Tao Tao

Dr. Tao Tao

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 January 2021 in Neural Computing and Applications
Verified
Journal Article
Closed access
PDF file
HLHeng Liu
Heng Liu
JLJianyong Liu
Jianyong Liu
SHShudong Hou
Shudong Hou
TTTao Tao
Tao Tao
JHJungong Han
Jungong Han

15 January 2025 in International Journal of Intelligent Systems
Verified
Journal Article
Open access
Weiqiang JinWeiqiang Jin
Weiqiang Jin
YGYang Gao
Yang Gao
TTTao Tao
Tao Tao
XWXiujun Wang
Xiujun Wang
NWNingwei Wang
Ningwei Wang
BZBiao Zhao
Biao Zhao
Fake news detection (FND) is a critical task in natural language processing (NLP) focused on identifying and mitigating the spread of misinformation. Large language models (LLMs) have recently shown remarkable abilities in understanding semantics and performing logical inference. However, their tendency to generate hallucinations poses significant challenges in accurately detecting deceptive content, leading to suboptimal performance. In addition, existing FND methods often underutilize the extensive prior knowledge embedded within LLMs, resulting in less effective classification outcomes. To address these issues, we propose the CAPE–FND framework, context‐aware prompt engineering, designed for enhancing FND tasks. This framework employs unique veracity‐oriented context‐aware constraints, background information, and analogical reasoning to mitigate LLM hallucinations and utilizes self‐adaptive bootstrap prompting optimization to improve LLM predictions. It further refines initial LLM prompts through adaptive iterative optimization using a random search bootstrap algorithm, maximizing the efficacy of LLM prompting. Extensive zero‐shot and few‐shot experiments using GPT‐3.5‐turbo across multiple public datasets demonstrate the effectiveness and robustness of our CAPE–FND framework, even surpassing advanced GPT‐4.0 and human performance in certain scenarios. To support further LLM–based FND, we have made our approach’s code publicly available on GitHub (our CAPE–FND code: https://github.com/albert-jin/CAPE-FND [Accessed on 2024.09]).

1 August 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
TTTao Tao
Tao Tao
CSChen Sun
Chen Sun
ZWZhaoyang Wu
Zhaoyang Wu
JYJian Yang
Jian Yang
JWJing Wang
Jing Wang
Studies reported that if teachers can accurately predict students’ follow-up learning effects via data mining and other means, as per their current performances, and explore the difficulty level of students’ mastery of future-related courses in advance, it will help improve students’ scores in future exams. Although educational data mining and learning analytics have experienced an increase in exploration and use, they are still difficult to precisely define. The usage of deep learning methods to predict academic performances and recommend optimal learning methods has not received considerable attention from researchers. This study aims to predict unknown course grades based on students’ previous learning situations and use clustering algorithms to identify similar learning situations, thereby improving students’ academic performance. In this study, the methods of linear regression, random forest, back-propagation neural network, and deep neural network are compared; the prediction and early warning of students’ academic performances based on deep neural network are proposed, in addition to the improved K-nearest neighbor clustering based on association rules (Pearson correlation coefficient). The algorithm performs a similar category clustering for early-warning students. Using the mean square error, standard deviation, mean absolute percentage error, and prediction of ups-and-downs accuracy as evaluation indicators, the proposed method achieves a steady improvement of 20% in the prediction of ups-and-downs accuracy, and demonstrates improved prediction results when compared under similar conditions.

19 August 2025 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
HZHao Zhou
Hao Zhou
YWYalun Wang
Yalun Wang
QZQian Zhang
Qian Zhang
TTTao Tao
Tao Tao
Wenqi RenWenqi Ren
Wenqi Ren
Atmospheric pollutants, such as haze, severely affect the quality of remote sensing images, leading to blurred details and impairing their effectiveness in applications like environmental monitoring and agricultural resource management. In recent years, diffusion models have attracted widespread attention due to their powerful generative capabilities. However, striking a balance between their expensive training costs and actual recovery effectiveness has become a major challenge. To address this key challenge, we propose a perceptual decoding dual-stage residual diffusion model (DS-RDMPD) for remote sensing image dehazing. The core innovation of our work lies in a dual-stage coarse-to-fine architecture that integrates the traditional U-Net with a diffusion model, enabling efficient adaptation of diffusion-based restoration to the dehazing task. This design not only achieves strong performance but also demonstrates remarkable generalization across various image restoration scenarios. In the first stage, we use the Multi-channel Efficient Selective Synthesis U-Net (MCESS-UNet) to pre-process the remote sensing haze images. This architecture performs initial dehazing and feature extraction through a multi-scale channel attention (MC) block, and then performs enhanced spatial feature aggregation through an Efficient Selective Synthesis (ESS) block. The preprocessed image is then used as the conditional input of the Residual Diffusion Model with Perceptual Decoding, where the perceptual decoder improves the generation quality by further decoupling the condition to refine the residual estimate. Extensive experiments on multiple datasets show that DS-RDMPD can achieve satisfactory results with only 300,000 iterations and about five sampling steps. It has achieved satisfactory results in both qualitative and quantitative experiments, and also exhibits strong performance in rain removal and deblurring tasks, demonstrating the excellent generalization ability of the model. The code is available at https://github.com/Aaronwangz/DS-RDMPD.

22 August 2024 in Scientific Reports
Verified
Journal Article
Open access
PDF file
WJWeiqiang Jin
Weiqiang Jin
NWNingwei Wang
Ningwei Wang
TTTao Tao
Tao Tao
BSBohang Shi
Bohang Shi
HBHaixia Bi
Haixia Bi
Guang YangGuang Yang
Guang Yang
With the rapid growth of social media, fake news (rumors) are rampant online, seriously endangering the health of mainstream social consciousness. Fake news detection (FEND), as a machine learning solution for automatically identifying fake news on Internet, is increasingly gaining the attentions of academic community and researchers. Recently, the mainstream FEND approaches relying on deep learning primarily involves fully supervised fine-tuning paradigms based on pre-trained language models (PLMs), relying on large annotated datasets. In many real scenarios, obtaining high-quality annotated corpora are time-consuming, expertise-required, labor-intensive, and expensive, which presents challenges in obtaining a competitive automatic rumor detection system. Therefore, developing and enhancing FEND towards data-scarce scenarios is becoming increasingly essential. In this work, inspired by the superiority of semi-/self- supervised learning, we propose a novel few-shot rumor detection framework based on semi-supervised adversarial learning and self-supervised contrastive learning, named Detection Yet See Few (DetectYSF). DetectYSF synergizes contrastive self-supervised learning and adversarial semi-supervised learning to achieve accurate and efficient FEND capabilities with limited supervised data. DetectYSF uses Transformer-based PLMs (e.g., BERT, RoBERTa) as its backbone and employs a Masked LM-based pseudo prompt learning paradigm for model tuning (prompt-tuning). Specifically, during DetectYSF training, the enhancement measures for DetectYSF are as follows: (1) We design a simple but efficient self-supervised contrastive learning strategy to optimize sentence-level semantic embedding representations obtained from PLMs; (2) We construct a Generation Adversarial Network (GAN), utilizing random noises and negative fake news samples as inputs, and employing Multi-Layer Perceptrons (MLPs) and an extra independent PLM encoder to generate abundant adversarial embeddings. Then, incorporated with the adversarial embeddings, we utilize semi-supervised adversarial learning to further optimize the output embeddings of DetectYSF during its prompt-tuning procedure. From the news veracity dissemination perspective, we found that the authenticity of the news shared by these collectives tends to remain consistent, either mostly genuine or predominantly fake, a theory we refer to as “news veracity dissemination consistency”. By employing an adjacent sub-graph feature aggregation algorithm, we infuse the authenticity characteristics from neighboring news nodes of the constructed veracity dissemination network during DetectYSF inference. It integrates the external supervisory signals from “news veracity dissemination consistency” to further refine the news authenticity detection results of PLM prompt-tuning, thereby enhancing the accuracy of fake news detection. Furthermore, extensive baseline comparisons and ablated experiments on three widely-used benchmarks demonstrate the effectiveness and superiority of DetectYSF for few-shot fake new detection under low-resource scenarios.

27 May 2024 in Electronics
Verified
Journal Article
Open access
PDF file
HZHao Zhou
Hao Zhou
ZCZekai Chen
Zekai Chen
QLQiao Li
Qiao Li
TTTao Tao
Tao Tao
Numerous extant image dehazing methods based on learning improve performance by increasing the depth or width, the size of the convolution kernel, or using the Transformer structure. However, this will inevitably introduce many parameters and increase the computational overhead. Therefore, we propose a lightweight dehazing framework: Dehaze-UNet, which has excellent dehazing performance and very low computational overhead to be suitable for terminal deployment. To allow Dehaze-UNet to aggregate the features of haze, we design a LAYER module. This module mainly aggregates the haze features of different hazy images through the batch normalization layer, so that Dehaze-UNet can pay more attention to haze. Furthermore, we revisit the use of the physical model in the network. We design an ASMFUN module to operate the feature map of the network, allowing the network to better understand the generation and removal of haze and learn prior knowledge to improve the network’s generalization to real hazy scenes. Extensive experimental results indicate that the lightweight Dehaze-UNet outperforms state-of-the-art methods, especially for hazy images of real scenes.