Author name cluster

Zhen Wei

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.

5 papers

2 author rows

ICML Conference 2025 Conference Paper

DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generation

Dongya Jia
Zhuo Chen 0006
Jiawei Chen
Chenpeng Du
Jian Wu
Jian Cong
Xiaobin Zhuang
Chumin Li 0002

Several recent studies have attempted to autoregressively generate continuous speech representations without discrete speech tokens by combining diffusion and autoregressive models, yet they often face challenges with excessive computational loads or suboptimal outcomes. In this work, we propose Diffusion Transformer Autoregressive Modeling (DiTAR), a patch-based autoregressive framework combining a language model with a diffusion transformer. This approach significantly enhances the efficacy of autoregressive models for continuous tokens and reduces computational demands. DiTAR utilizes a divide-and-conquer strategy for patch generation, where the language model processes aggregated patch embeddings, and the diffusion transformer subsequently generates the next patch based on the output of the language model. For inference, we propose defining temperature as the time point of introducing noise during the reverse diffusion ODE to balance diversity and determinism. We also show in the extensive scaling analysis that DiTAR has superb scalability. In zero-shot speech generation, DiTAR achieves state-of-the-art performance in robustness, speaker similarity, and naturalness.

Details

EAAI Journal 2025 Journal Article

Skin lesion classification network based on improved MobileViT

Fuyun He
Rongqing Wu
Xuqing Zeng
Haixing Song
Guanglian Li
Zhen Wei

Computer-aided diagnosis can alleviate the pressure on dermatologists while helping patients to recognize skin lesions at an early stage. Recent studies have shown that integrated networks can effectively handle dermatological classification, but they are not conducive to practical applications. Meanwhile, lightweight networks are often limited by network depth, which somewhat affects their performance when facing complex classification tasks. For this purpose, we present a skin lesion classification network. The network acquires local features via a convolutional layer and then models the global features using the Transformer structure. We designed the enhanced feature representation module, which focuses on the spatial features of the receptive field while further incorporating the directional weights, and is able to provide a richer feature representation. In addition, the cosine similarity downsampling module is proposed in order to reduce the information loss caused by the baseline network during downsampling as well as to enhance the ability to capture key features. This module uses parallel downsampling branches and further introduces cosine similarity for weighting to focus on similar feature information. We perform validation experiments on three publicly available dermatological datasets, which include clinical images and dermoscopic images. Experimental results on three datasets show that our network is able to better balance model complexity and skin lesion classification performance compared to some state-of-the-art classification networks and skin lesion classification networks.

Details DOI

AAAI Conference 2023 Conference Paper

Fast and Accurate Binary Neural Networks Based on Depth-Width Reshaping

Ping Xue
Yang Lu
Jingfei Chang
Xing Wei
Zhen Wei

Network binarization (i.e., binary neural networks, BNNs) can efficiently compress deep neural networks and accelerate model inference but cause severe accuracy degradation. Existing BNNs are mainly implemented based on the commonly used full-precision network backbones, and then the accuracy is improved with various techniques. However, there is a question of whether the full-precision network backbone is well adapted to BNNs. We start from the factors of the performance degradation of BNNs and analyze the problems of directly using full-precision network backbones for BNNs: for a given computational budget, the backbone of a BNN may need to be shallower and wider compared to the backbone of a full-precision network. With this in mind, Depth-Width Reshaping (DWR) is proposed to reshape the depth and width of existing full-precision network backbones and further optimize them by incorporating pruning techniques to better fit the BNNs. Extensive experiments demonstrate the analytical result and the effectiveness of the proposed method. Compared with the original backbones, the DWR backbones constructed by the proposed method result in close to O(√s) decrease in activations, while achieving an absolute accuracy increase by up to 1.7% with comparable computational cost. Besides, by using the DWR backbones, existing methods can achieve new state-of-the-art (SOTA) accuracy (e.g., 67.2% on ImageNet with ResNet-18 as the original backbone). We hope this work provides a novel insight into the backbone design of BNNs. The code is available at https://github.com/pingxue-hfut/DWR.

PDF Details DOI

YNICL Journal 2022 Journal Article

Imbalance between the caudate and putamen connectivity in obsessive–compulsive disorder

Ziwen Peng
Tingxin He
Ping Ren
Lili Jin
Qiong Yang
Chuanyong Xu
Rongzhen Wen
Jierong Chen

BACKGROUND: Compulsive behaviors in obsessive-compulsive disorder (OCD) have been suggested to result from an imbalance in cortico-striatal connectivity. However, the nature of this impairment, the relative involvement of different striatal areas, their imbalance in genetically related but unimpaired individuals, and their relationship with cognitive dysfunction in OCD patients, remain unknown. METHODS: In the current study, striatal (i.e., caudate and putamen) whole-brain connectivity was computed in a sample of OCD patients (OCD, n = 62), unaffected first-degree relatives (UFDR, n = 53) and healthy controls (HC, n = 73) by ROI-based resting-state functional magnetic resonance imaging (rs-fMRI). A behavioral task switch paradigm outside of the scanner was also performed to measure cognitive flexibility in OCD patients. RESULTS: There were significantly increased strengths (Z-transformed Pearson correlation coefficient) in caudate connectivity in OCD patients. A significant correlation between the two types of connectivity strengths in the relevant regions was observed only in the OCD patient group. Furthermore, the caudate connectivity of patients was negatively associated with their task-switch performance. CONCLUSIONS: The imbalance between the caudate and putamen connectivity, arising from the abnormal increase of caudate activity, may serve as a clinical characteristic for obsessive-compulsive disorder.

Details DOI

YNICL Journal 2021 Journal Article

Aberrant rich club organization in patients with obsessive-compulsive disorder and their unaffected first-degree relatives

Ziwen Peng
Xinyi Yang
Chuanyong Xu
Xiangshu Wu
Qiong Yang
Zhen Wei
Zihan Zhou
Tom Verguts

Recent studies suggested that the rich club organization promoting global brain communication and integration of information, may be abnormally increased in obsessive-compulsive disorder (OCD). However, the structural and functional basis of this organization is still not very clear. Given the heritability of OCD, as suggested by previous family-based studies, we hypothesize that aberrant rich club organization may be a trait marker for OCD. In the present study, 32 patients with OCD, 30 unaffected first-degree relatives (FDR) and 32 healthy controls (HC) underwent diffusion tensor imaging (DTI) and functional magnetic resonance imaging (fMRI). We examined the structural rich club organization and its interrelationship with functional coupling. Our results showed that rich club and peripheral connection strength in patients with OCD was lower than in HC, while it was intermediate in FDR. Finally, the coupling between structural and functional connections of the rich club, was decreased in FDR but not in OCD relative to HC, which suggests a buffering mechanism of brain functions in FDR. Overall, our findings suggest that alteration of the rich club organization may reflect a vulnerability biomarker for OCD, possibly buffered by structural and functional coupling of the rich club.

Details DOI