Nan Wang

EAAI Journal 2026 Journal Article

A unified prediction framework for vehicle position and motion state based on transformer-gated recurrent unit and multi-task learning

• Xuliang Guo
• Hongfei Jia
• Qingyu Luo
• Qiuyang Huang
• Nan Wang
• Zixuan Mao

In complex traffic environments with the mixed driving of human-driven and autonomous vehicles, accurate prediction of the position and motion state of surrounding vehicles is crucial for autonomous vehicles to assess traffic risks and make safety planning decisions. However, existing methods neglect the significant differences in dynamic structures and temporal patterns exhibited by tasks in different directions when modeling the interdependencies between multiple tasks. To address this limitation, this paper adopts a direction-aware task division strategy, which functionally groups prediction tasks into lateral and longitudinal categories based on the motion direction, and proposes a multi-task unified prediction framework. The proposed framework consists of two parallel sub-models: the lateral task prediction model and the longitudinal task prediction model. This design achieves functional decoupling and avoids feature interference between tasks in different directions. Each sub-model adopts an architecture that integrates multi-task learning (MTL), Transformer, and Gated Recurrent Unit (GRU) to enable feature sharing and correlation modeling between tasks in the same direction. This framework effectively addresses the limitations of existing methods for predicting vehicle position and motion state, and provides a systematic modeling perspective for multi-task prediction research in autonomous driving. Experiments on two real-world datasets demonstrate that the proposed unified prediction framework achieves highly accurate vehicle position and motion state prediction, significantly outperforming representative predictive methods. Furthermore, ablation experiments demonstrate the effectiveness of the key design features of the proposed framework.

EAAI Journal 2026 Journal Article

Information gain-based diffusion model for group recommendation

• Lijin Mu
• Nan Wang
• Rui Liu
• Ziqi Liu

With the rapid development of social networks and their technologies, group recommendation systems have received increasing attention. However, traditional deep learning-based group recommendation methods still face two key challenges: vulnerability to noise, and sparse user-item interactions that hinder accurate preference modeling. To tackle these issues, we propose a group recommendation model based on information gain-driven diffusion. From the artificial intelligence perspective, our contribution lies in the engineering-oriented adaptation and enhancement of artificial intelligence techniques: we design a self-iterative diffusion denoising module to suppress noise in representation learning and an adaptive edge entropy algorithm based on information gain to guide graph augmentation under sparse interactions. These modules demonstrate how diffusion models and entropy principles can be structurally adapted to solve practical recommendation challenges. From the engineering application perspective, we further construct a Term Frequency–Inverse Document Frequency (TF-IDF) based weighted group graph to capture inter-group similarity and propose a multi-view fusion strategy to comprehensively model group preferences. Extensive experiments on real-world public datasets show that the proposed method effectively enhances denoising capability. It also significantly improves group recommendation accuracy, demonstrating strong practical value in scenarios such as social platforms and recommendation services.

YNICL Journal 2025 Journal Article

Advanced neuroimaging techniques to decipher brain connectivity networks in patients with disorder of consciousness: a narrative review

• Sipeng Zhu
• Tianqing Cao
• Qiheng He
• Nan Wang
• Yitong Jia
• Xiaoke Chai
• Yi Yang

Advanced neuroimaging techniques have revolutionized our ability to decode brain networks in patients with disorders of consciousness (DoC), offering unprecedented insights into the structural and functional underpinnings of consciousness impairment. This review systematically examines and summarizes the clinical applications of modern neuroimaging methodologies-specifically functional MRI and diffusion MRI- for DoC patients from three key perspectives: (1) pathogenic mechanism and theory evolution, (2) accurate diagnosis and prognosis assessment, and (3) treatment strategy and efficacy evaluation. By integrating network neuroscience with clinical insights, we highlight the transformative role of neuroimaging in unraveling network-level damage, refining clinical assessments, and guiding therapeutic innovations. We further outline the potential applicational challenges associated with leveraging neuroimaging techniques to advance both scientific research on consciousness networks and clinical practice in DoC management, hoping to better address these complex conditions.

NeurIPS Conference 2025 Conference Paper

Breaking the Discretization Barrier of Continuous Physics Simulation Learning

• Fan Xu
• Hao Wu
• Nan Wang
• Lilan Peng
• Kun Wang
• Wei Gong
• Xibin Zhao

The modeling of complicated time-evolving physical dynamics from partial observations is a long-standing challenge. Particularly, observations can be sparsely distributed in a seemingly random or unstructured manner, making it difficult to capture highly nonlinear features in a variety of scientific and engineering problems. However, existing data-driven approaches are often constrained by fixed spatial and temporal discretization. While some researchers attempt to achieve spatio-temporal continuity by designing novel strategies, they either overly rely on traditional numerical methods or fail to truly overcome the limitations imposed by discretization. To address these, we propose CoPS, a purely data-driven methods, to effectively model continuous physics simulation from partial observations. Specifically, we employ multiplicative filter network to fuse and encode spatial information with the corresponding observations. Then we customize geometric grids and use message-passing mechanism to map features from original spatial domain to the customized grids. Subsequently, CoPS models continuous-time dynamics by designing multi-scale graph ODEs, while introducing a Markov-based neural auto-correction module to assist and constrain the continuous extrapolations. Comprehensive experiments demonstrate that CoPS advances the state-of-the-art methods in space-time continuous modeling across various scenarios. The source code is available at~\url{https: //github. com/Sunxkissed/CoPS}.

NeurIPS Conference 2025 Conference Paper

Unifying Appearance Codes and Bilateral Grids for Driving Scene Gaussian Splatting

• Nan Wang
• Lixing Xiao
• Yuantao Chen
• Weiqing Xiao
• Pierre Merriaux
• Lei Lei
• Ziyang Yan
• Saining Zhang

Neural rendering techniques, including NeRF and Gaussian Splatting (GS), rely on photometric consistency to produce high-quality reconstructions. However, in real-world driving scenarios, it is challenging to guarantee perfect photometric consistency in acquired images. Appearance codes have been widely used to address this issue, but their modeling capability is limited, as a single code is applied to the entire image. Recently, the bilateral grid was introduced to perform pixel-wise color mapping, but it is difficult to optimize and constrain effectively. In this paper, we propose a novel multi-scale bilateral grid that unifies appearance codes and bilateral grids. We demonstrate that this approach significantly improves geometric accuracy in dynamic, decoupled autonomous driving scene reconstruction, outperforming both appearance codes and bilateral grids. This is crucial for autonomous driving, where accurate geometry is important for obstacle avoidance and control. Our method shows strong results across four datasets: Waymo, NuScenes, Argoverse, and PandaSet. We further demonstrate that the improvement in geometry is driven by the multi-scale bilateral grid, which effectively reduces floaters caused by photometric inconsistency.

AIIM Journal 2024 Journal Article

Corrigendum to “DeepGA for automatically estimating fetal gestational age through ultrasound imaging” [Artif. Intell. Med. 135 (2023) 102453]

• Tingting Dan
• Xijie Chen
• Miao He
• Hongmei Guo
• Xiaoqin He
• Jiazhou Chen
• Jianbo Xian
• Yu Hu

EAAI Journal 2024 Journal Article

FDTNet: Enhancing frequency-aware representation for prohibited object detection from X-ray images via dual-stream transformers

• Ziming Zhu
• Yu Zhu
• Haoran Wang
• Nan Wang
• Jiongyao Ye
• Xiaofeng Ling

With the extensive application of object detection in intelligent security, the demand for detecting prohibited items in X-ray images has become increasingly stringent. Unlike natural images, X-ray images present unique challenges such as complex backgrounds and mutual occlusion between prohibited and normal items. Consequently, applying traditional detection methods to X-ray images remains a significant challenge. To tackle these challenges, we have developed a unique frequency-aware dual-stream transformers (FDTNet) that is specifically designed for analyzing X-ray images. The FDTNet consists of two streams: one handles the original image, while the other deals with an image that has been enhanced with frequency domain features. In order to achieve precise detection of prohibited items, we introduce a frequency-aware module (FAM) that enhances the representation of prohibited items by utilizing information from the frequency domain. This FAM can be easily integrated into other backbones or detectors as it is a plug-and-play module. Additionally, to enhance the fusion of feature maps from both streams, we utilize a global and channel attention module (GCA) that aggregates texture representations for spatial feature streams. Our evaluation of the proposed FDTNet on the OPIXray datasets and PIDray datasets demonstrates that our detection mAP achieves 88. 02 and 68. 2, respectively. Extensive experiments conducted on publicly available datasets provide substantial evidence that our proposed network significantly improves the detection of prohibited items compared to state-of-the-art methods.

AAAI Conference 2024 Conference Paper

Revisiting Graph-Based Fraud Detection in Sight of Heterophily and Spectrum

• Fan Xu
• Nan Wang
• Hao Wu
• Xuezhi Wen
• Xibin Zhao
• Hai Wan

Graph-based fraud detection (GFD) can be regarded as a challenging semi-supervised node binary classification task. In recent years, Graph Neural Networks (GNN) have been widely applied to GFD, characterizing the anomalous possibility of a node by aggregating neighbor information. However, fraud graphs are inherently heterophilic, thus most of GNNs perform poorly due to their assumption of homophily. In addition, due to the existence of heterophily and class imbalance problem, the existing models do not fully utilize the precious node label information. To address the above issues, this paper proposes a semi-supervised GNN-based fraud detector SEC-GFD. This detector includes a hybrid filtering module and a local environmental constraint module, the two modules are utilized to solve heterophily and label utilization problem respectively. The first module starts from the perspective of the spectral domain, and solves the heterophily problem to a certain extent. Specifically, it divides the spectrum into various mixed-frequency bands based on the correlation between spectrum energy distribution and heterophily. Then in order to make full use of the node label information, a local environmental constraint module is adaptively designed. The comprehensive experimental results on four real-world fraud detection datasets denote that SEC-GFD outperforms other competitive graph-based fraud detectors. We release our code at https://github.com/Sunxkissed/SEC-GFD.

EAAI Journal 2023 Journal Article

Convolutional sparse filter with data and mechanism fusion: A few-shot fault diagnosis method for power transformer

• Jia Qin
• Dongsheng Yang
• Nan Wang
• Xueqing Ni

In actual industrial scenarios, fault data is rare and fault labels are difficult to obtain, which brings many obstacles for fault diagnosis. For this situation, this research proposes a novel semi-supervised convolutional sparse filter with local mechanism similarity regularization (CSF-LMSR) to construct a more reliable few-shot diagnosis method for power transformer. First, a sparse filter with local mechanism similarity regularization term (SF-LMSR) is designed as a more interpretable unsupervised feature extractor with prior knowledge. This unsupervised process enables the model to extract satisfactory features from the whole dataset even with a lower proportion of labeled data. Second, SF-LMSR is combined with convolutional neural network (CNN) by a novel coupling mode of kernel replacement, which enhances the learning ability of CNN. This classification model still adopts supervised learning training, but the demand for labeled fault data is greatly reduced, which reduces the burden of labels. The effectiveness of the proposed method is verified using real power transformer dissolved gas analysis (DGA) datasets. It can be seen from experimental results that the proposed method does provide a new perspective for transformer fault diagnosis, and it is a successful attempt for the power industry few-shot diagnosis problem.

AIIM Journal 2023 Journal Article

DeepGA for automatically estimating fetal gestational age through ultrasound imaging

• Tingting Dan
• Xijie Chen
• Miao He
• Hongmei Guo
• Xiaoqin He
• Jiazhou Chen
• Jianbo Xian
• Yu Hu

Accurate estimation of gestational age (GA) is vital for identifying fetal abnormalities. Conventionally, GA is estimated by measuring the morphology of the cranium, abdomen, and femur manually and inputting them into the classic Hadlock formula to assess fetal growth. However, this procedure incurs considerable overhead and suffers from bias caused by the operators, yielding suboptimal estimations. To address this challenge, we develop an automatic DeepGA model to achieve fully automatic GA prediction in an end-to-end manner. Our model uses a deep segmentation model (DeepSeg) to accurately identify and segment three critical tissues, including the cranium, abdomen, and femur, in which their morphology is automatically extracted. After that, we are able to directly estimate the GA via a deep regression model (DeepReg). We evaluate DeepGA on a large dataset, including 10, 413 ultrasound images from 7113 subjects. It achieves superior performance over the traditional measurement approach, with a mean absolute estimation error (MAE) of 5 days. Our DeepGA model is a novel automatic solution on the basis of artificial intelligence learning that can help radiologists improve the performance of GA estimation in various clinical scenarios, thereby enhancing the efficiency of prenatal examinations.

YNIMG Journal 2023 Journal Article

High-fidelity mesoscale in-vivo diffusion MRI through gSlider-BUDA and circular EPI with S-LORAKS reconstruction

• Congyu Liao
• Uten Yarach
• Xiaozhi Cao
• Siddharth Srinivasan Iyer
• Nan Wang
• Tae Hyung Kim
• Qiyuan Tian
• Berkin Bilgic

PURPOSE: * image blurring compared to typical highly accelerated echo-planar imaging (EPI) acquisitions at sub-millimeter isotropic resolution. METHODS: We first proposed a circular-EPI trajectory with partial Fourier sampling on both the readout and phase-encoding directions to minimize the echo-train-length and echo time. We then utilized this trajectory in an interleaved two-shot EPI acquisition with reversed phase-encoding polarity, to aid in the correction of off-resonance-induced image distortions and provide complementary k-space coverage in the missing partial Fourier regions. Using model-based reconstruction with structured low-rank constraint and smooth phase prior, we corrected the shot-to-shot phase variations across the two shots and recover the missing k-space data. Finally, we combined the proposed acquisition/reconstruction framework with an SNR-efficient RF-encoded simultaneous multi-slab technique, termed gSlider, to achieve high-fidelity 720 µm and 500 µm isotropic resolution in-vivo diffusion MRI. RESULTS: *-blurring. The in-vivo results of 720 µm and 500 µm datasets show high-fidelity diffusion images with reduced image blurring and echo time using the proposed approaches. CONCLUSIONS: * blurring at 500µm-isotropic-resolution compared to standard multi-shot EPI.

NeurIPS Conference 2023 Conference Paper

Multi-Objective Intrinsic Reward Learning for Conversational Recommender Systems

• Zhendong Chu
• Nan Wang
• Hongning Wang

Conversational Recommender Systems (CRS) actively elicit user preferences to generate adaptive recommendations. Mainstream reinforcement learning-based CRS solutions heavily rely on handcrafted reward functions, which may not be aligned with user intent in CRS tasks. Therefore, the design of task-specific rewards is critical to facilitate CRS policy learning, which remains largely under-explored in the literature. In this work, we propose a novel approach to address this challenge by learning intrinsic rewards from interactions with users. Specifically, we formulate intrinsic reward learning as a multi-objective bi-level optimization problem. The inner level optimizes the CRS policy augmented by the learned intrinsic rewards, while the outer level drives the intrinsic rewards to optimize two CRS-specific objectives: maximizing the success rate and minimizing the number of turns to reach a successful recommendation}in conversations. To evaluate the effectiveness of our approach, we conduct extensive experiments on three public CRS benchmarks. The results show that our algorithm significantly improves CRS performance by exploiting informative learned intrinsic rewards.

IJCAI Conference 2022 Conference Paper

IMO^3: Interactive Multi-Objective Off-Policy Optimization

• Nan Wang
• Hongning Wang
• Maryam Karimzadehgan
• Branislav Kveton
• Craig Boutilier

Most real-world optimization problems have multiple objectives. A system designer needs to find a policy that trades off these objectives to reach a desired operating point. This problem has been studied extensively in the setting of known objective functions. However, we consider a more practical but challenging setting of unknown objective functions. In industry, optimization under this setting is mostly approached with online A/B testing, which is often costly and inefficient. As an alternative, we propose Interactive Multi-Objective Off-policy Optimization (IMO^3). The key idea of IMO^3 is to interact with a system designer using policies evaluated in an off-policy fashion to uncover which policy maximizes her unknown utility function. We theoretically show that IMO^3 identifies a near-optimal policy with high probability, depending on the amount of designer's feedback and training data for off-policy estimation. We demonstrate its effectiveness empirically on several multi-objective optimization problems.

UAI Conference 2021 Conference Paper

CORe: Capitalizing On Rewards in Bandit Exploration

• Nan Wang
• Branislav Kveton
• Maryam Karimzadehgan

We propose a bandit algorithm that explores purely by randomizing its past observations. In particular, the sufficient optimism in the mean reward estimates is achieved by exploiting the variance in the past observed rewards. We name the algorithm Capitalizing On Rewards (CORe). The algorithm is general and can be easily applied to different bandit settings. The main benefit of CORe is that its exploration is fully data-dependent. It does not rely on any external noise and adapts to different problems without parameter tuning. We derive a $\tilde O(d\sqrt{n\log K})$ gap-free bound on the n-round regret of CORe in a stochastic linear bandit, where d is the number of features and K is the number of arms. Extensive empirical evaluation on multiple synthetic and real-world problems demonstrates the effectiveness of CORe.

AAAI Conference 2020 Conference Paper

Hypergraph Label Propagation Network

• Yubo Zhang
• Nan Wang
• Yufeng Chen
• Changqing Zou
• Hai Wan
• Xinbin Zhao
• Yue Gao

In recent years, with the explosion of information on the Internet, there has been a large amount of data produced, and analyzing these data is useful and has been widely employed in real world applications. Since data labeling is costly, lots of research has focused on how to efficiently label data through semi-supervised learning. Among the methods, graph and hypergraph based label propagation algorithms have been a widely used method. However, traditional hypergraph learning methods may suffer from their high computational cost. In this paper, we propose a Hypergraph Label Propagation Network (HLPN) which combines hypergraphbased label propagation and deep neural networks in order to optimize the feature embedding for optimal hypergraph learning through an end-to-end architecture. The proposed method is more effective and also efficient for data labeling compared with traditional hypergraph learning methods. We verify the effectiveness of our proposed HLPN method on a real-world microblog dataset gathered from Sina Weibo. Experiments demonstrate that the proposed method can significantly outperform the state-of-the-art methods and alternative approaches.

AAAI Conference 2018 Conference Paper

Hypergraph Learning With Cost Interval Optimization

• Xibin Zhao
• Nan Wang
• Heyuan Shi
• Hai Wan
• Jin Huang
• Yue Gao

In many classification tasks, the misclassification costs of different categories usually vary significantly. Under such circumstances, it is essential to identify the importance of different categories and thus assign different misclassification losses in many applications, such as medical diagnosis, saliency detection and software defect prediction. However, we note that it is infeasible to determine the accurate cost value without great domain knowledge. In most common cases, we may just have the information that which category is more important than the other categories, i. e. , the identification of defect-prone softwares is more important than that of defect-free. To tackle these issues, in this paper, we propose a hypergraph learning method with cost interval optimization, which is able to handle cost interval when data is formulated using the high-order relationships. In this way, data correlations are modeled by a hypergraph structure, which has the merit to exploit the underlying relationships behind the data. With a cost-sensitive hypergraph structure, in order to improve the performance of the classifier without precise cost value, we further introduce cost interval optimization to hypergraph learning. In this process, the optimization on cost interval achieves better performance instead of choosing uncertain fixed cost in the learning process. To evaluate the effectiveness of the proposed method, we have conducted experiments on two groups of dataset, i. e. , the NASA Metrics Data Program (NASA) dataset and UCI Machine Learning Repository (UCI) dataset. Experimental results and comparisons with state-of-the-art methods have exhibited better performance of our proposed method.

IJCAI Conference 2018 Conference Paper

Iterative Metric Learning for Imbalance Data Classification

• Nan Wang
• Xibin Zhao
• Yu Jiang
• Yue Gao

In many classification applications, the amount of data from different categories usually vary significantly, such as software defect predication and medical diagnosis. Under such circumstances, it is essential to propose a proper method to solve the imbalance issue among the data. However, most of the existing methods mainly focus on improving the performance of classifiers rather than searching for an appropriate way to find an effective data space for classification. In this paper, we propose a method named Iterative Metric Learning (IML) to explore the correlations among imbalance data and construct an effective data space for classification. Given the imbalance training data, it is important to select a subset of training samples for each testing data. Thus, we aim to find a more stable neighborhood for testing data using the iterative metric learning strategy. To evaluate the effectiveness of the proposed method, we have conducted experiments on two groups of dataset, i. e. , the NASA Metrics Data Program (NASA) dataset and UCI Machine Learning Repository (UCI) dataset. Experimental results and comparisons with state-of-the-art methods have exhibited better performance of our proposed method.