arXiv subjects

Zekun Zhou

Publications and source records attributed to Zekun Zhou.

13 recordsLinked to original sources

arXiv2026

Hybrid Gated Attention

Gated attention is an effective approach to mitigate attention sinks and enhance the representational capacity of attention. To further extend its effectiveness-efficiency Pareto frontier, we propose a Hybrid Gated Attention (HyGA) framework that contains three types of gating strategies. Specifically, these gates leverage diverse information from multiple stages of attention, and collaboratively build element-wise/head-wise gating from multiple perspectives, capturing intra-head and cross-head information interactions. Through our hybrid gating components, HyGA could provide multi-source modulation signals, enabling more comprehensive control over information flow and improving the representational capacity of attention. We also introduce low-rank matrix decomposition and learnable attention sink to further enhance training efficiency and stability. In experiments, we evaluate HyGA on widely-used benchmarks based on different backbones. The experimental results show that our HyGA comprehensively improves both training loss and various downstream performances compared with Gated attention. HyGA has also been verified to achieve the best performance at different computation costs, with comprehensive model analyses for better understanding. The proposed HyGA sheds light on a more effective, efficient, and stable attention mechanism.

cs.CL↗

arXiv2026

MPR-GUI: Benchmarking and Enhancing Multilingual Perception and Reasoning in GUI Agents

Large Vision-Language Models (LVLMs) have shown strong potential as multilingual Graphical User Interface (GUI) agents, as evidenced by existing GUI benchmarks. However, these benchmarks exhibit two primary limitations: (1) although Perception and Reasoning (P&R) capabilities are fundamental for GUI agents, current benchmarks lack fine-grained diagnostics to identify which specific capabilities lead to task failures, hindering targeted improvements; (2) existing benchmarks fail to provide a strictly aligned cross-lingual evaluation environment, introducing confounding factors that prevent isolating the language impact on GUI agent performance. To address these issues, we propose the Multilingual P&R GUI Benchmark (MPR-GUI-Bench), featuring strictly aligned environments across six languages and eight fine-grained P&R tasks. Our benchmark reveals consistent P&R gaps between English and non-English settings, particularly on reasoning-intensive tasks. To leverage the superior English P&R capabilities for bridging cross-lingual gaps, we identify layers sensitive to language and propose GUI-XLI, a GUI Cross-Lingual Intervention method that aligns non-English hidden states with their English counterparts at these layers during inference. Experiments show that GUI-XLI effectively reduces the cross-lingual gaps, with an average gain of 6.5% in non-English settings.

cs.AI↗

arXiv2026

AS-Mamba: Asymmetric Self-Guided Mamba Decoupled Iterative Network for Metal Artifact Reduction

Metal artifact significantly degrades Computed Tomography (CT) image quality, impeding accurate clinical diagnosis. However, existing deep learning approaches, such as CNN and Transformer, often fail to explicitly capture the directional geometric features of artifacts, leading to compromised structural restoration. To address these limitations, we propose the Asymmetric Self-Guided Mamba (AS-Mamba) for metal artifact reduction. Specifically, the linear propagation of metal-induced streak artifacts aligns well with the sequential modeling capability of State Space Models (SSMs). Consequently, the Mamba architecture is leveraged to explicitly capture and suppress these directional artifacts. Simultaneously, a frequency domain correction mechanism is incorporated to rectify the global amplitude spectrum, thereby mitigating intensity inhomogeneity caused by beam hardening. Furthermore, to bridge the distribution gap across diverse clinical scenarios, we introduce a self-guided contrastive regularization strategy. Extensive experiments on public andclinical dental CBCT datasets demonstrate that AS-Mamba achieves superior performance in suppressing directional streaks and preserving structural details, validating the effectiveness of integrating physical geometric priors into deep network design.

eess.IV↗

arXiv2026

Visible Singularities Guided Correlation Network for Limited-Angle CT Reconstruction

Limited-angle computed tomography (LACT) offers the advantages of reduced radiation dose and shortened scanning time. Traditional reconstruction algorithms exhibit various inherent limitations in LACT. Currently, most deep learning-based LACT reconstruction methods focus on multi-domain fusion or the introduction of generic priors, failing to fully align with the core imaging characteristics of LACT-such as the directionality of artifacts and directional loss of structural information, which are caused by the absence of projection angles in certain directions. Inspired by the theory of visible and invisible singularities, taking into account the aforementioned core imaging characteristics of LACT, we propose a Visible Singularities Guided Correlation network for LACT reconstruction (VSGC). The design philosophy of VSGC consists of two core steps: First, extract VS edge features from LACT images and focus the model's attention on these VS. Second, establish correlations between the VS edge features and other regions of the image. Additionally, a multi-scale loss function with anisotropic constraint is employed to constrain the model to converge in multiple aspects. Finally, qualitative and quantitative validations are conducted on both simulated and real datasets to verify the effectiveness and feasibility of the proposed design. Particularly, in comparison with alternative methods, VSGC delivers more prominent performance in small angular ranges, with the PSNR improvement of 2.45 dB and the SSIM enhancement of 1.5\%. The code is publicly available at https://github.com/yqx7150/VSGC.

eess.IV↗

arXiv2026

Extendable Generalization Self-Supervised Diffusion for Low-Dose CT Reconstruction

Current methods based on deep learning for self-supervised low-dose CT (LDCT) reconstruction, while reducing the dependence on paired data, face the problem of significantly decreased generalization when training with single-dose data and extending to other doses. To enable dose-extensive generalization using only single-dose projection data for training, this work proposes a novel method of Extendable GENeraLization self-supervised Diffusion (EGenDiff) for low-dose CT reconstruction. Specifically, a contextual subdata self-enhancing similarity strategy is designed to provide an initial prior for the subsequent progress. During training, the initial prior is used to combine knowledge distillation with a deep combination of latent diffusion models for optimizing image details. On the stage of inference, the pixel-wise self-correcting fusion technique is proposed for data fidelity enhancement, resulting in extensive generalization of higher and lower doses or even unseen doses. EGenDiff requires only LDCT projection data for training and testing. Comprehensive evaluation on benchmark datasets, clinical data, photon counting CT data, and across all three anatomical planes (transverse, coronal, and sagittal) demonstrates that EGenDiff enables extendable generalization multi-dose, yielding reconstructions that consistently outperform leading existing methods.

cs.CV↗

arXiv2025

From Hypothesis to Publication: A Comprehensive Survey of AI-Driven Research Support Systems

Research is a fundamental process driving the advancement of human civilization, yet it demands substantial time and effort from researchers. In recent years, the rapid development of artificial intelligence (AI) technologies has inspired researchers to explore how AI can accelerate and enhance research. To monitor relevant advancements, this paper presents a systematic review of the progress in this domain. Specifically, we organize the relevant studies into three main categories: hypothesis formulation, hypothesis validation, and manuscript publication. Hypothesis formulation involves knowledge synthesis and hypothesis generation. Hypothesis validation includes the verification of scientific claims, theorem proving, and experiment validation. Manuscript publication encompasses manuscript writing and the peer review process. Furthermore, we identify and discuss the current challenges faced in these areas, as well as potential future directions for research. Finally, we also offer a comprehensive overview of existing benchmarks and tools across various domains that support the integration of AI into the research process. We hope this paper serves as an introduction for beginners and fosters future research. Resources have been made publicly available at https://github.com/zkzhou126/AI-for-Research.

cs.AI↗

arXiv2025

Physics-informed DeepCT: Sinogram Wavelet Decomposition Meets Masked Diffusion

Diffusion model shows remarkable potential on sparse-view computed tomography (SVCT) reconstruction. However, when a network is trained on a limited sample space, its generalization capability may be constrained, which degrades performance on unfamiliar data. For image generation tasks, this can lead to issues such as blurry details and inconsistencies between regions. To alleviate this problem, we propose a Sinogram-based Wavelet random decomposition And Random mask diffusion Model (SWARM) for SVCT reconstruction. Specifically, introducing a random mask strategy in the sinogram effectively expands the limited training sample space. This enables the model to learn a broader range of data distributions, enhancing its understanding and generalization of data uncertainty. In addition, applying a random training strategy to the high-frequency components of the sinogram wavelet enhances feature representation and improves the ability to capture details in different frequency bands, thereby improving performance and robustness. Two-stage iterative reconstruction method is adopted to ensure the global consistency of the reconstructed image while refining its details. Experimental results demonstrate that SWARM outperforms competing approaches in both quantitative and qualitative performance across various datasets.

eess.IV↗

arXiv2025

Physics-Guided Null-Space Diffusion with Sparse Masking for Corrective Sparse-View CT Reconstruction

Diffusion models have demonstrated remarkable generative capabilities in image processing tasks. We propose a Sparse condition Temporal Rewighted Integrated Distribution Estimation guided diffusion model (STRIDE) for sparse-view CT reconstruction. Specifically, we design a joint training mechanism guided by sparse conditional probabilities to facilitate the model effective learning of missing projection view completion and global information modeling. Based on systematic theoretical analysis, we propose a temporally varying sparse condition reweighting guidance strategy to dynamically adjusts weights during the progressive denoising process from pure noise to the real image, enabling the model to progressively perceive sparse-view information. The linear regression is employed to correct distributional shifts between known and generated data, mitigating inconsistencies arising during the guidance process. Furthermore, we construct a dual-network parallel architecture to perform global correction and optimization across multiple sub-frequency components, thereby effectively improving the model capability in both detail restoration and structural preservation, ultimately achieving high-quality image reconstruction. Experimental results on both public and real datasets demonstrate that the proposed method achieves the best improvement of 2.58 dB in PSNR, increase of 2.37\% in SSIM, and reduction of 0.236 in MSE compared to the best-performing baseline methods. The reconstructed images exhibit excellent generalization and robustness in terms of structural consistency, detail restoration, and artifact suppression.

cs.CV↗

arXiv2025

PWD: Prior-Guided and Wavelet-Enhanced Diffusion Model for Limited-Angle CT

Generative diffusion models have received increasing attention in medical imaging, particularly in limited-angle computed tomography (LACT). Standard diffusion models achieve high-quality image reconstruction but require a large number of sampling steps during inference, resulting in substantial computational overhead. Although skip-sampling strategies have been proposed to improve efficiency, they often lead to loss of fine structural details. To address this issue, we propose a prior information embedding and wavelet feature fusion fast sampling diffusion model for LACT reconstruction. The PWD enables efficient sampling while preserving reconstruction fidelity in LACT, and effectively mitigates the degradation typically introduced by skip-sampling. Specifically, during the training phase, PWD maps the distribution of LACT images to that of fully sampled target images, enabling the model to learn structural correspondences between them. During inference, the LACT image serves as an explicit prior to guide the sampling trajectory, allowing for high-quality reconstruction with significantly fewer steps. In addition, PWD performs multi-scale feature fusion in the wavelet domain, effectively enhancing the reconstruction of fine details by leveraging both low-frequency and high-frequency information. Quantitative and qualitative evaluations on clinical dental arch CBCT and periapical datasets demonstrate that PWD outperforms existing methods under the same sampling condition. Using only 50 sampling steps, PWD achieves at least 1.7 dB improvement in PSNR and 10% gain in SSIM.

eess.IV↗

arXiv2025

FD-DiT: Frequency Domain-Directed Diffusion Transformer for Low-Dose CT Reconstruction

Low-dose computed tomography (LDCT) reduces radiation exposure but suffers from image artifacts and loss of detail due to quantum and electronic noise, potentially impacting diagnostic accuracy. Transformer combined with diffusion models has been a promising approach for image generation. Nevertheless, existing methods exhibit limitations in preserving finegrained image details. To address this issue, frequency domain-directed diffusion transformer (FD-DiT) is proposed for LDCT reconstruction. FD-DiT centers on a diffusion strategy that progressively introduces noise until the distribution statistically aligns with that of LDCT data, followed by denoising processing. Furthermore, we employ a frequency decoupling technique to concentrate noise primarily in high-frequency domain, thereby facilitating effective capture of essential anatomical structures and fine details. A hybrid denoising network is then utilized to optimize the overall data reconstruction process. To enhance the capability in recognizing high-frequency noise, we incorporate sliding sparse local attention to leverage the sparsity and locality of shallow-layer information, propagating them via skip connections for improving feature representation. Finally, we propose a learnable dynamic fusion strategy for optimal component integration. Experimental results demonstrate that at identical dose levels, LDCT images reconstructed by FD-DiT exhibit superior noise and artifact suppression compared to state-of-the-art methods.

eess.IV↗

arXiv2025

Symmetry-Broken Kondo Screening and Zero-Energy Mode in the Kagome Superconductor CsV3Sb5

The quantum states of matter reorganize themselves in response to defects, giving rise to emergent local excitations that imprint unique characteristics of the host states. While magnetic impurities are known to generate Kondo screening in a Fermi liquid and Yu-Shiba-Rusinov (YSR) states in a conventional superconductor, it remains unclear whether they can evoke distinct phenomena in the kagome superconductor AV3Sb5 (where A is K, Rb or Cs), which may host an orbital-antiferromagnetic charge density wave (CDW) state and an unconventional superconducting state driven by the convergence of topology, geometric frustration and electron correlations. In this work, we visualize the local density of states induced near various types of impurities in both the CDW and superconducting phases of CsV3-xMxSb5 (M = Ta, Cr) using scanning tunneling microscopy. We observe Kondo resonance states near magnetic Cr dopants. Notably, unlike in any known metal or CDW compound, the spatial pattern of Kondo screening breaks all in-plane mirror symmetries of the kagome lattice, suggesting an electronic chirality due to putative orbital loop currents. While Cooper pairs show relative insensitivity to nonmagnetic impurities, native V vacancies with weak magnetic moments induce a pronounced zero-bias conductance peak (ZBCP). This ZBCP coexists with trivial YSR states within the superconducting gap and does not split in energy with increasing tunneling transmission, tending instead to saturate. This behavior is reminiscent of signature of Majorana zero modes, which could be trapped by a sign-change boundary in the superconducting order parameter near a V vacancy, consistent with a surface topological superconducting state. Our findings provide a new approach to exploring novel quantum states on kagome lattices.

cond-mat.supr-con↗

arXiv2024

Discrete Modeling via Boundary Conditional Diffusion Processes

We present an novel framework for efficiently and effectively extending the powerful continuous diffusion processes to discrete modeling. Previous approaches have suffered from the discrepancy between discrete data and continuous modeling. Our study reveals that the absence of guidance from discrete boundaries in learning probability contours is one of the main reasons. To address this issue, we propose a two-step forward process that first estimates the boundary as a prior distribution and then rescales the forward trajectory to construct a boundary conditional diffusion model. The reverse process is proportionally adjusted to guarantee that the learned contours yield more precise discrete data. Experimental results indicate that our approach achieves strong performance in both language modeling and discrete image generation tasks. In language modeling, our approach surpasses previous state-of-the-art continuous diffusion language models in three translation tasks and a summarization task, while also demonstrating competitive performance compared to auto-regressive transformers. Moreover, our method achieves comparable results to continuous diffusion models when using discrete ordinal pixels and establishes a new state-of-the-art for categorical image generation on the Cifar-10 dataset.

cs.LG↗

arXiv2022

ConvNeXt-backbone HoVerNet for nuclei segmentation and classification

This manuscript gives a brief description of the algorithm used to participate in CoNIC Challenge 2022. After the baseline was made available, we follow the method in it and replace the ResNet baseline with ConvNeXt one. Moreover, we propose to first convert RGB space to Haematoxylin-Eosin-DAB(HED) space, then use Haematoxylin composition of origin image to smooth semantic one hot label. Afterwards, nuclei distribution of train and valid set are explored to select the best fold split for training model for final test phase submission. Results on validation set shows that even with channel of each stage smaller in number, HoVerNet with ConvNeXt-tiny backbone still improves the mPQ+ by 0.04 and multi r2 by 0.0144

eess.IV↗