Author name cluster

Zhenyu Zhao

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

1 author row

JBHI Journal 2026 Journal Article

Attention-Enhanced Temporal and Spatial Feature Extraction Network for ADHD Diagnosis based on fMRI

Dandan Li
Zhenyu Zhao
Jiangyang Hao
Xingwang Dong
Yating Zhang
Jie Xiang
Bin Wang

Attention Deficit Hyperactivity Disorder (ADHD) is a prevalent neurodevelopmental disorder, and accurate diagnosis is critical for ensuring timely intervention. The integration of deep learning and fMRI can effectively explore the abnormal spatiotemporal features of ADHD. However, existing deep learning models are unable to fully capture the temporal dependence and spatial consistency of fMRI data, primarily due to insufficient modeling of multi-scale temporal dependencies and the lack of explicit interaction between static and dynamic brain networks, resulting in poor diagnostic performance for ADHD. To comprehensively and efficiently extract the spatiotemporal features of fMRI signals, we propose an Attention-Enhanced Spatiotemporal Feature Extraction Network (AE-STEN), which comprises a Temporal Cross-scale Convolutional Attention Module (TCAM), a Spatial Collaborative Attention-Guided Graph Representation Module (SCGRM), and a Spatial-Temporal KAN Network (STKAN). TCAM is designed to capture short- and long-term dependencies in fMRI time series by jointly modeling local transient fluctuations and global temporal dependencies. SCGRM effectively extracts consistent spatial features from both dynamic and static fMRI data by explicitly modeling their collaborative interaction rather than treating them independently. STKAN integrates the extracted spatiotemporal features for final classification. Experiments on the ADHD-200 dataset, involving 747 subjects across seven sites, demonstrate that AE-STEN achieves a classification accuracy of up to 76. 06% ± 0. 65%. Moreover, AE-STEN identifies brain regions associated with ADHD consistent with clinical findings, indicating strong interpretability and highlighting the model's potential for clinical application.

Details DOI

NeurIPS Conference 2025 Conference Paper

LEDiT: Your Length-Extrapolatable Diffusion Transformer without Positional Encoding

Shen Zhang
Siyuan Liang
Yaning Tan
Zhaowei Chen
Linze Li
Ge Wu
Yuhao Chen
Shuheng Li

Diffusion transformers (DiTs) struggle to generate images at resolutions higher than their training resolutions. The primary obstacle is that the explicit positional encodings (PE), such as RoPE, need extrapolating to unseen positions which degrades performance when the inference resolution differs from training. In this paper, We propose a Length-Extrapolatable Diffusion Transformer (LEDiT) to overcome this limitation. LEDiT needs no explicit PEs, thereby avoiding PE extrapolation. The key innovation of LEDiT lies in the use of causal attention. We demonstrate that causal attention can implicitly encode global positional information and show that such information facilitates extrapolation. We further introduce a locality enhancement module, which captures fine-grained local information to complement the global coarse-grained position information encoded by causal attention. Experimental results on both conditional and text-to-image generation tasks demonstrate that LEDiT supports up to 4× resolution scaling (e. g. , from 256$\times$256 to 512$\times$512), achieving better image quality compared to the state-of-the-art length extrapolation methods. We believe that LEDiT marks a departure from the standard RoPE-based methods and offers a promising insight into length extrapolation. Project page: https: //shenzhang2145. github. io/ledit/

PDF Details

YNIMG Journal 2024 Journal Article

Investigating unilateral and bilateral motor imagery control using electrocorticography and fMRI in awake craniotomy

Jie Ma
Zhengsheng Li
Qian Zheng
Shichen Li
Rui Zong
Zhizhen Qin
Li Wan
Zhenyu Zhao

BACKGROUND: The rapid development of neurosurgical techniques, such as awake craniotomy, has increased opportunities to explore the mysteries of the brain. This is crucial for deepening our understanding of motor control and imagination processes, especially in developing brain-computer interface (BCI) technologies and improving neurorehabilitation strategies for neurological disorders. OBJECTIVE: This study aimed to analyze brain activity patterns in patients undergoing awake craniotomy during actual movements and motor imagery, mainly focusing on the motor control processes of the bilateral limbs. METHODS: We conducted detailed observations of patients undergoing awake craniotomies. The experimenter requested participants to perform and imagine a series of motor tasks involving their hands and tongues. Brain activity during these tasks was recorded using functional magnetic resonance imaging (fMRI) and intraoperative electrocorticography (ECoG). The study included left and right finger tapping, tongue protrusion, hand clenching, and imagined movements corresponding to these actions. RESULTS: fMRI revealed significant activation in the brain's motor areas during task performance, mainly involving bilateral brain regions during imagined movement. ECoG data demonstrated a marked desynchronization pattern in the ipsilateral motor cortex during bilateral motor imagination, especially in bilateral coordination tasks. This finding suggests a potential controlling role of the unilateral cerebral cortex in bilateral motor imagination. CONCLUSION: Our study highlights the unilateral cerebral cortex's significance in controlling bilateral limb motor imagination, offering new insights into future brain network remodeling in patients with hemiplegia. Additionally, these findings provide important insights into understanding motor imagination and its impact on BCI and neurorehabilitation.

Details DOI

AAAI Conference 2016 Conference Paper

Relaxed Majorization-Minimization for Non-Smooth and Non-Convex Optimization

Chen Xu
Zhouchen Lin
Zhenyu Zhao
Hongbin Zha

We propose a new majorization-minimization (MM) method for non-smooth and non-convex programs, which is general enough to include the existing MM methods. Besides the local majorization condition, we only require that the difference between the directional derivatives of the objective function and its surrogate function vanishes when the number of iterations approaches inﬁnity, which is a very weak condition. So our method can use a surrogate function that directly approximates the non-smooth objective function. In comparison, all the existing MM methods construct the surrogate function by approximating the smooth component of the objective function. We apply our relaxed MM methods to the robust matrix factorization (RMF) problem with different regularizations, where our locally majorant algorithm shows great advantages over the state-of-the-art approaches for RMF. This is the ﬁrst algorithm for RMF ensuring, without extra assumptions, that any limit point of the iterates is a stationary point.

PDF Details