Author name cluster

Hui Ma

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.

15 papers

2 author rows

AAAI Conference 2026 Conference Paper

AgentMental: An Interactive Multi-Agent Framework for Explainable and Adaptive Mental Health Assessment

Jinpeng Hu
Ao Wang
Qianqian Xie
Zhuo Li
Hui Ma
Dan Guo

Mental health assessment is crucial for early intervention and effective treatment, yet traditional clinician-based approaches are limited by the shortage of qualified professionals. Recent advances in artificial intelligence have sparked growing interest in automated psychological assessment, yet most existing approaches are constrained by their reliance on static text analysis, limiting their ability to capture deeper and more informative insights that emerge through dynamic interaction and iterative questioning. Therefore, in this paper, we propose a multi-agent framework for mental health evaluation that simulates clinical doctor-patient dialogues, with specialized agents assigned to questioning, adequacy evaluation, scoring, and updating. In detail, we introduce an adaptive questioning mechanism in which an evaluation agent assesses the adequacy of user responses to determine the necessity of generating targeted follow-up queries to address ambiguity and missing information. Additionally, we employ a tree-structured memory in which the root node encodes the user's basic information, while child nodes (e.g., topic and statement) organize key information according to distinct symptom categories and interaction turns. This memory is dynamically updated throughout the interaction to reduce redundant questioning and enhance the information extraction and contextual tracking capabilities. Experimental results on the DAIC-WOZ dataset illustrate the effectiveness of our proposed method, which achieves better performance than existing approaches. Our code is released at \url{https://github.com/MindIntLab-HFUT/AgentMental}.

PDF Details DOI

EAAI Journal 2026 Journal Article

Dual-path adaptive feature elevation system for detecting small targets in remote sensing imagery

Liangjun Xu
Hui Ma

Detecting small targets in remote sensing imagery has long been a challenge due to factors such as weak target features and complex backgrounds. Existing methods primarily focus on improving detection efficiency, often resulting in suboptimal accuracy for small targets. This study proposes the dual-path adaptive feature elevation system (DAES-net) for detecting small targets in remote sensing imagery, which significantly enhances small target detection accuracy while maintaining reasonable detection efficiency, effectively overcoming this challenge. DAES-net first integrates a proprietary dual-path self-calibration module (DSM). This module optimizes feature fusion through global modeling and local denoising, enhancing global feature correlation while reducing redundancy to provide more precise fused features for the detection system. Second, the dynamic normalized wasserstein distance (D-NWD) loss function was designed to achieve more precise localization of minute targets. By dynamically adjusting the regression weights of the constraint terms in the normalized wasserstein distance (NWD) loss function, D-NWD implements an optimal localization strategy for small targets, thereby improving the model's localization efficiency for them. Finally, the one-time aggregated feature reuse reparameterized convolution (FRRO) was proposed. This feature reuse structure prevents information loss for small targets while accelerating model inference efficiency. Experimental results demonstrate that DAES-Net achieves the highest mean average precision (MAP) across four public small object detection datasets, outperforming existing state-of-the-art methods. This highlights the significant contribution of this research to the field of small object detection.

Details DOI

AAAI Conference 2026 Conference Paper

LoRA in LoRA: Towards Parameter-Efficient Architecture Expansion for Continual Visual Instruction Tuning

Chang Che
Ziqi Wang
Pengwan Yang
Cheems Wang
Hui Ma
Zenglin Shi

Continual Visual Instruction Tuning (CVIT) enables Multimodal Large Language Models (MLLMs) to incrementally learn new tasks over time. However, this process is challenged by catastrophic forgetting, where performance on previously learned tasks deteriorates as the model adapts to new ones. A common approach to mitigate forgetting is architecture expansion, which introduces task-specific modules to prevent interference. Yet, existing methods often expand entire layers for each task, leading to significant parameter overhead and poor scalability. To overcome these issues, we introduce LoRA in LoRA (LiLoRA), a highly efficient architecture expansion method tailored for CVIT in MLLMs. LiLoRA shares the LoRA matrix A across tasks to reduce redundancy, applies an additional low-rank decomposition to matrix B to minimize task-specific parameters, and incorporates a cosine-regularized stability loss to preserve consistency in shared representations over time. Extensive experiments on a diverse CVIT benchmark show that LiLoRA consistently achieves superior performance in sequential task learning while significantly improving parameter efficiency compared to existing approaches.

PDF Details DOI

AAAI Conference 2026 Conference Paper

PointMC: Multi-view Consistent Encoding and Center-Global Feature Fusion for Point Clouds Understanding

Xinxing Yu
Ajian Liu
Sunyuan Qiang
Yuzhong Wang
Hui Ma
Yanyan Liang

Point cloud tasks have recently benefited from Mamba-based architecture, which leverage state space modeling to achieve strong performance. Previous studies have primarily focused on network design while overlooking the importance of position encoding and relying on coarse-grained geometric feature aggregation. The former leads to semantic ambiguity due to inconsistent spatial relationships, while the latter results in geometric feature dispersion by overlooking fine-grained local geometric details. To tackle the above problem, we propose a novel framework, PointMC, including Multi-view Consistent Learnable Position Encoding (MCLPE) and Center-Global Feature Fusion (CGFF), to provide semantically coherent positional guidance for inter-patch and enable fine-grained geometric structure aggregation within intra-patch regions. Specifically, the proposed MCLPE module is inspired by a spatial structure modeling mechanism guided by physical constraints, leverages multi-view virtual reconstruction and a learnable strategy to dynamically constrain spatial relationships along patch boundaries, thereby enhancing the semantic consistency and representational clarity across inter-patch regions. Furthermore, considering the lack of local structural information within each patch, the CGFF module employs a dual-guidance mechanism based on center and global structures to effectively promote the aggregation of local geometric features. Extensive experiments on multiple benchmark datasets validate the effectiveness of PointMC, consistently outperforming existing state-of-the-art methods, and demonstrating superior capability in capturing both inter-patch semantic consistency and intra-patch geometric details.

PDF Details DOI

YNIMG Journal 2026 Journal Article

The impact of chronic psychosocial stress on corticomuscular responses to thermal pain stimulation

Lili Li
Hui Ma
Yang Zheng
Zhongliang Yu

Psychosocial stress refers to the subjective experience and appraisal of real or potentially threatening psychosocial conditions. Pain is a complex physiological and psychological phenomenon, referring to unpleasant sensory and emotional experience associated with actual or potential tissue damage. To investigate the impact of chronic psychosocial stress on neural circuit responses to thermal pain, this study analyzed corticomuscular activities by electroencephalograph and electromyography. The results demonstrate that chronic psychosocial stress can change the cortical synchronization at α and γ frequencies and enhance motor unit recruitment under heat pain at both initial and progressive stages. Moreover, under progressive stimulation, pain-related neural feedback and localization functions may be disrupted, presenting impaired corticomuscular coherence. Therefore, chronic psychosocial stress can alter the integrated processing across both central and peripheral pathways, indicating a disintegration of the cortical-motor integration function of heat pain at initial and progressive stages.

Details DOI

IJCAI Conference 2025 Conference Paper

Advancing Community Detection with Graph Convolutional Neural Networks: Bridging Topological and Attributive Cohesion

Anjali de Silva
Gang Chen
Hui Ma
Seyed Mohammad Nekooei
Xingquan Zuo

Community detection, a vital technology for real-world applications, uncovers cohesive node groups (communities) by leveraging both topological and attribute similarities in social networks. However, existing Graph Convolutional Networks (GCNs) trained to maximize modularity often converge to suboptimal solutions. Additionally, directly using human-labeled communities for training can undermine topological cohesiveness by grouping disconnected nodes based solely on node attributes. We address these issues by proposing a novel Topological and Attributive Similarity-based Community detection (TAS-Com) method. TAS-Com introduces a novel loss function that exploits the highly effective and scalable Leiden algorithm to detect community structures with global optimal modularity. Leiden is further utilized to refine human-labeled communities to ensure connectivity within each community, enabling TAS-Com to detect community structures with desirable trade-offs between modularity and compliance with human labels. Experimental results on multiple benchmark networks confirm that TAS-Com can significantly outperform several state-of-the-art algorithms.

PDF Details DOI

IJCAI Conference 2025 Conference Paper

GATES: Cost-aware Dynamic Workflow Scheduling via Graph Attention Networks and Evolution Strategy

Ya Shen
Gang Chen
Hui Ma
Mengjie Zhang

Cost-aware Dynamic Workflow Scheduling (CADWS) is a key challenge in cloud computing, focusing on devising an effective scheduling policy to efficiently schedule dynamically arriving workflow tasks, represented as Directed Acyclic Graphs (DAG), to suitable virtual machines (VMs). Deep reinforcement learning (DRL) has been widely employed for automated scheduling policy design. However, the performance of DRL is heavily influenced by the design of the problem-tailored policy network and is highly sensitive to hyperparameters and the design of reward feedback. Considering the above-mentioned issues, this study proposes a novel DRL method combining Graph Attention Networks-based policy network and Evolution Strategy, referred to as GATES. The contributions of GATES are summarized as follows: (1) GATES can capture the impact of current task scheduling on subsequent tasks by learning the topological relationships between tasks in a DAG. (2) GATES can assess the importance of each VM to the ready task, enabling it to adapt to dynamically changing VM resources. (3) Utilizing Evolution Strategy's robustness, exploratory nature, and tolerance for delayed rewards, GATES achieves stable policy learning in CADWS. Extensive experimental results demonstrate the superiority of the proposed GATES in CADWS, outperforming several state-of-the-art algorithms. The source code is available at: https: //github. com/YaShen998/GATES.

PDF Details DOI

ICLR Conference 2025 Conference Paper

Graph Assisted Offline-Online Deep Reinforcement Learning for Dynamic Workflow Scheduling

Yifan Yang
Gang Chen
Hui Ma
Cong Zhang
Zhiguang Cao
Mengjie Zhang

Dynamic workflow scheduling (DWS) in cloud computing presents substantial challenges due to heterogeneous machine configurations, unpredictable workflow arrivals/patterns, and constantly evolving environments. However, existing research often assumes homogeneous setups and static conditions, limiting flexibility and adaptability in real-world scenarios. In this paper, we propose a novel *Graph assisted Offline-Online Deep Reinforcement Learning* (GOODRL) approach to building an effective and efficient scheduling agent for DWS. Our approach features three key innovations: (1) a *task-specific* graph representation and a *Graph Attention Actor Network* that enable the agent to dynamically assign focused tasks to heterogeneous machines while explicitly considering the future impact of each machine on these tasks; (2) a *system-oriented* graph representation and a *Graph Attention Critic Network* that facilitate efficient processing of new information and understanding its impact on the current state, crucial for managing unpredictable workflow arrivals/patterns in real-time; and (3) an *offline-online* method that utilizes imitation learning for effective offline training and applies gradient control and decoupled high-frequency critic training techniques during online learning to sustain the agent’s robust performance in rapidly changing environments. Experimental results demonstrate that GOODRL significantly outperforms several state-of-the-art algorithms, achieving substantially lower mean flowtime and high adaptability in various online and offline scenarios.

Details

EAAI Journal 2025 Journal Article

Multimodal unified generalization and translation network for intelligent fault diagnosis under dynamic environments

Chao Zhao
Weiming Shen
Enrico Zio
Hui Ma

Multimodal data fusion can generate reliable fault representations for intelligent fault diagnosis. However, simple data fusion strategies often introduce fault-irrelevant information, thereby reducing robustness against unknown domain shifts. Moreover, traditional methods generally lack adaptive mechanisms to address missing modalities, leading to considerable performance degradation under sensor failure conditions. To address these problems, this paper proposes a multimodal unified generalization and translation network. To learn invariant unified representations for resisting unknown data distribution shifts, information-enhanced concatenation first generates intra-domain and cross-domain representations. Subsequently, mutual information maximization is applied to remove fault-unrelated information from these representations. Finally, A hybrid ensemble diagnosis strategy fully leverages the interaction of multimodal information across different levels. In addition, semantic supervision investigates the relationships among different modalities and enables intermodal translation in the event of a sensor failure within the monitoring system. Extensive experimental results based on a public bearing dataset and a self-collected motor dataset indicate that the proposed method improves accuracy by 10. 53 % and 8. 47 % compared to the state-of-the-art methods, respectively. The code and datasets are available at https: //github. com/CHAOZHAO-1/MUGTN.

Details DOI

IROS Conference 2025 Conference Paper

Occlusion-Aware 6D Pose Estimation with Visual Observation Guided Diffusion Model

Yanbin Xiong
Buzhen Huang
Hui Ma
Yu Liu
Jun Cheng

Category-level 6D pose estimation in cluttered and occluded environments is a challenging task. Most existing methods rely on deterministic point-based correspondences to estimate target poses, which cannot consider the uncertainty for occluded objects, and thus result in inferior performance. In this paper, we propose a diffusion model guided by occlusion-aware observations to adaptively refine the object poses in occluded and cluttered scenes. Specifically, we first extract various 2D and 3D features from an RGB-D image to construct the conditions of diffusion model. In the reverse diffusion process, the model is guided by implicit correspondences, perception distance, and occlusion relationships to refine the noisy pose sampled from a standard Gaussian distribution. With several denoising steps, our method can produce accurate results that are consistent with image observations in occluded scenarios. The experimental results show that the proposed method can outperform baseline methods in major metrics in occlusion scenarios. Furthermore, our approach can also be applied in robotic grasping and manipulation tasks through grasping experiments in a cluttered enviroment on a physical UR5 robot.

Details

IROS Conference 2025 Conference Paper

SDF-guided Keyframe Selection: Novel Boost for NeRF SLAM Loop Closure

Hui Ma
Yu Liu
Jun Cheng

In the domain of Simultaneous Localization and Mapping (SLAM), loop closure is a linchpin for achieving accurate and consistent 3D environment mapping. However, the process is fraught with abrupt light changes and motion blur. These elements introduce uncertainties and inaccuracies in the data captured by sensors, severely undermining the system’s robustness. To address this critical challenge, we present a novel SDF-guided keyframe selection algorithm tailored for loop closure. Our approach capitalizes on the geometric insights provided by the Signed Distance Function (SDF) to meticulously choose keyframes, effectively mitigating the impact of noisy data. By doing so, we enhance the reliability of loop closure, refine the accuracy of 3D map reconstructions, and fortify the overall stability of the system. Our algorithm’s efficacy is substantiated through comprehensive experiments on datasets like Replica, ScanNet, and Tum-RGBD. Notably, it can be easily integrated as a plug-and-play module into diverse existing methods, enhancing their performance across different scenarios. Real-world trials using a hand-held LeTMC-520 camera for indoor scene reconstruction further validate its practicality and effectiveness.

Details

YNIMG Journal 2025 Journal Article

The association among individual gray matter volume of frontal-limbic circuitry, fatigue susceptibility, and comorbid neuropsychiatric symptoms following COVID-19

Xuan Niu
Wenrui Bao
Zhaoyao Luo
Pang Du
Heping Zhou
Haiyang Liu
Baoqi Wang
Huawen Zhang

BACKGROUND: Fatigue is often accompanied by comorbid sleep disturbance and psychiatric distress following the COVID-19 infection. However, identifying individuals at risk for developing post-COVID fatigue remains challenging. This study aimed to identify the neurobiological markers underlying fatigue susceptibility and further investigate their effect on COVID-19-related neuropsychiatric symptoms. METHODS: Individuals following a mild SARS-CoV-2 infection (COV+) underwent neuropsychiatric measurements (n = 335) and MRI scans (n = 271) within 1 month (baseline), and 191 (70.5 %) of the individuals were followed up 3 months after infection. Sixty-seven healthy controls (COV-) completed the same recruitment protocol. RESULTS: Whole-brain voxel-wise analysis showed that gray matter volume (GMV) during the acute phase did not differ between the COV+ and COV- groups. GMV in the right dorsolateral prefrontal cortex (DLPFC) and left dorsal anterior cingulate cortex (dACC) were associated with fatigue severity only in the COV+ group at baseline, which were assigned to the frontal system and limbic system, respectively. Furthermore, fatigue mediated the associations between volume differences in fatigue susceptibility and COVID-related sleep, post-traumatic stress disorder, anxiety and depression. Crucially, the initial GMV in the right DLPFC can predict fatigue symptoms 3 months after infection. CONCLUSIONS: We provide novel evidence on the neuroanatomical basis of fatigue vulnerability and emphasize that acute fatigue is an important link between early GMV in the frontal-limbic regions and comorbid neuropsychiatric symptoms at baseline and 3 months after infection. Our findings highlight the role of the frontal-limbic system in predisposing individuals to develop post-COVID fatigue.

Details DOI

EAAI Journal 2024 Journal Article

A novel metric-based model with the ability of zero-shot learning for intelligent fault diagnosis

Caizi Fan
Yongchao Zhang
Hui Ma
Zeyu Ma
Kun Yu
Songtao Zhao
Xiaoxu Zhang

Intelligent fault diagnosis plays an important role in maintaining the safe and reliable operation of rotating machinery. However, the data collected in real engineering scenarios may be severely insufficient, which presents challenges to the intelligent fault diagnosis methods. To address this problem, this paper introduces a metric-based meta learning approach for gear fault diagnosis under zero shot conditions. Firstly, a gear-rotor dynamics model is established to simulate the vibration signals under different fault conditions. And the signals are converted into energy maps through wavelet transformation to provide frequency domain fault features. Secondly, a deep convolutional network is employed as the feature extraction module to construct the prototype representations by calculating the average embedding within each fault class. Then, the distances between the actual signals collected from the gear test rig and the class prototypes are computed. Finally, the softmax is applied to convert these distances into probability distributions for outputting the predicted fault classes. Furthermore, label smoothing technology is introduced to mitigate the probability distribution differences between simulated signals and real signals. The experimental results demonstrate that the average diagnostic accuracy of the proposed model reaches 98. 9%, which is better than other models.

Details DOI

ICRA Conference 2023 Conference Paper

DEdgeNet: Extrinsic Calibration of Camera and LiDAR with Depth-discontinuous Edges

Yiyang Hu
Hui Ma
Leiping Jie
Hui Zhang 0062

This paper addresses the problem of calibrating extrinsic parameter matrix between an RGB camera and a LiDAR. Multimodal sensing systems are essential for fully autonomous navigation platforms. A key pre-requisite for such a system is calibration between different sensors. As the two most widely equipped sensors, calibration between RGB cameras and LiDARs remains challenging. Existing methods address this problem without using explicit geometric priors. In this paper, we propose a novel real-time network that utilizes depth-discontinuous edges extracted from a single image to calibrate cameras and LiDARs. Our network consists of two key components: (1) a self-supervised edge extraction network named DEdgeNet, which detects depth-discontinuous edges from a single image and extracts corresponding features; (2) prediction of the extrinsic parameter matrix between the camera and the LiDAR by matching fixed features in RGB images and updating depth features in a coarse-to-fine frame. Specifically, considering that edges are rich and common in natural scenes, DEdgeNet simplifies RGB image encoding and extracts fixed edges for feature matching. We conducted extensive experiments on the KITTI-odometry dataset. The results show that our method achieves an average rotation error of 0. 028° and an average translation error of 0. 247 cm, which demonstrates the superiority of our method.

Details

EAAI Journal 2023 Journal Article

Information complementary attention-based multidimension feature learning for person re-identification

Mingyang Wang
Hui Ma
Yiwei Huang

With the need for criminal investigation technology and the development of deep learning, the task of person re-identification has gradually become a research hotspot. Recently, various neural network-based person re-identification technologies designed by researchers have shown excellent results. However, most of the frameworks focus on complex structural design or redundant networks to guide model construction, which hugely increases the cost of train and application cost. In addition, the correlation between the channel information and spatial information on the pedestrian feature map is also relatively lacking. Therefore, we design a lightweight attention module to address the lack of correlation question response. The proposed module sequentially extracts person images’ channel and spatial features and effectively associates the two kinds of information through sequential connections. The proposed attention module has a simple structure, and the parameter increase in the backbone network is tiny. We place the fuse module in each feature extraction layer to focus on the pedestrian information extracted by each layer. To solve the problem of complex model structure, we choose the residual network as the backbone network and the attention mechanism to extract person features without using pose point estimation or additional network assistance to reduce model complexity. We adjust the drop rate of the person classification layer to improve the model’s generalization ability. We estimate the performance of our method on three public datasets: Market-1501, DukeMTMC-reID, and CUHK03 (both detected and labeled) demonstrate the proposed method’s effectiveness and obtain highly competitive performance on the three datasets.

Details DOI