challenges faced during the integration of multi-omics with advanced imaging data. We identify the state-of-the-art FMs, publicly available multi-modal repositories, and advanced tools and methods for data integration. We argue that current state-of-the-art integrative methods provide the essential groundwork for developing the next generation of large-scale, pre-trained models poised to further revolutionize oncology. To the best of our knowledge, this is the first review to systematically map the transition from conventional ML to advanced FM for multimodal data integration in oncology, while also framing these developments as foundational for the forthcoming era of large-scale AI models in cancer research.

q-bio.QM↗

arXiv2025

MAQuA: Adaptive Question-Asking for Multidimensional Mental Health Screening using Item Response Theory

Recent advances in large language models (LLMs) offer new opportunities for scalable, interactive mental health assessment, but excessive querying by LLMs burdens users and is inefficient for real-world screening across transdiagnostic symptom profiles. We introduce MAQuA, an adaptive question-asking framework for simultaneous, multidimensional mental health screening. Combining multi-outcome modeling on language responses with item response theory (IRT) and factor analysis, MAQuA selects the questions with most informative responses across multiple dimensions at each turn to optimize diagnostic information, improving accuracy and potentially reducing response burden. Empirical results on a novel dataset reveal that MAQuA reduces the number of assessment questions required for score stabilization by 50-87% compared to random ordering (e.g., achieving stable depression scores with 71% fewer questions and eating disorder scores with 85% fewer questions). MAQuA demonstrates robust performance across both internalizing (depression, anxiety) and externalizing (substance use, eating disorder) domains, with early stopping strategies further reducing patient time and burden. These findings position MAQuA as a powerful and efficient tool for scalable, nuanced, and interactive mental health screening, advancing the integration of LLM-based agents into real-world clinical workflows.

cs.CL↗

arXiv2025

A Bit Level Weight Reordering Strategy Based on Column Similarity to Explore Weight Sparsity in RRAM-based NN Accelerator

Compute-in-Memory (CIM) and weight sparsity are two effective techniques to reduce data movement during Neural Network (NN) inference. However, they can hardly be employed in the same accelerator simultaneously because CIM requires structural compute patterns which are disrupted in sparse NNs. In this paper, we partially solve this issue by proposing a bit level weight reordering strategy which can realize compact mapping of sparse NN weight matrices onto Resistive Random Access Memory (RRAM) based NN Accelerators (RRAM-Acc). In specific, when weights are mapped to RRAM crossbars in a binary complement manner, we can observe that, which can also be mathematically proven, bit-level sparsity and similarity commonly exist in the crossbars. The bit reordering method treats bit sparsity as a special case of bit similarity, reserve only one column in a pair of columns that have identical bit values, and then map the compressed weight matrices into Operation Units (OU). The performance of our design is evaluated with typical NNs. Simulation results show a 61.24% average performance improvement and 1.51x-2.52x energy savings under different sparsity ratios, with only slight overhead compared to the state-of-the-art design.

cs.AR↗

arXiv2025

Segmented Exponent Alignment and Dynamic Wordline Activation for Floating-Point Analog CIM Macros

With the rise of compute-in-memory (CIM) accelerators, floating-point multiply-and-accumulate (FP-MAC) operations have gained extensive attention for their higher accuracy over integer MACs in neural networks. However, the hardware overhead caused by exponent comparison and mantissa alignment, along with the delay introduced by bit-serial input methods, remains a hinder to implement FP-MAC efficiently. In view of this, we propose Segmented Exponent Alignment (SEA) and Dynamic Wordline Activation (DWA) strategies. SEA exploits the observation that input exponents are often clustered around zero or within a narrow range. By segmenting the exponent space and aligning mantissas accordingly, SEA eliminates the need for maximum exponent detection and reduces input mantissa shifting, and thus reduces the processing latency. DWA further reduces latency and maintains accuracy by activating wordlines based on the exponent segments defined by SEA. Simulation results demonstrate that, when compared with conventional comparison tree based maximum exponent alignment method, our approach saves 63.8\% power consumption, and achieves a 40.87\% delay reduction on the VGG16-CIFAR10 benchmark.

cs.ET↗

arXiv2025

LISA: A Layer-wise Integration and Suppression Approach for Hallucination Mitigation in Multimodal Large Language Models

Multimodal Large Language Models (MLLMs) excel in vision-language tasks such as image captioning but remain prone to object hallucinations, where they describe objects that do not appear in the image. To mitigate this, we propose LISA, a Layer-wise Integration and Suppression Approach. LISA leverages the layer-wise functional roles in MLLMs: shallow layers provide visual grounding, middle layers encode semantics, and deep layers tend to amplify spurious signals. First, layer-wise spectral modulation stabilizes attention by suppressing over-amplified activations in deeper layers while preserving alignment cues in earlier layers. Second, token-level logits from selected layers are fused via anchor-based routing, with token-wise anchor selection and soft logit fusion enabling adaptive integration during decoding. LISA is fully plug-and-play and can be seamlessly integrated into existing MLLMs, including Qwen2.5-VL. Experiments on multiple benchmarks show that LISA reduces hallucinations by up to 53.6% in $\text{CHAIR}_\text{I}$ and improves POPE F1 by up to 5.1%, demonstrating strong generalization across models and tasks. Our code is available at https://github.com/zhlisa1010-eng/LISA.

cs.CV↗

arXiv2025

Negative Entity Suppression for Zero-Shot Captioning with Synthetic Images

Text-only training provides an attractive approach to address data scarcity challenges in zero-shot image captioning (ZIC), avoiding the expense of collecting paired image-text annotations. However, although these approaches perform well within training domains, they suffer from poor cross-domain generalization, often producing hallucinated content when encountering novel visual environments. Retrieval-based methods attempt to mitigate this limitation by leveraging external knowledge, but they can paradoxically exacerbate hallucination when retrieved captions contain entities irrelevant to the inputs. We introduce the concept of negative entities--objects that appear in generated caption but are absent from the input--and propose Negative Entity Suppression (NES) to tackle this challenge. NES seamlessly integrates three stages: (1) it employs synthetic images to ensure consistent image-to-text retrieval across both training and inference; (2) it filters negative entities from retrieved content to enhance accuracy; and (3) it applies attention-level suppression using identified negative entities to further minimize the impact of hallucination-prone features. Evaluation across multiple benchmarks demonstrates that NES maintains competitive in-domain performance while improving cross-domain transfer and reducing hallucination rates, achieving new state-of-the-art results in ZIC. Our code is available at https://github.com/nidongpinyinme/NESCap.

cs.CV↗

arXiv2025

OVERT: A Benchmark for Over-Refusal Evaluation on Text-to-Image Models

Text-to-Image (T2I) models have achieved remarkable success in generating visual content from text inputs. Although multiple safety alignment strategies have been proposed to prevent harmful outputs, they often lead to overly cautious behavior -- rejecting even benign prompts -- a phenomenon known as $\textit{over-refusal}$ that reduces the practical utility of T2I models. Despite over-refusal having been observed in practice, there is no large-scale benchmark that systematically evaluates this phenomenon for T2I models. In this paper, we present an automatic workflow to construct synthetic evaluation data, resulting in OVERT ($\textbf{OVE}$r-$\textbf{R}$efusal evaluation on $\textbf{T}$ext-to-image models), the first large-scale benchmark for assessing over-refusal behaviors in T2I models. OVERT includes 4,600 seemingly harmful but benign prompts across nine safety-related categories, along with 1,785 genuinely harmful prompts (OVERT-unsafe) to evaluate the safety-utility trade-off. Using OVERT, we evaluate several leading T2I models and find that over-refusal is a widespread issue across various categories (Figure 1), underscoring the need for further research to enhance the safety alignment of T2I models without compromising their functionality. As a preliminary attempt to reduce over-refusal, we explore prompt rewriting; however, we find it often compromises faithfulness to the meaning of the original prompts. Finally, we demonstrate the flexibility of our generation framework in accommodating diverse safety requirements by generating customized evaluation data adapting to user-defined policies.

cs.LG↗

arXiv2025

SPENet: Self-guided Prototype Enhancement Network for Few-shot Medical Image Segmentation

Few-Shot Medical Image Segmentation (FSMIS) aims to segment novel classes of medical objects using only a few labeled images. Prototype-based methods have made significant progress in addressing FSMIS. However, they typically generate a single global prototype for the support image to match with the query image, overlooking intra-class variations. To address this issue, we propose a Self-guided Prototype Enhancement Network (SPENet). Specifically, we introduce a Multi-level Prototype Generation (MPG) module, which enables multi-granularity measurement between the support and query images by simultaneously generating a global prototype and an adaptive number of local prototypes. Additionally, we observe that not all local prototypes in the support image are beneficial for matching, especially when there are substantial discrepancies between the support and query images. To alleviate this issue, we propose a Query-guided Local Prototype Enhancement (QLPE) module, which adaptively refines support prototypes by incorporating guidance from the query image, thus mitigating the negative effects of such discrepancies. Extensive experiments on three public medical datasets demonstrate that SPENet outperforms existing state-of-the-art methods, achieving superior performance.

cs.CV↗

arXiv2025

Patch Progression Masked Autoencoder with Fusion CNN Network for Classifying Evolution Between Two Pairs of 2D OCT Slices

Age-related Macular Degeneration (AMD) is a prevalent eye condition affecting visual acuity. Anti-vascular endothelial growth factor (anti-VEGF) treatments have been effective in slowing the progression of neovascular AMD, with better outcomes achieved through timely diagnosis and consistent monitoring. Tracking the progression of neovascular activity in OCT scans of patients with exudative AMD allows for the development of more personalized and effective treatment plans. This was the focus of the Monitoring Age-related Macular Degeneration Progression in Optical Coherence Tomography (MARIO) challenge, in which we participated. In Task 1, which involved classifying the evolution between two pairs of 2D slices from consecutive OCT acquisitions, we employed a fusion CNN network with model ensembling to further enhance the model's performance. For Task 2, which focused on predicting progression over the next three months based on current exam data, we proposed the Patch Progression Masked Autoencoder that generates an OCT for the next exam and then classifies the evolution between the current OCT and the one generated using our solution from Task 1. The results we achieved allowed us to place in the Top 10 for both tasks. Some team members are part of the same organization as the challenge organizers; therefore, we are not eligible to compete for the prize.

cs.CV↗

arXiv2025

KELPS: A Framework for Verified Multi-Language Autoformalization via Semantic-Syntactic Alignment

Modern large language models (LLMs) show promising progress in formalizing informal mathematics into machine-verifiable theorems. However, these methods still face bottlenecks due to the limited quantity and quality of multilingual parallel corpora. In this paper, we propose a novel neuro-symbolic framework KELPS (Knowledge-Equation based Logical Processing System) to address these problems. KELPS is an iterative framework for translating, synthesizing, and filtering informal data into multiple formal languages (Lean, Coq, and Isabelle). First, we translate natural language into Knowledge Equations (KEs), a novel language that we designed, theoretically grounded in assertional logic. Next, we convert them to target languages through rigorously defined rules that preserve both syntactic structure and semantic meaning. This process yielded a parallel corpus of over 60,000 problems. Our framework achieves 88.9% syntactic accuracy (pass@1) on MiniF2F, outperforming SOTA models such as Deepseek-V3 (81%) and Herald (81.3%) across multiple datasets. All datasets and codes are available in the supplementary materials.

cs.CL↗

arXiv2025

LFR-PINO: A Layered Fourier Reduced Physics-Informed Neural Operator for Parametric PDEs

Physics-informed neural operators have emerged as a powerful paradigm for solving parametric partial differential equations (PDEs), particularly in the aerospace field, enabling the learning of solution operators that generalize across parameter spaces. However, existing methods either suffer from limited expressiveness due to fixed basis/coefficient designs, or face computational challenges due to the high dimensionality of the parameter-to-weight mapping space. We present LFR-PINO, a novel physics-informed neural operator that introduces two key innovations: (1) a layered hypernetwork architecture that enables specialized parameter generation for each network layer, and (2) a frequency-domain reduction strategy that significantly reduces parameter count while preserving essential spectral features. This design enables efficient learning of a universal PDE solver through pre-training, capable of directly handling new equations while allowing optional fine-tuning for enhanced precision. The effectiveness of this approach is demonstrated through comprehensive experiments on four representative PDE problems, where LFR-PINO achieves 22.8%-68.7% error reduction compared to state-of-the-art baselines. Notably, frequency-domain reduction strategy reduces memory usage by 28.6%-69.3% compared to Hyper-PINNs while maintaining solution accuracy, striking an optimal balance between computational efficiency and solution fidelity.

cs.LG↗

arXiv2025

Agile Orchestration at Will: An Entire Smart Service-Based Security Architecture Towards 6G

The upcoming 6G will fundamentally reshape mobile networks beyond communications, unlocking a multitude of applications that were once considered unimaginable. Meanwhile, security and resilience are especially highlighted in the 6G design principles. However, safeguarding 6G networks will be quite challenging due to various known and unknown threats from highly heterogeneous networks and diversified security requirements of distinct use cases, calling for a comprehensive re-design of security architecture. This motivates us to propose ES3A (Entire Smart Service-based Security Architecture), a novel security architecture for 6G networks. Specifically, we first discuss six high-level principles of our ES3A that include hierarchy, flexibility, scalability, resilience, endogeny, and trust and privacy. With these goals in mind, we then introduce three guidelines from a deployment perspective, envisioning our ES3A that offers service-based security, end-to-end protection, and smart security automation for 6G networks. Our architecture consists of three layers and three domains. It relies on a two-stage orchestration mechanism to tailor smart security strategies for customized protection in high-dynamic 6G networks, thereby addressing the aforementioned challenges. Finally, we prototype the proposed ES3A on a real-world radio system based on Software-Defined Radio (SDR). Experiments show the effectiveness of our ES3A. We also provide a case to show the superiority of our architecture.

cs.NI↗

arXiv2025

Structure theorems of commuting transformations and minimal $\mathbb{R}$-flows

In this paper, we develop several structure theorems concerning commuting transformations and minimal $\mathbb{R}$-flows. Specifically, we show that if $(X,S)$, $(X,T)$ are minimal systems with $S$ and $T$ being commutative, then they possess an identical higher-order regionally proximal relation. Consequently, both $(X, S)$ and $(X, T)$ share the same increasing sequence of pro-nilfactors. For minimal $\mathbb{R}$-flows, we introduce the concept of higher-order regionally proximal relations and nilfactors, and establish that nilfactors are characteristic factors for minimal $\mathbb{R}$-flows, up to almost one to one extensions.

math.DS↗

arXiv2025

SecureNT: Smart Topology Obfuscation for Privacy-Aware Network Monitoring

Network tomography plays a crucial role in network monitoring and management, where network topology serves as the fundamental basis for various tomography tasks including traffic matrix estimation and link performance inference. The topology information, however, can be inferred through end-to-end measurements using various inference algorithms, posing significant security risks to network infrastructure. While existing protection methods attempt to secure topology information by modifying end-to-end measurements, they often require complex computation and sophisticated modification strategies, making real-time protection challenging. Moreover, these modifications typically render the measurements unusable for network monitoring, even by trusted users. This paper presents a novel privacy-preserving framework that addresses these limitations. Our approach provides efficient topology protection while maintaining the utility of measurements for authorized network monitoring. Through extensive evaluation on both simulated and real-world networks, we demonstrate that our framework achieves superior privacy protection compared to existing methods while enabling trusted users to effectively monitor network performance. Our solution offers a practical approach for organizations to protect sensitive topology information without sacrificing their network monitoring capabilities.

cs.CR↗

arXiv2025

Enhanced RMT estimator for signal number estimation in the presence of colored noise

The subspace-based techniques are widely utilized in various scientific fields, and they need accurate estimation of the signal subspace dimension. The classic RMT estimator for model order estimation based on random matrix theory assumes that the noise is white Gaussian, and performs poorly in the presence of colored noise with unknown covariance matrix. In the presence of colored noise, the multivariate regression (MV-R) algorithm models the source detection as a multivariate regression problem and infers the model order from the covariance matrix of the residual error. However, the MV-R algorithm requires that the noise is sufficiently weaker than the signal. In order to deal with these problems, this paper proposes a novel signal number estimation algorithm in the presence of colored noise based on the analysis of the behavior of information theoretic criteria. Firstly, a first criterion is defined as the ratio of the current eigenvalue and the mean of the next ones, and its properties is analyzed with respect to the over-modeling and under-modeling. Moreover, a second criterion is designed as the ratio of the current value and the next value of the first criterion, and its properties is analyzed with respect to the over-modeling and under-modeling. Then, a novel enhanced RMT estimator is proposed for signal number estimation by analyzing the detection properties among the signal number estimates obtained by these two criteria, the MV-R estimator and the RMT estimator to sequentially determine whether the eigenvalue being tested is arising from a signal or from noise. Finally, simulation results are presented to illustrate that the proposed enhanced RMT estimator has better estimation performance than the existing methods.

cs.IT↗

arXiv2025

DB-GNN: Dual-Branch Graph Neural Network with Multi-Level Contrastive Learning for Jointly Identifying Within- and Cross-Frequency Coupled Brain Networks

Within-frequency coupling (WFC) and cross-frequency coupling (CFC) in brain networks reflect neural synchronization within the same frequency band and cross-band oscillatory interactions, respectively. Their synergy provides a comprehensive understanding of neural mechanisms underlying cognitive states such as emotion. However, existing multi-channel EEG studies often analyze WFC or CFC separately, failing to fully leverage their complementary properties. This study proposes a dual-branch graph neural network (DB-GNN) to jointly identify within- and cross-frequency coupled brain networks. Firstly, DBGNN leverages its unique dual-branch learning architecture to efficiently mine global collaborative information and local cross-frequency and within-frequency coupling information. Secondly, to more fully perceive the global information of cross-frequency and within-frequency coupling, the global perception branch of DB-GNN adopts a Transformer architecture. To prevent overfitting of the Transformer architecture, this study integrates prior within- and cross-frequency coupling information into the Transformer inference process, thereby enhancing the generalization capability of DB-GNN. Finally, a multi-scale graph contrastive learning regularization term is introduced to constrain the global and local perception branches of DB-GNN at both graph-level and node-level, enhancing its joint perception ability and further improving its generalization performance. Experimental validation on the emotion recognition dataset shows that DB-GNN achieves a testing accuracy of 97.88% and an F1- score of 97.87%, reaching the state-of-the-art performance.

q-bio.NC↗

arXiv2025

On systems disjoint from all minimal systems

Recently, Górska, Lemańczyk, and de la Rue characterized the class of automorphisms disjoint from all ergodic automorphisms. Inspired by their work, we provide several characterizations of systems that are disjoint from all minimal systems. For a topological dynamical system $(X,T)$, it is disjoint from all minimal systems if and only if there exist minimal subsets $(M_i)_{i\in\mathbb{N}}$ of $X$ whose union is dense in $X$ and each of them is disjoint from $X$ (we also provide a measure-theoretical analogy of the result). For a semi-simple system $(X,T)$, it is disjoint from all minimal systems if and only if there exists a dense $G_δ$ set $Ω$ in $X \times X$ such that for every pair $(x_1,x_2) \in Ω$, the subsystems $\overline{\mathcal{O}}(x_1,T)$ and $\overline{\mathcal{O}}(x_2,T)$ are disjoint. Furthermore, for a general system a characterization similar to the ergodic case is obtained.

math.DS↗