Author name cluster

Jie Zhao

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.

19 papers

2 author rows

EAAI Journal 2026 Journal Article

A twin-branch decoupled network for multi-class unsupervised anomaly detection

Bohan Wang
Jihong Wan
Jie Zhao
Xiaocao Ouyang
Xiaoping Li

The use of powerful pre-trained Vision Transformer (ViT) encoders in Multi-Class Unsupervised Anomaly Detection (MUAD) can lead to an “identity mapping shortcut”, where the model’s strong generalization inadvertently reconstructs anomalies. To address this specific manifestation of the over-generalization problem, this paper proposes DAD-Net, an innovative hybrid framework combining ViT and Convolutional Neural Networks (CNNs) that imposes synergistic constraints from both the model architecture and the training objective. Architecturally, a novel asymmetric twin-branch CNN decoder is designed to achieve a multi-scale reconstruction of normal patterns. Its shallow branch is specialized for reconstructing high-frequency textures, while its deep branch models abstract semantics. At the objective level, a hard feature loss compels the model to focus on the most complex normal patterns, effectively inhibiting the formation of the “identity mapping shortcut”. Comprehensive experiments validate DAD-Net’s direct applicability to engineering tasks. For industrial defect detection, the framework achieves superior performance on standard benchmarks. Furthermore, the model shows excellent generalization on a challenging cross-domain medical dataset. This highlights its potential as a versatile tool for other critical domains, such as medical diagnostic support. Ablation studies confirm the effectiveness of our core designs, positioning DAD-Net as a robust and practical solution for real-world quality control systems.

Details DOI

AAAI Conference 2026 Conference Paper

Universal EEG Epilepsy Detection via Evidential Multi-View De-Biasing

Ziqi Wen
Cai Xu
Wanqing Zhao
Jie Zhao
Wei Zhao

Epilepsy is a widespread neurological disorder characterized by highly patient-specific EEG patterns. Existing EEG-based seizure detection methods either train individualized models for each patient or adapt models pre-trained on known patients to new ones. However, when encountering previously unseen patients, these methods typically require retraining or fine-tuning, which limits their practical utility in clinical settings. This limitation can be linked to biases caused by patient-specific variations, which obscure the underlying pathological patterns of seizures. To address this, we propose an evidential multi-view framework that reinforces the learning of core epileptic features by promoting consistency across multiple views and reducing reliance on high-uncertainty, patient-specific segments. Specifically, we introduce Bias-guided Fisher-Evidential Multi-View Learning (BF-EML) to guide the model toward discovering intrinsic seizure patterns. BF-EML employs a two-stage training architecture: In Stage 1, we use the Fisher Information Matrix to reorder EEG segments by uncertainty and deliberately train a biased feature generator on low-evidence segments. In Stage 2, we design a dual-branch network where the biased and unbiased branches are alternately trained, encouraging the unbiased branch to reduce its reliance on patient-specific biases. Finally, we introduce a shift-calibrated fusion strategy to enhance the consistency of pathogenic feature integration. Extensive experiments on public datasets and a clinical dataset demonstrate that our method achieves superior performance in both single- and multi-patient scenarios. Importantly, it generalizes well to unseen patients without the need for retraining.

PDF Details DOI

IROS Conference 2025 Conference Paper

Design and Development of a Propulsion Induced Rolling Spherical Tensegrity Robot

Niansong Zhang
Rui Jiang
Xinfeng Shao
Yongliang Wu
Guiyan Qiang
Wenkai Huang
Yixiang Liu
Yibin Li

Spherical tensegrity structure has good dynamic stability, support strength and flexibility, and is widely used in the field of mobile robot research. Most of the tensegrity spherical robots deform themselves to make gravity work to realize the motion, but the deformation of both rods and ropes affects the robot's motion efficiency and motion instability. In this paper, a new type of tensegrity spherical robot is proposed, which is powered by six fixed ducted thrusters, and the thrust is provided to induce the robot to roll when in different attitudes. This paper firstly introduces the structural design and principle of the robot. Secondly analyzes the magnitude of the propulsive force required for the robot's motion and establishes a kinematic model. Finally, the robot prototype model was built and the robot motion experiments were conducted in simulation and the real environment respectively. The experimental results show that the robot has a simple structure but high motion efficiency, and has a strong ability to adapt to the environment.

Details

EAAI Journal 2025 Journal Article

Federated Reinforcement Learning for smart and privacy-preserving energy management of residential microgrids clusters

Mao Tan
Jie Zhao
Xiao Liu
Yongxin Su
Ling Wang
Rui Wang
Zhuocen Dai

Real-time energy management optimizes energy utilization and manages electrical loads, which is crucial for improving the operational efficiency of residential microgrids. However, existing management methods suffer from model complexity and slow training speed. To solve this problem, we introduce Federated Reinforcement Learning to manage residential microgrids by training a control strategy in a decentralized and privacy-preserving manner. Specifically, a residential microgrid energy optimization management model is first established based on the Proximal Policy Optimization (PPO) method. Then, we propose a cooperative training strategy for multiple Residential microgrids based on Federated Reinforcement Learning (RFRL). The proposed method improves the training speed of residential microgrid models by sharing parameter information, such as network weights, while protects users’ usage data. Finally, clustering analysis is introduced in the case of heterogeneous residential microgrid data. Extensive experimental evaluation shows that our method outperforms the alternative residential microgrid management methods in terms of cost efficiency.

Details DOI

IROS Conference 2025 Conference Paper

MagicGel: A Novel Visual-Based Tactile Sensor Design with Magnetic Gel

Jianhua Shan
Jie Zhao
Jiangduo Liu
Xiangbo Wang
Ziwei Xia
Guangzeng Chen
Zeyu Ren
Guangyuan Xu

Force estimation is the core indicator for evaluating the performance of tactile sensors, and it is also the key technical path to achieving precise force feedback mechanisms. This study proposes a design method for a visual tactile sensor (VBTS) that integrates a magnetic perception mechanism, and develops a new tactile sensor called MagicGel. The sensor uses strong magnetic particles as markers and captures magnetic field changes in real time through Hall sensors. On this basis, MagicGel achieves the coordinated optimization of multimodal perception capabilities: it not only has fast response characteristics, but also can perceive non-contact status information of home electronic products. Specifically, MagicGel simultaneously analyzes the visual characteristics of magnetic particles and the multimodal data of changes in magnetic field intensity, ultimately improving force estimation capabilities.

Details

NeurIPS Conference 2025 Conference Paper

Revolutionizing Graph Aggregation: From Suppression to Amplification via BoostGCN

Jiaxin Wu
Chenglong Pang
Guangxiong Chen
Jie Zhao

Graph Convolutional Networks (GCNs) based on linear aggregation have been widely applied across various domains due to their exceptional performance. To enhance performance, these networks often utilize the graph Laplacian norm to suppress the propagation of information from first-order neighbors. However, this approach may dilute valuable interaction information and make the model slowly learn sparse interaction relationships from neighbors, which increases training time and negatively affects performance. To address these issues, we introduce BoostGCN, a novel linear GCN model that focuses on amplifying significant interactions with first-order neighbors, which enables the model to accurately and quickly capture significant relationships. BoostGCN has relatively fixed parameters, making it user-friendly. Experiments on four real-world datasets demonstrate that BoostGCN outperforms existing state-of-the-art GCN models in both performance and efficiency.

PDF Details

ICML Conference 2025 Conference Paper

Robust Multimodal Large Language Models Against Modality Conflict

Zongmeng Zhang
Wengang Zhou 0001
Jie Zhao
Houqiang Li

Despite the impressive capabilities of multimodal large language models (MLLMs) in vision-language tasks, they are prone to hallucinations in real-world scenarios. This paper investigates the hallucination phenomenon in MLLMs from the perspective of modality conflict. Unlike existing works focusing on the conflicts between model responses and inputs, we study the inherent conflicts in inputs from different modalities that place MLLMs in a dilemma and directly lead to hallucinations. We formally define the modality conflict and construct a dataset named Multimodal Modality Conflict (MMMC) to simulate this phenomenon in vision-language tasks. Three methods based on prompt engineering, supervised fine-tuning, and reinforcement learning are proposed to alleviate the hallucination caused by modality conflict. Extensive experiments are conducted on the MMMC dataset to analyze the merits and demerits of these methods. Our results show that the reinforcement learning method achieves the best performance in mitigating the hallucination under modality conflict, while the supervised fine-tuning method shows promising and stable performance. Our work sheds light on the unnoticed modality conflict that leads to hallucinations and provides more insights into the robustness of MLLMs.

Details

NeurIPS Conference 2025 Conference Paper

Structure-Aware Cooperative Ensemble Evolutionary Optimization on Combinatorial Problems with Multimodal Large Language Models

Jie Zhao
Kang Cheong

Evolutionary algorithms (EAs) have proven effective in exploring the vast solution spaces typical of graph-structured combinatorial problems. However, traditional encoding schemes, such as binary or numerical representations, often fail to straightforwardly capture the intricate structural properties of networks. Through employing the image-based encoding to preserve topological context, this study utilizes multimodal large language models (MLLMs) as evolutionary operators to facilitate structure-aware optimization over graph data. To address the visual clutter inherent in large-scale network visualizations, we leverage graph sparsification techniques to simplify structures while maintaining essential structural features. To further improve robustness and mitigate bias from different sparsification views, we propose a cooperative evolutionary optimization framework that facilitates cross-domain knowledge transfer and unifies multiple sparsified variants of diverse structures. Additionally, recognizing the sensitivity of MLLMs to network layout, we introduce an ensemble strategy that aggregates outputs from various layout configurations through consensus voting. Finally, experiments on real-world networks through various tasks demonstrate that our approach improves both the quality and reliability of solutions in MLLM-driven evolutionary optimization.

PDF Details

NeurIPS Conference 2025 Conference Paper

TrajAgent: An LLM-Agent Framework for Trajectory Modeling via Large-and-Small Model Collaboration

Yuwei Du
Jie Feng
Jie Zhao
Yong Li

Trajectory modeling, which includes research on trajectory data pattern mining and future prediction, has widespread applications in areas such as life services, urban transportation, and public administration. Numerous methods have been proposed to address specific problems within trajectory modeling. However, the heterogeneity of data and the diversity of trajectory tasks make effective and reliable trajectory modeling an important yet highly challenging endeavor, even for domain experts. In this paper, we propose TrajAgent, a agent framework powered by large language models (LLMs), designed to facilitate robust and efficient trajectory modeling through automation modeling. This framework leverages and optimizes diverse specialized models to address various trajectory modeling tasks across different datasets effectively. In TrajAgent, we first develop UniEnv, an execution environment with a unified data and model interface, to support the execution and training of various models. Building on UniEnv, we introduce an agentic workflow designed for automatic trajectory modeling across various trajectory tasks and data. Furthermore, we introduce collaborative learning schema between LLM-based agents and small speciallized models, to enhance the performance of the whole framework effectively. Extensive experiments on four tasks using four real-world datasets demonstrate the effectiveness of TrajAgent in automated trajectory modeling, achieving a performance improvement of 2. 38%-69. 91% over baseline methods. The codes and data can be accessed via https: //github. com/tsinghua-fib-lab/TrajAgent.

PDF Details

AAAI Conference 2025 Conference Paper

UniTR: A Unified Framework for Joint Representation Learning of Trajectories and Road Networks

Jie Zhao
Chao Chen
Yuanshao Zhu
Mingyu Deng
Yuxuan Liang

Representation learning of urban spatial-temporal data is fundamental and critical, serving a wide range of intelligent applications. Given that road networks and trajectories are inherently interrelated, their joint representation learning can significantly enhance the accuracy and utility of these applications. However, effectively learning joint representations for these two types of data remains challenging, particularly due to the complexities of interaction modeling and cross-scale optimization. To this end, we propose a unified framework, named UniTR, for joint representation learning of road networks and trajectories. Specifically, we first design a hierarchical propagation mechanism to model the complex many-to-many interactions between road networks and trajectories, thereby generating informative embeddings. Then, a triple-level contrastive optimization module is incorporated to systematically select valid positive and negative samples, further refining the embeddings. Experiments conducted on real-world datasets from two cities clearly demonstrate the effectiveness and superiority of UniTR.

PDF Details DOI

TCS Journal 2025 Journal Article

Verifiable attribute-based multi-keyword search scheme with sensitive information hiding for cloud-assisted e-healthcare sharing systems

Jie Zhao
Hejiao Huang
Yongliang Xu
Xiaojun Zhang
Hongwei Du
Chao Huang

Cloud-assisted e-healthcare sharing systems (EHSSs) play an increasingly pivotal role in the contemporary healthcare field. By outsourcing electronic medical records (EMRs) to the cloud, hospitals can alleviate local storage and management burdens while facilitating data sharing. Due to the highly sensitive nature of EMRs, encryption is necessary before storing them on the cloud. Attribute-based keyword search (ABKS) enables the privacy protection of EMRs with efficient search services. However, there remain some limitations in practical application. Firstly, most ABKS schemes only support single keyword queries, resulting in inaccurate results and wastage of computing and bandwidth resources. Secondly, since sensitive information within EMRs is encrypted as a whole, different data users (including internal doctors and external researchers) should have varying access rights to prevent leakage of this sensitive information. Thirdly, incorrect search results could lead to misdiagnosis or endanger patients' lives and affect researchers' decision-making processes. To effectively tackle these challenges, this paper proposes a verifiable attribute-based multi-keyword search scheme with sensitive information hiding (VABMKS-SIH) for cloud-assisted EHSSs, where we present a secure model for multi-keyword search with two-level access structure by incorporating an improved blindness filtering technique into ciphertext-policy attribute-based encryption (CP-ABE) within existing keyword search framework. Our scheme employs a super-increasing sequence to aggregate multiple filtered data blocks into one unified ciphertext, thereby greatly reducing communication overhead during the transmission phases of ciphertext. To check the correctness of returned results, we introduce a lightweight algebraic signature algorithm based on fundamental algebraic operations. A security analysis demonstrates that VABMKS-SIH is provably secure under the random oracle mode. Additionally, we also evaluate the proposed scheme's performance to demonstrate its utility in cloud-assisted EHSSs.

Details DOI

ICLR Conference 2024 Conference Paper

Large Language Model Cascades with Mixture of Thought Representations for Cost-Efficient Reasoning

Murong Yue
Jie Zhao
Min Zhang
Liang Du
Ziyu Yao 0002

Large language models (LLMs) such as GPT-4 have exhibited remarkable performance in a variety of tasks, but this strong performance often comes with the high expense of using paid API services. In this paper, we are motivated to study building an LLM "cascade" to save the cost of using LLMs, particularly for performing (e.g., mathematical, causal) reasoning tasks. Our cascade pipeline follows the intuition that simpler questions can be addressed by a weaker but more affordable LLM, whereas only the most challenging questions necessitate the stronger and more expensive LLM. To realize this decision-making, we consider the "answer consistency" of the weaker LLM as a signal of the question difficulty and propose several methods for answering sampling and consistency checking, including one leveraging a mixture of two thought representations (i.e., Chain-of-Thought and Program-of-Thought). Through experiments on six reasoning benchmark datasets, with GPT-3.5-turbo and GPT-4 being the weaker and stronger LLMs, respectively, our cascade pipeline demonstrates comparable performance but reduces about 60% of the cost compared with fully using the stronger LLM.

Details

EAAI Journal 2023 Journal Article

A novel shape-based averaging algorithm for time series

Yutao Liu
Yong-An Zhang
Ming Zeng
Jie Zhao

Time series averaging is one of the essential subroutines in time series analysis. DTW Barycenter Averaging (DBA) has proven to be an effective and popular DTW-based time series averaging algorithm. However, DBA lacks the ability to average time series in the time domain, making it sensitive to initialization. In this research, we propose a novel shape-based time series averaging algorithm, called Shape DTW Weighted Averaging (ShapeDWA), to address the shortcomings of DBA. The proposed ShapeDWA algorithm combines the advantages of the DBA and the Cubic-spline DTW (CDTW) averaging methods. The concepts of time index averaging and re-sampling in the CDTW algorithm are incorporated into the DBA algorithm, giving ShapeDWA the ability to average a set of time series in both the amplitude and time domains. Moreover, ShapeDWA utilizes a weighed average instead of the barycenter average in DBA, which effectively attenuate the effects of noise, outliers, and local amplitude differences between the time series. To qualitatively evaluate and compare the proposed time series averaging algorithm, two metrics have been developed: average discrepancy distance and average time distortion. Extensive experimental results on the UCR time series database illustrate the superior performance of ShapeDWA over DBA and SSG, with an average reduction of 23. 42% and 24. 89% for average discrepancy distance, and 18. 76% and 19. 81% for average time distortion. Furthermore, the template matching-based classification experiment shows that ShapeDWA combined with these two developed metrics improves the classification rate by 17. 07% and 16. 42% compared to DBA and SSG, respectively.

Details DOI

EAAI Journal 2023 Journal Article

TCAMixer: A lightweight Mixer based on a novel triple concepts attention mechanism for NLP

Xiaoyan Liu
Huanling Tang
Jie Zhao
Quansheng Dou
MingYu Lu

Large-scale model sizes and expensive computing costs cause the challenge of deploying and applying large pre-trained models. Hence, this paper presents a novel Triple Concepts Attention Mechanism and a lightweight TCAMixer model for edge devices to classify texts. Furthermore, the TCAMixer abstracts textual concepts in a human way, which is unmatched by other counterparts such as pNLP-Mixer (a projection-based MLP-Mixer model for Nature Language Processing) and HyperMixer (a hyper network using dynamic token-mixing layers). Experimental results on several public datasets demonstrate that the TCAMixer outperforms the counterparts by a significant margin, for example, achieving 3% higher accuracy with a smaller model size of 0. 177M. Additionally, the TCAMixer achieves a performance of 85% to 98. 7% compared to that of large pre-trained models but only occupies 1/3000 to 1/2000 of their size on most test datasets.

Details DOI

IJCAI Conference 2022 Conference Paper

Charge Prediction by Constitutive Elements Matching of Crimes

Jie Zhao
Ziyu Guan
Cai Xu
Wei Zhao
Enze Chen

Charge prediction is to automatically predict the judgemental charges for legal cases. To convict a person/unit of a charge, the case description must contain matching instances of the constitutive elements (CEs) of that charge. This knowledge of CEs is a valuable guide for the judge in making final decisions. However, it is far from fully exploited for charge prediction in the literature. In this paper we propose a novel method named Constitutive Elements-guided Charge Prediction (CECP). CECP mimics human's charge identification process to extract potential instances of CEs and generate predictions accordingly. It avoids laborious labeling of matching instances of CEs by a novel reinforcement learning module which progressively selects potentially matching sentences for CEs and evaluates their relevance. The final prediction is generated based on the selected sentences and their relevant CEs. Experiments on two real-world datasets show the superiority of CECP over competitive baselines.

PDF Details DOI

IJCAI Conference 2022 Conference Paper

Region-Aware Metric Learning for Open World Semantic Segmentation via Meta-Channel Aggregation

Hexin Dong
Zifan Chen
Mingze Yuan
Yutong Xie
Jie Zhao
Fei Yu
Bin Dong
Li Zhang

As one of the most challenging and practical segmentation tasks, open-world semantic segmentation requires the model to segment the anomaly regions in the images and incrementally learn to segment out-of-distribution (OOD) objects, especially under a few-shot condition. The current state-of-the-art (SOTA) method, Deep Metric Learning Network (DMLNet), relies on pixel-level metric learning, with which the identification of similar regions having different semantics is difficult. Therefore, we propose a method called region-aware metric learning (RAML), which first separates the regions of the images and generates region-aware features for further metric learning. RAML improves the integrity of the segmented anomaly regions. Moreover, we propose a novel meta-channel aggregation (MCA) module to further separate anomaly regions, forming high-quality sub-region candidates and thereby improving the model performance for OOD objects. To evaluate the proposed RAML, we have conducted extensive experiments and ablation studies on Lost And Found and Road Anomaly datasets for anomaly segmentation and the CityScapes dataset for incremental few-shot learning. The results show that the proposed RAML achieves SOTA performance in both stages of open world segmentation. Our code and appendix are available at https: //github. com/czifan/RAML.

PDF Details DOI

YNICL Journal 2022 Journal Article

The longitudinal neural dynamics changes of whole brain connectome during natural recovery from poststroke aphasia

Liming Fan
Chenxi Li
Zi-gang Huang
Jie Zhao
Xiaofeng Wu
Tian Liu
Youjun Li
Jue Wang

Poststroke aphasia is one of the most dramatic functional deficits that results from direct damage of focal brain regions and dysfunction of large-scale brain networks. The reconstruction of language function depends on the hierarchical whole-brain dynamic reorganization. However, investigations into the longitudinal neural changes of large-scale brain networks for poststroke aphasia remain scarce. Here we characterize large-scale brain dynamics in left-frontal-stroke aphasia through energy landscape analysis. Using fMRI during an auditory comprehension task, we find that aphasia patients suffer serious whole-brain dynamics perturbation in the acute and subacute stages after stroke, in which the brains were restricted into two major activity patterns. Following spontaneous recovery process, the brain flexibility improved in the chronic stage. Critically, we demonstrated that the abnormal neural dynamics are correlated with the aberrant brain network coordination. Taken together, the energy landscape analysis exhibited that the acute poststroke aphasia has a constrained, low dimensional brain dynamics, which were replaced by less constrained and high dimensional dynamics at chronic aphasia. Our study provides a new perspective to profoundly understand the pathological mechanisms of poststroke aphasia.

Details DOI

IJCAI Conference 2020 Conference Paper

EndCold: An End-to-End Framework for Cold Question Routing in Community Question Answering Services

Jiankai Sun
Jie Zhao
Huan Sun
Srinivasan Parthasarathy

Routing newly posted questions (a. k. a cold questions) to potential answerers with suitable expertise in Community Question Answering sites (CQAs) is an important and challenging task. The existing methods either focus only on embedding the graph structural information and are less effective for newly posted questions, or adopt manually engineered feature vectors that are not as representative as the graph embedding methods. Therefore, we propose to address the challenge of leveraging heterogeneous graph and textual information for cold question routing by designing an end-to-end framework that jointly learns CQA node embeddings and finds best answerers for cold questions. We conducted extensive experiments to confirm the usefulness of incorporating the textual information from question tags and demonstrate that an end-2-end framework can achieve promising performances on routing newly posted questions asked by both existing users and newly registered users.

PDF Details DOI

EAAI Journal 2014 Journal Article

Adaptive dynamic surface control with Nussbaum gain for course-keeping of ships

Jialu Du
Ajith Abraham
Shuanghe Yu
Jie Zhao

Combining dynamic surface control and Nussbaum gain function with backstepping algorithm, a novel adaptive nonlinear control strategy is proposed for the nonlinear course control problem of ships with parameter uncertainties and completely unknown control coefficient. Dynamic surface control is incorporated into backstepping technique to overcome the problem of its inherent “explosion of terms” so that the control law is simpler and easier to implement in engineering. Nussbaum function is used to deal with the unknown sign of uncertain control coefficient and the possible controller singularity problem. By means of Lyapunov function and the lemma of Nussbaum function, it is proved theoretically that the designed adaptive nonlinear control law can force the actual course of ships to converge to and keep at the desired course of ships, while guarantee the global uniform boundedness of all signals of the resulting closed-loop control system. The effectiveness of the proposed scheme is demonstrated through the simulations involving two ships.

Details DOI