Author name cluster

Juan Li

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.

14 papers

2 author rows

AAAI Conference 2026 Conference Paper

DRSoRec: Dual-Rectification of Social Networks for Recommendation

Liangxun Yang
Tianzi Zang
Jiayi Sun
Juan Li
Yicong Li

Leveraging social homophily to enhance user preference modeling, social recommendation has become a cornerstone of modern recommender systems. However, the raw social network contains inherent unreliability as it teems with noise---misclicks, bot-generated and transient ties---while many meaningful links remain unobserved. In this study, we propose DRSoRec, a dual-rectification model to rectify the raw social networks by simultaneously removing noisy signals and preserving useful information. Specifically, the invariant social rationale discovery module distills each user's influential core social circle of the current recommendation, whereas the adaptive social connection refinement module employs a mixture-of-experts structure learner to prune spurious edges and uncover latent links. A contrastive optimization objective is designed to align and mutually enhance these two modules, and the refined user representations are fused with collaborative representations generated from interactions for the final recommendation. Experiments on three public datasets confirm that DRSoRec consistently gains over state-of-the-art baselines.

PDF Details DOI

YNIMG Journal 2026 Journal Article

Intrinsic neural timescales shape memory encoding and retrieval

Xinyu Shen
Xiaoyu Cui
Yasir Çatal
Juan Li
Georg Northoff

Historically, different memory processes like encoding and retrieval have been distinguished. However, recent models emphasize their continuum across the shorter and longer timescales of encoding and retrieval while, at the same time, both are featured by distinct cognitive demands. The exact neural mechanisms connecting and, at the same time, differentiating encoding and retrieval across their multiple timescales remain yet unclear, though. Using EEG, we here measure the brain's Intrinsic neural timescales (INT) by the autocorrelation window (ACW) during encoding and retrieval of memory. Our main findings are: (i) direct behavioral connection of encoding (spatial fit judgment of the pictures) with those of retrieval (precision, false alarms, accuracy); (ii) a clear state-dependent neural differentiation, with longer ACW during encoding (temporal integration) and shorter ACW during retrieval (temporal segregation), a distinction not observed for another dynamic measure, the power-law exponent (PLE); (iii) high trait-like stability of ACW, with an individual's ACW remaining strongly correlated across rest, encoding, and retrieval states; and (iv) this stable, trait-like ACW (but not its state-dependent modulation) robustly predicts memory performance, with longer trait ACW correlating with higher accuracy and precision and fewer false alarms. Together, we demonstrate that the brain's INT both connect and differentiate encoding and retrieval on both neural and behavioral grounds. This supports and extends current dynamic, e.g., temporal, models of memory by showing the key relevance of the brain's INT (as measured by the ACW) in shaping encoding and retrieval.

Details DOI

AAAI Conference 2026 Conference Paper

Self-Correction Distillation for Structured Data Question Answering

Yushan Zhu
Wen Zhang
Long Jin
Mengshu Sun
Ling Zhong
Zhiqiang Liu
Juan Li
Lei Liang

Structured data question answering (QA), including table QA, Knowledge Graph (KG) QA, and temporal KG QA, is a pivotal research area. Advances in large language models (LLMs) have driven significant progress in unified structural QA frameworks like TrustUQA. However, these frameworks face challenges when applied to small-scale LLMs since small-scale LLMs are prone to errors in generating structured queries. To improve the structured data QA ability of small-scale LLMs, we propose a self-correction distillation (SCD) method. In SCD, an error prompt mechanism (EPM) is designed to detect errors and provide customized error messages during inference, and a two-stage distillation strategy is designed to transfer large-scale LLMs' query-generation and error-correction capabilities to small-scale LLM. Experiments across 5 benchmarks with 3 structured data types demonstrate that our SCD achieves the best performance and superior generalization on small-scale LLM (8B) compared to other distillation methods, and closely approaches the performance of GPT4 on some datasets. Furthermore, large-scale LLMs equipped with EPM surpass the state-of-the-art results on most datasets.

PDF Details DOI

EAAI Journal 2026 Journal Article

Unknown malware detection model based on genetic evolutionary strategy

Tun Li
Meishi Song
Juan Li
Mingru Jin
Lei Qiao
Chengkai Liu
Qian Li
Yunpeng Xiao

In recent years, malware variants have proliferated rapidly, while traditional detection systems exhibit slow recognition of unknown threats and high False Positive Rates (FPR). This paper proposes a detection model for unknown malware based on genetic evolutionary strategies. The core hypothesis is that simulating the natural evolutionary process of malware can generate representative unknown malware variants for training, thereby enhancing detection capabilities. The methodology incorporates three key technologies: first, Genetic Evolution-based Malicious Sample Generation (GE-MS), a method that evolves malicious samples and generates potential malware variants through selection, crossover, and mutation operations; second, Isolation Forest-Local Outlier Factor (IF-LOF), a hybrid anomaly detection approach combining Isolation Forests (IF) and Local Outlier Factor (LOF) algorithms to filter unrealistic samples; third, Active Learning-based Soft Voting (ALSV), an active learning-based ensemble detection model that enhances through uncertainty sampling and soft voting mechanisms. Experiments conducted on the Drebin dataset demonstrate that the proposed model outperforms baseline methods, achieving 95. 31% accuracy, a 95. 12% F1-score, and a low false positive rate of 5. 86%, proving its high efficacy in malware detection.

Details DOI

IROS Conference 2025 Conference Paper

BoRe-Depth: Self-Supervised Monocular Depth Estimation with Boundary Refinement for Embedded Systems

Juan Li
Sheng Zhang
Chang Liu
Jie Li
Xu Zhang

Depth estimation is one of the key technologies for realizing 3D perception in unmanned systems. Monocular depth estimation has been widely researched because of its low-cost advantage, but the existing methods face the challenges of poor depth estimation performance and blurred object boundaries on embedded systems. In this paper, we propose a novel monocular depth estimation model, BoRe-Depth, which contains only 8. 7M parameters. It can accurately estimate depth maps on embedded systems and significantly improves boundary quality. Firstly, we design an Enhanced Feature Adaptive Fusion Module (EFAF) which adaptively fuses depth features to enhance boundary detail representation. Secondly, we integrate semantic knowledge into the encoder to improve the object recognition and boundary perception capabilities. Finally, BoRe-Depth is deployed on NVIDIA Jetson Orin, and runs efficiently at 50. 7 FPS. We demonstrate that the proposed model significantly outperforms previous lightweight models on multiple challenging datasets, and we provide detailed ablation studies for the proposed methods. The code is available at https://github.com/liangxiansheng093/BoRe-Depth.

Details

ICML Conference 2025 Conference Paper

Bridging Layout and RTL: Knowledge Distillation based Timing Prediction

Mingjun Wang
Yihan Wen
Bin Sun
Jianan Mu
Juan Li
Xiaoyi Wang
Jing Ye 0001
Bei Yu 0001

Accurate and efficient timing prediction at the register-transfer level (RTL) remains a fundamental challenge in electronic design automation (EDA), particularly in striking a balance between accuracy and computational efficiency. While static timing analysis (STA) provides high-fidelity results through comprehensive physical parameters, its computational overhead makes it impractical for rapid design iterations. Conversely, existing RTL-level approaches sacrifice accuracy due to the limited physical information available. We propose RTLDistil, a novel cross-stage knowledge distillation framework that bridges this gap by transferring precise physical characteristics from a layout-aware teacher model (Teacher GNN) to an efficient RTL-level student model (Student GNN), both implemented as graph neural networks (GNNs). RTLDistil efficiently predicts key timing metrics, such as arrival time (AT), and employs a multi-granularity distillation strategy that captures timing-critical features at node, subgraph, and global levels. Experimental results demonstrate that RTLDistil achieves significant improvement in RTL-level timing prediction error reduction, compared to state-of-the-art prediction models. This framework enables accurate early-stage timing prediction, advancing EDA’s “left-shift” paradigm while maintaining computational efficiency. Our code and dataset will be publicly available at https: //github. com/sklp-eda-lab/RTLDistil.

Details

EAAI Journal 2025 Journal Article

Diabetes risk assessment model based on unbalanced public health examination data

Liangjun Jiang
Jing Wang
Jie Xie
Zhenhua Xia
Juan Li
Haimei Gong
Lei Wang

Timely risk assessment is crucial for the prevention, treatment, and management of diabetes. In this study, we propose an intelligent risk assessment model framework for diabetes based on public health examination data, focusing on both clinical examination and personal lifestyle dimensions. First, to address the multi-feature issue in examination data, a progressive correlation-based feature selection method was established to select risk features. Fourteen and six key features were selected for the clinical examination and personal lifestyle dimensions, respectively, with the features being concise, transparent, and highly interpretable. Second, to address the issue of sample imbalance and the medical focus on minority class samples, we designed an under-sampling ensemble classification iterative boosting method using light gradient boosting machine as the base classifier. This method combines the advantages of ensemble learning and undersampling, and progressively improves model performance through adaptive sampling mechanisms and multiple rounds of iterative learning. Compared to other balancing methods, our approach demonstrated superior overall performance, achieving accuracies of 89. 02% and 87. 53% in the clinical examination and personal lifestyle dimensions, respectively. Finally, to enhance the practicality of predictions, we designed a web-based visual risk grading scorecard. On an independent test set, the accuracies for the clinical examination and personal lifestyle dimensions reached 85. 74% and 85. 48%, respectively, indicating that the information loss after binning was relatively low and that the features effectively captured factors related to diabetes risk. The proposed diabetes risk assessment model framework demonstrates good practicality and lays a solid foundation for diabetes risk warning and decision support.

Details DOI

AILAW Journal 2025 Journal Article

Summarizing judicial documents: a hybrid extractive- abstractive model with legal domain knowledge

Yan Gao
Jie Wu
Zhengtao Liu
Juan Li

Abstract The automatic summarization of judgment documents is a challenging task due to their length and the dispersed nature of the important information they contain. The prevailing approach to tackling the summarization of lengthy documents involves the integration of both extractive and abstractive summarization models. However, current extractive models face challenges in capturing all essential details due to the scattered distribution of pertinent information within judgment documents. Additionally, the existing abstractive models still grapple with the problem of "hallucinations" which leads to generating inaccurate information. In our work, we proposed a novel hybrid legal summarization method that incorporates legal domain knowledge into both the extractive model and abstractive model. The method consists of two parts: (1) The rhetorical role of sentences is identified by the sentence-level sequence labeling method, and the rhetorical information is integrated into the extractive model based on WoBERT through the conditional normalization to ensure that the identification of key sentences is both precise and complete. (2) The pre-trained model RoFormer is combined with Seq2Seq to construct a long text summarization model, and the prior knowledge in the external resources and the document itself is introduced into the decoding process to improve the faithfulness and coherence of the composed summary. In addition, the contrastive learning strategy is employed during the training process to enhance the robustness of the abstractive model. Experimental results on the CAIL2020 dataset show that the proposed model is superior to the baseline methods. Furthermore, our method outperforms GPT and other LLMs in processing judgment documents.

Details DOI

EAAI Journal 2024 Journal Article

A self-iterative learning with dual attention mechanism fusion method for pumpkin seed quality equipment

Weiming Shi
Runzhe Zhang
Kui Xuan
Cong Wang
Huayu Fu
Longgang Zhao
Juan Li
Zhongzhi Han

To perform fast and accurate classification of pumpkin seeds, three batches of pumpkin seed images were taken. A self-iterative learning large kernel attention-Squeeze and Excitation-Residual Network34 (LKA-SE-ResNet34) model was proposed by adding dual attention mechanism fusion of large kernal attention (LKA) mechanism and Squeeze and Excitation (SE) attention mechanism to each residual module of ResNet34 for recognizing pumpkin seeds. ResNet34 network model was chosen as the basic framework by comparing GoogleNet, AlexNet, EfficientNet, MobileNet, DenseNet, ResNet34 and Residual Network50 (ResNet50) deep learning network models. The comparation result showed that the top two models with the highest accuracy (Acc) are ResNet50 network model and ResNet34 network model among the compared models. The experimental results showed that the self-iterative learning LKA-SE-ResNet34 model outperformed the above-mentioned other network models in pumpkin seed recognition with an accuracy of 91. 8%. To further validate the effectiveness of the proposed model for small sample size of data, two-sided images and deformed images of pumpkin seeds were collected and used, and the experimental results still proved that the proposed model had good generalization ability and accuracy, with the accuracies of 93. 63% and 94. 15% for two sides of pumpkin seeds as well as an accuracy of 99. 03% for deformed pumpkin seeds. A set of seed sorting machine and an application (APP) for non-destructive testing of seeds were initially developed.

Details DOI

NeurIPS Conference 2024 Conference Paper

Learning Distinguishable Trajectory Representation with Contrastive Loss

Tianxu Li
Kun Zhu
Juan Li
Yang Zhang

Policy network parameter sharing is a commonly used technique in advanced deep multi-agent reinforcement learning (MARL) algorithms to improve learning efficiency by reducing the number of policy parameters and sharing experiences among agents. Nevertheless, agents that share the policy parameters tend to learn similar behaviors. To encourage multi-agent diversity, prior works typically maximize the mutual information between trajectories and agent identities using variational inference. However, this category of methods easily leads to inefficient exploration due to limited trajectory visitations. To resolve this limitation, inspired by the learning of pre-trained models, in this paper, we propose a novel Contrastive Trajectory Representation (CTR) method based on learning distinguishable trajectory representations to encourage multi-agent diversity. Specifically, CTR maps the trajectory of an agent into a latent trajectory representation space by an encoder and an autoregressive model. To achieve the distinguishability among trajectory representations of different agents, we introduce contrastive learning to maximize the mutual information between the trajectory representations and learnable identity representations of different agents. We implement CTR on top of QMIX and evaluate its performance in various cooperative multi-agent tasks. The empirical results demonstrate that our proposed CTR yields significant performance improvement over the state-of-the-art methods.

PDF Details DOI

EAAI Journal 2024 Journal Article

Self-ensembling with mask-boundary domain adaptation for optic disc and cup segmentation

Yanlin He
Jun Kong
Di Liu
Juan Li
Caixia Zheng

Due to different retinal fundus image acquisition devices having various imaging principles, domain shift often occurs between different datasets. Hence, a segmentation network well-trained on one dataset (i. e. , source domain) usually obtains very poor performance on another dataset (i. e. , target domain), which results in us having to annotate the new dataset (target domain) to train the segmentation network again. However, annotating a new dataset is usually time-consuming and laborious. To address this problem, we proposed a novel unsupervised domain adaptation method for optic disc and cup segmentation. To be specific, we first utilized a domain adaptation method based on self-ensembling to effectively align the features of the source domain and target domain. Then, we designed a novel backbone network (MBU-Net) to make full use of the mask and boundary information to improve the segmentation performance of self-ensembling. Finally, we proposed an output-level adversarial domain adaptation (OADA) to address the domain shift problem of the structured output space in self-ensembling. In experiments, we test our proposed method on three different target domain datasets including Target Domain 1 (RIM-ONE_r3 dataset), Target Domain 2 (Drishti-GS dataset) and Target Domain 3 (REFUGE dataset). The experimental results demonstrate that our proposed method outperforms the compared state-of-the-art methods in the optic disc and cup segmentation tasks.

Details DOI

YNICL Journal 2021 Journal Article

Longitudinal [18F]FDG and [13N]NH3 PET/CT imaging of brain and spinal cord in a canine hemisection spinal cord injury model

Lijian Zhang
Francisco R. López-Picón
Yingqin Jia
Yao Chen
Juan Li
Chunlei Han
Xiaoqing Zhuang
Hechun Xia

To further understand the neurological changes induced by spinal cord injury (SCI) in its acute and subacute stages, we evaluated longitudinal changes in glucose and glutamate metabolism in the spinal cord and brain regions of a canine hemisection SCI model. [18F]FDG and [13N]NH3 positron-emission tomography (PET) with computed tomography (CT) was performed before SCI and at 1, 3, 7, 14, and 21 days after SCI. Spinal cord [18F]FDG uptake increased and peaked at 3 days post SCI. Similar changes were observed in the brain regions but were not statistically significant. Compared to the acute phase of SCI, [13N]NH3 uptake increased in the subacute stage and peaked at 7 days post SCI in all analyzed brain regions. But in spinal cord, no [13N]NH3 uptake was detected before SCI when the blood-spinal cord barrier (BSCB) was intact, then gradually increased when the BSCB was damaged after SCI. [13N]NH3 uptake was significantly correlated with plasma levels of the BSCB disruption marker, monocyte chemoattractant protein-1 (MCP-1). Overall, we showed that SCI induced in vivo changes in glucose uptake in both the spinal cord and the examined brain regions, and changes in glutamine synthetase activity in the latter. Moreover, our results suggest that [13N]NH3 PET may serve as a potential method for assessing BSCB permeability in vivo.

Details DOI

YNIMG Journal 2012 Journal Article

Effects of lactate on the early visual cortex of non-human primates, investigated by pharmaco-MRI and neurochemical analysis

Veronika von Pföstl
Juan Li
Daniel Zaldivar
Jozien Goense
Xiaozhe Zhang
Nadine Serr
Nikos K. Logothetis
Alexander Rauch

In contrast to the limited use of functional magnetic resonance imaging (fMRI) in clinical diagnostics, it is currently a mainstay of neuroimaging in clinical and basic brain research. However, its non-invasive use in combination with its high temporal and spatial resolution would make fMRI a perfect diagnostic tool. We are interested in whether a pharmacological challenge imposed on the brain can be reliably traced by the blood oxygen level-dependent (BOLD) signal and possibly further exploited for diagnostics. We have chosen a systemic challenge with lactate and pyruvate to test whether the physiological formation of these monocarboxylic acids contributes to the BOLD signal and can be detected using fMRI. This information is also of interest because lactate levels in the cerebrospinal fluid rise concomitantly with reduced vascular responsiveness of the brain during the progression of Alzheimer disease (AD). We studied the BOLD response after a low-dose lactate challenge and monitored the induced plasma lactate levels in anesthetized non-human primates. We observed reliable lactate-induced BOLD responses, which could be confirmed at population and individual level by their strong correlation with systemic lactate concentrations. Comparable BOLD effects where observed after a slow infusion of pyruvate. We show here that physiological changes in lactate and pyruvate levels are indeed reflected in the BOLD signal, and describe the technical prerequisites to reliably trace a lactate challenge using BOLD-fMRI.

Details DOI

IROS Conference 2006 Conference Paper

Time-Optimal Trajectory Generation of a Fast-Motion Planar Parallel Manipulator

Yanjie Liu
Chenqi Wang
Juan Li
Lining Sun

This paper proposes time-optimal trajectory generation method for industrial robots. The proposed time-optimal trajectory generation method studies the relationship between the maximum acceleration and the maximum velocity, and presents an algorithm for deriving the optimal trajectory based on this relationship. In order to verify this method, a new planar parallel robotic manipulator with fast motion and high precision is designed. Finally, the proposed method is applied to the designed robot, and the simulation results prove that the method is effective for the industrial robot

Details