Rui Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Rui Li has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Junsong Zhang
School of Informatics, Xiamen University, Xiamen, China
3 shared publications - Jingying Chen
National Engineering Research Center for E-Learning, Faculty of Artificial Intelligence in Education, Central China Normal University, Wuhan 430079, China
2 shared publications Fengpeng Wang
Epilepsy Center, Xiamen Humanity Hospital, Xiamen, Fujian 361006, China; HH-SIAT Joint Laboratory for Epilepsy Research, Xiamen, Fujian 361006, China
1 shared publicationHuimin Huang
School of Education, Jianghan University, Wuhan, Hubei 430056 China
1 shared publicationHuiqing Jia
Brain Cognition and Intelligent Computing Lab, Department of Artificial Intelligence, School of Informatics, Xiamen University, Xiamen, Fujian 361005 China
1 shared publicationLizhi Yang
Brain Cognition and Intelligent Computing Lab, Department of Artificial Intelligence, School of Informatics, Xiamen University, Xiamen, Fujian 361005 China
1 shared publication
Latest Publications
- Open Access
- 1 September 2026
- Published by MDPI AG in Journal of Intelligence
- Vol. 14 (9) , 194
EEG-Based Characterization of Learning Potential-Related Neural Representations via Dynamic Assessment Tasks
Learning potential assessment is important for understanding individual differences in learning processes and cognitive development. Traditional assessments mainly rely on questionnaires or behavioral data collected during tasks, emphasizing external performance while lacking sensitivity to learners’ internal cognitive activities. Therefore, they provide limited evidence about the neurocognitive mechanisms underlying individual learning potential. This study investigated whether task-evoked EEG responses acquired during a dynamic learning paradigm could characterize individual differences in task-specific learning performance under graduated instructional support. Participants were 50 undergraduate students who completed a dynamic cognitive task designed to evaluate learning performance under graduated instructional support. An electroencephalogram (EEG)-based Multi-scale Learning Potential Assessment (MS-LPA) framework was developed, including a Dynamic Learning Paradigm with progressively complex cognitive tasks and responsive cueing; multiscale Neural Complexity Representations quantifying signal complexity and inter-regional synchronization; and a ResNet-18 model with SHAP-based interpretability for classification and biomarker identification. Experiments showed that MS-LPA captured task-evoked neural responses and outperformed traditional outcome-driven evaluation schemes. Entropy-based features achieved an accuracy of 0.77, and functional connectivity matrices reached 0.83. These findings demonstrate the feasibility of using EEG-derived neural representations to differentiate individual differences in task-specific dynamic learning performance and provide insights into its underlying neural mechanisms.
- 1 September 2026
- Published by MDPI AG in Journal of Intelligence
- Vol. 14 (9) , 194
Open AccessEEG-Based Characterization of Learning Potential-Related Neural Representations via Dynamic Assessment Tasks
Learning potential assessment is important for understanding individual differences in learning processes and cognitive development. Traditional assessments mainly rely on questionnaires or behavioral data collected during tasks, emphasizing external performance while lacking sensitivity to learners’ internal cognitive activities. Therefore, they provide limited evidence about the neurocognitive mechanisms underlying individual learning potential. This study investigated whether task-evoked EEG responses acquired during a dynamic learning paradigm could characterize individual differences in task-specific learning performance under graduated instructional support. Participants were 50 undergraduate students who completed a dynamic cognitive task designed to evaluate learning performance under graduated instructional support. An electroencephalogram (EEG)-based Multi-scale Learning Potential Assessment (MS-LPA) framework was developed, including a Dynamic Learning Paradigm with progressively complex cognitive tasks and responsive cueing; multiscale Neural Complexity Representations quantifying signal complexity and inter-regional synchronization; and a ResNet-18 model with SHAP-based interpretability for classification and biomarker identification. Experiments showed that MS-LPA captured task-evoked neural responses and outperformed traditional outcome-driven evaluation schemes. Entropy-based features achieved an accuracy of 0.77, and functional connectivity matrices reached 0.83. These findings demonstrate the feasibility of using EEG-derived neural representations to differentiate individual differences in task-specific dynamic learning performance and provide insights into its underlying neural mechanisms.
- Open Access
- 6 August 2026
- Published by MDPI AG in Journal of Intelligence
- Vol. 14 (8) , 180
Learning Potential as a Dynamic Component of Academic Intelligence: An fNIRS-Based Dynamic Assessment Study of English Reading Comprehension
Foreign language reading comprehension is a critical indicator of university students’ academic cognitive ability and global competence, yet effectively assessing their latent learning potential remains a major challenge. Therefore, from a neurocognitive perspective, this study combined functional near-infrared spectroscopy (fNIRS) with dynamic assessment (DA) to investigate the activation characteristics of the left frontal and temporal regions in non-English majors during reading tasks across two difficulty levels (CET-4/CET-6) and two assessment conditions (static/dynamic testing). The results showed that reading tasks activated the dorsolateral prefrontal cortex and middle temporal gyrus. Compared with CET-4, the more difficult CET-6 task showed a broader descriptive cortical activation pattern. Notably, mediated prompts were associated with different behavioral and activation-frequency patterns across task difficulty levels: in the CET-4 task, dynamic assessment showed higher normalized activation-frequency values than static assessment in areas corresponding to the middle and inferior frontal gyrus, accompanied by rising prompt scores; however, the CET-6 task exhibited the opposite pattern. These findings suggest that mediated prompts may be more effective in stimulating learning potential when task difficulty aligns with the learner’s zone of proximal development. Overall, by considering behavioral dynamic-assessment indicators in foreign-language reading together with fNIRS-based cortical activation patterns, this exploratory study offers preliminary insights into learning potential, personalized instructional interventions, and academic cognitive assessment.
- 6 August 2026
- Published by MDPI AG in Journal of Intelligence
- Vol. 14 (8) , 180
Open AccessLearning Potential as a Dynamic Component of Academic Intelligence: An fNIRS-Based Dynamic Assessment Study of English Reading Comprehension
Foreign language reading comprehension is a critical indicator of university students’ academic cognitive ability and global competence, yet effectively assessing their latent learning potential remains a major challenge. Therefore, from a neurocognitive perspective, this study combined functional near-infrared spectroscopy (fNIRS) with dynamic assessment (DA) to investigate the activation characteristics of the left frontal and temporal regions in non-English majors during reading tasks across two difficulty levels (CET-4/CET-6) and two assessment conditions (static/dynamic testing). The results showed that reading tasks activated the dorsolateral prefrontal cortex and middle temporal gyrus. Compared with CET-4, the more difficult CET-6 task showed a broader descriptive cortical activation pattern. Notably, mediated prompts were associated with different behavioral and activation-frequency patterns across task difficulty levels: in the CET-4 task, dynamic assessment showed higher normalized activation-frequency values than static assessment in areas corresponding to the middle and inferior frontal gyrus, accompanied by rising prompt scores; however, the CET-6 task exhibited the opposite pattern. These findings suggest that mediated prompts may be more effective in stimulating learning potential when task difficulty aligns with the learner’s zone of proximal development. Overall, by considering behavioral dynamic-assessment indicators in foreign-language reading together with fNIRS-based cortical activation patterns, this exploratory study offers preliminary insights into learning potential, personalized instructional interventions, and academic cognitive assessment.
- Open Access
- 26 March 2026
- Published by Elsevier in NeuroImage
- Vol. 331, 121891
Hippocampal-parietal directed connectivity mediates brain network reconfiguration between internal and external attention: An intracranial EEG study
- 26 March 2026
- Published by Elsevier in NeuroImage
- Vol. 331, 121891
Open AccessHippocampal-parietal directed connectivity mediates brain network reconfiguration between internal and external attention: An intracranial EEG study
- Open Access
Improving Chinese Character Representation with Formation Tree
Learning effective representations for Chinese characters presents unique challenges, primarily due to the vast number of characters and their continuous growth, which requires models to handle an expanding category space. Additionally, the inherent sparsity of character usage complicates the generalization of learned representations. Prior research has explored radical-based sequences to overcome these issues, achieving progress in recognizing unseen characters. However, these approaches fail to fully exploit the inherent tree structure of such sequences. To address these limitations and leverage established data properties, we propose Formation Tree-CLIP (FT-CLIP). This model utilizes formation trees to represent characters and incorporates a dedicated tree encoder, significantly improving performance in both seen and unseen character recognition tasks. We further introduce masking for to both character images and tree nodes, enabling efficient and effective training. This approach accelerates training significantly (by a factor of 2 or more) while enhancing accuracy. Extensive experiments show that processing characters through formation trees aligns better with their inherent properties than direct sequential methods, significantly enhancing the generality and usability of the representations.
Open AccessImproving Chinese Character Representation with Formation Tree
Learning effective representations for Chinese characters presents unique challenges, primarily due to the vast number of characters and their continuous growth, which requires models to handle an expanding category space. Additionally, the inherent sparsity of character usage complicates the generalization of learned representations. Prior research has explored radical-based sequences to overcome these issues, achieving progress in recognizing unseen characters. However, these approaches fail to fully exploit the inherent tree structure of such sequences. To address these limitations and leverage established data properties, we propose Formation Tree-CLIP (FT-CLIP). This model utilizes formation trees to represent characters and incorporates a dedicated tree encoder, significantly improving performance in both seen and unseen character recognition tasks. We further introduce masking for to both character images and tree nodes, enabling efficient and effective training. This approach accelerates training significantly (by a factor of 2 or more) while enhancing accuracy. Extensive experiments show that processing characters through formation trees aligns better with their inherent properties than direct sequential methods, significantly enhancing the generality and usability of the representations.
- Open Access
NRTR: Neuron Reconstruction with Transformer from 3D Optical Microscopy Images
The neuron reconstruction from raw Optical Microscopy (OM) image stacks is the basis of neuroscience. Manual annotation and semi-automatic neuron tracing algorithms are time-consuming and inefficient. Existing deep learning neuron reconstruction methods, although demonstrating exemplary performance, greatly demand complex rule-based components. Therefore, a crucial challenge is designing an end-to-end neuron reconstruction method that makes the overall framework simpler and model training easier. We propose a Neuron Reconstruction Transformer (NRTR) that, discarding the complex rule-based components, views neuron reconstruction as a direct set-prediction problem. To the best of our knowledge, NRTR is the first image-to-set deep learning model for end-to-end neuron reconstruction. In experiments using the BigNeuron and VISoR-40 datasets, NRTR achieves excellent neuron reconstruction results for comprehensive benchmarks and outperforms competitive baselines. Results of extensive experiments indicate that NRTR is effective at showing that neuron reconstruction is viewed as a set-prediction problem, which makes end-to-end model training available.
Open AccessNRTR: Neuron Reconstruction with Transformer from 3D Optical Microscopy Images
The neuron reconstruction from raw Optical Microscopy (OM) image stacks is the basis of neuroscience. Manual annotation and semi-automatic neuron tracing algorithms are time-consuming and inefficient. Existing deep learning neuron reconstruction methods, although demonstrating exemplary performance, greatly demand complex rule-based components. Therefore, a crucial challenge is designing an end-to-end neuron reconstruction method that makes the overall framework simpler and model training easier. We propose a Neuron Reconstruction Transformer (NRTR) that, discarding the complex rule-based components, views neuron reconstruction as a direct set-prediction problem. To the best of our knowledge, NRTR is the first image-to-set deep learning model for end-to-end neuron reconstruction. In experiments using the BigNeuron and VISoR-40 datasets, NRTR achieves excellent neuron reconstruction results for comprehensive benchmarks and outperforms competitive baselines. Results of extensive experiments indicate that NRTR is effective at showing that neuron reconstruction is viewed as a set-prediction problem, which makes end-to-end model training available.