Author name cluster

Heng Zhou

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.

10 papers

1 author row

EAAI Journal 2026 Journal Article

A lightweight framework with adaptive feature enhancement for accurate pavement distress evaluation

Yi Liang
Jueqiang Tao
Qing Yang
Xin Qiu
Tingfeng Zhang
Yafang Liu
Heng Zhou

Timely pavement condition survey ensures optimal pavement performance and extends its service life. However, existing lightweight object detection models for pavement distress identification often struggle with a trade-off between computational efficiency and fine-grained feature extraction, fail to adapt to the irregular, elongated morphologies of cracks using fixed-grid convolutions, and are hindered by class imbalance and complex backgrounds that lead to misclassifications. To address these gaps, this study proposes the Lightweight Pavement Distress Network (LPD-Net), a crack-feature enhanced framework based on You Only Look Once version 11 (YOLOv11) for accurate pavement distress detection. Firstly, a large-scale dataset comprising depth images was constructed using a three-dimensional (3D) laser imaging sensor. Secondly, Dynamic Snake Convolution (DySConv) was integrated into the Cross Stage Partial with kernel size 2 (C3k2) module to adaptively adjust kernel sampling for better capturing crack contours and edges. Thirdly, a Bi-level Routing Attention (BRA) module was embedded to dynamically filter background noise and focus on sparse distress features, alleviating class imbalance. Lastly, a Lightweight Asymmetric Detection Head (LADH) incorporating Depthwise Separable Convolution (DSConv) was designed to reduce computational overhead while maintaining localization precision. Experimental results demonstrate that LPD-Net achieves a superior balance, reducing computational cost by 15. 9 % to 5. 3 Giga Floating Point Operations (GFLOPs) compared to the baseline while increasing mean Average Precision at 50 % intersection over union (mAP@50) by 6. 5 % to 0. 506. Measurement-oriented evaluation via Pavement Condition Index (PCI) further confirms its reliability, with 40. 72 % agreement within ± 5 PCI, aligning well with metrological standards.

Details DOI

EAAI Journal 2026 Journal Article

Designing a digital twin framework for degraded engines using an interpretable ensemble model with spatiotemporal graph learning and physics knowledge

Wenyue Cui
Xiaofei Diao
Tao Sun
Zezhou Liu
Heng Zhou

Accurate estimation of key parameters during aero-engine degradation is crucial for safe and reliable operation. This study presents a digital twin framework that integrates physics-informed graph correction with spatio-temporal graph learning to predict performance and compensate thrust loss in degraded engines. The framework constructs an initial sensor correlation graph from operational data and refines its connectivity using thermodynamic relationships to obtain a physically consistent graph structure. A spatio-temporal model combining graph convolutional networks and gated recurrent units estimates unmeasured parameters and predicts thrust under degradation, and its output drives a proportional–integral feedback controller that compensates performance loss in real time. The framework is validated on real-world aero-engine degradation data, achieving a root mean squared error of 0. 022 and a mean absolute error of 0. 017, outperforming baseline models. The results demonstrate improved robustness and practical applicability for aero-engine condition monitoring and performance retention.

Details DOI

AAAI Conference 2026 Conference Paper

State-Derivative-Aware Neural Controlled Differential Equations for Multivariate Time Series Anomaly Detection and Diagnosis

Xin Sun
Heng Zhou
Yuhao Wu
Chao Li

Multivariate time series anomaly detection is a crucial factor in real-world applications but a challenging task due to the complex temporal dependencies and system dynamics. Reconstruction-based methods have made great improvements in recent years. However, we observe an issue these methods are suffering, that they primarily measure deviations in the time points themselves when performing anomaly detection but ignore changes in the dynamic properties of the system. In these cases, they are unable to produce sufficient reconstruction errors to detect anomalies, so some potential abnormal time points caused by the dynamic evolution of the system are missing. To address this problem, we propose a novel method, SDA2D, which models system dynamics by the derivative of the NCDE-derived state vector with respect to time, enabling the learning of reconstruction deviation and system evolution jointly. Our experimental results show that SDA2D achieves noticeable improvements in four benchmark datasets, and the visualization also provides further instructions for anomaly diagnosis, which helps locate the sources of these anomalies.

PDF Details DOI

TMLR Journal 2026 Journal Article

The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

Guibin Zhang
Hejia Geng
Xiaohang Yu
Zhenfei Yin
Zaibin Zhang
Zelin Tan
Heng Zhou
Zhong-Zhi Li

The emergence of agentic reinforcement learning (Agentic RL) marks a paradigm shift from conventional reinforcement learning applied to large language models (LLM RL), reframing LLMs from passive sequence generators into autonomous, decision-making agents embedded in complex, dynamic worlds. This survey formalizes this conceptual shift by contrasting the degenerate single-step Markov Decision Processes (MDPs) of LLM RL with the temporally extended Partially Observable Markov Decision Processes (POMDPs) that define Agentic RL. Building on this foundation, we propose a comprehensive twofold taxonomy: one organized around core agentic capabilities, including planning, tool use, memory, reasoning, self-improvement, and perception, and the other around their applications across diverse task domains. Central to our thesis is that reinforcement learning serves as the critical mechanism for transforming these capabilities from static, heuristic modules into adaptive, robust agentic behavior. To support and accelerate future research, we consolidate the landscape of open-source environments, benchmarks, and frameworks into a practical compendium. By synthesizing over five hundred recent works, this survey charts the contours of this rapidly evolving field and highlights the opportunities and challenges that will shape the development of scalable, general-purpose AI agents.

PDF Details

EAAI Journal 2025 Journal Article

A large-scale mobile application knowledge graph for the research of cybersecurity: Construction and application

Weizhuo Li
Heng Zhou
Yiming Tan
Weiqi Luo
Qiu Ji
Yuyang Bian

Large-scale datasets for mobile applications (terms as “apps”) have been developed and become important assets for malware identification and other tasks of cybersecurity. However, existing datasets focus on extending the scale of apps, while ignoring the relevance among apps. On the other hand, several works try to integrate different metadata of apps to discover the relevance among apps, but most of them pay little attention to the roles such as normal users, developers, cybersecurity analysts, and they do not take full advantage of these metadata so that the fine-grained correlations among apps are difficult to be captured. To fill these gaps, we present a mobile application knowledge graph, which collects millions of apps’ information from various resources, including application markets, encyclopedias and news. Precisely, a lightweight ontology is designed for our knowledge graph. It defines a unified semantic schema of collected apps so that more linkages of these apps can be shared with each other. Moreover, we employ several promising algorithms of information extraction and knowledge alignment, and evaluate their performances during the process of construction. To detect more relevance with respect to sensitive apps, we propose a hybrid embedding-based method, in which the vector representations of apps are iteratively encoded with knowledge graph embedding methods and network embedding models. Experimental results show that our hybrid method can obtain better performances than several existing models for the relevance detection of sensitive apps. Finally, we list three use cases of mobile application knowledge graph for cybersecurity and discuss their limitations that would be improved in future works.

Details DOI

NeurIPS Conference 2025 Conference Paper

Multivariate Time Series Anomaly Detection with Idempotent Reconstruction

Xin Sun
Heng Zhou
Chao Li

Reconstruction-based methods are competitive choices for multivariate time series anomaly detection (MTS AD). However, one challenge these methods may suffer is over generalization, where abnormal inputs are also well reconstructed. In addition, balancing robustness and sensitivity is also important for final performance, as robustness ensures accurate detection in potentially noisy data, while sensitivity enables early detection of subtle anomalies. To address these problems, inspired by idempotent generative network, we take the view from the manifold and propose a novel module named I dempotent G eneration for A nomaly D etection (IGAD) which can be flexibly combined with a reconstruction-based method without introducing additional trainable parameters. We modify the manifold to make sure that normal time points can be mapped onto it while tightening it to drop out abnormal time points simultaneously. Regarding the latest findings of AD metrics, we evaluated IGAD on various methods with four real-world datasets, and they achieve visible improvements in VUS-PR than their predecessors, demonstrating the effective potential of IGAD for further improvements in MTS AD tasks. Our instructions on integrating IGAD into customized models and example codes are available at https: //github. com/ProEcho1/Idempotent-Generation-for-Anomaly-Detection-IGAD.

PDF Details

NeurIPS Conference 2025 Conference Paper

VIKI‑R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning

Li Kang
Xiufeng Song
Heng Zhou
Yiran Qin
Jie Yang
Xiaohong Liu
Philip Torr
Lei Bai

Coordinating multiple embodied agents in dynamic environments remains a core challenge in artificial intelligence, requiring both perception-driven reasoning and scalable cooperation strategies. While recent works have leveraged large language models (LLMs) for multi-agent planning, a few have begun to explore vision-language models (VLMs) for visual reasoning. However, these VLM-based approaches remain limited in their support for diverse embodiment types. In this work, we introduce VIKI-Bench, the first hierarchical benchmark tailored for embodied multi-agent cooperation, featuring three structured levels: agent activation, task planning, and trajectory perception. VIKI-Bench includes diverse robot embodiments, multi-view visual observations, and structured supervision signals to evaluate reasoning grounded in visual inputs. To demonstrate the utility of VIKI-Bench, we propose VIKI-R, a two-stage framework that fine-tunes a pretrained vision-language model (VLM) using Chain-of-Thought annotated demonstrations, followed by reinforcement learning under multi-level reward signals. Our extensive experiments show that VIKI-R significantly outperforms baselines method across all task levels. Furthermore, we show that reinforcement learning enables the emergence of compositional cooperation patterns among heterogeneous agents. Together, VIKI-Bench and VIKI-R offer a unified testbed and method for advancing multi-agent, visual-driven cooperation in embodied AI systems.

PDF Details

JBHI Journal 2024 Journal Article

An Implicit-Explicit Prototypical Alignment Framework for Semi-Supervised Medical Image Segmentation

Chunna Tian
Zhenxi Zhang
Xinbo Gao
Heng Zhou
Ran Ran
Zhicheng Jiao

Semi-supervised learning methods have been explored to mitigate the scarcity of pixel-level annotation in medical image segmentation tasks. Consistency learning, serving as a mainstream method in semi-supervised training, suffers from low efficiency and poor stability due to inaccurate supervision and insufficient feature representation. Prototypical learning is one potential and plausible way to handle this problem due to the nature of feature aggregation in prototype calculation. However, the previous works have not fully studied how to enhance the supervision quality and feature representation using prototypical learning under the semi-supervised condition. To address this issue, we propose an implicit-explicit alignment (IEPAlign) framework to foster semi-supervised consistency training. In specific, we develop an implicit prototype alignment method based on dynamic multiple prototypes on-the-fly. And then, we design a multiple prediction voting strategy for reliable unlabeled mask generation and prototype calculation to improve the supervision quality. Afterward, to boost the intra-class consistency and inter-class separability of pixel-wise features in semi-supervised segmentation, we construct a region-aware hierarchical prototype alignment, which transmits information from labeled to unlabeled and from certain regions to uncertain regions. We evaluate IEPAlign on three medical image segmentation tasks. The extensive experimental results demonstrate that the proposed method outperforms other popular semi-supervised segmentation methods and achieves comparable performance with fully-supervised training methods.

Details DOI

NeurIPS Conference 2024 Conference Paper

SS3DM: Benchmarking Street-View Surface Reconstruction with a Synthetic 3D Mesh Dataset

Yubin Hu
Kairui Wen
Heng Zhou
Xiaoyang Guo
Yong-Jin Liu

Reconstructing accurate 3D surfaces for street-view scenarios is crucial for applications such as digital entertainment and autonomous driving simulation. However, existing street-view datasets, including KITTI, Waymo, and nuScenes, only offer noisy LiDAR points as ground-truth data for geometric evaluation of reconstructed surfaces. These geometric ground-truths often lack the necessary precision to evaluate surface positions and do not provide data for assessing surface normals. To overcome these challenges, we introduce the SS3DM dataset, comprising precise \textbf{S}ynthetic \textbf{S}treet-view \textbf{3D} \textbf{M}esh models exported from the CARLA simulator. These mesh models facilitate accurate position evaluation and include normal vectors for evaluating surface normal. To simulate the input data in realistic driving scenarios for 3D reconstruction, we virtually drive a vehicle equipped with six RGB cameras and five LiDAR sensors in diverse outdoor scenes. Leveraging this dataset, we establish a benchmark for state-of-the-art surface reconstruction methods, providing a comprehensive evaluation of the associated challenges. For more information, visit our homepage at https: //ss3dm. top.

PDF Details DOI

EAAI Journal 2023 Journal Article

Quaternion convolutional neural networks for hyperspectral image classification

Heng Zhou
Xin Zhang
Chunlei Zhang
Qiaoyu Ma

Quaternion convolutional neural networks (QCNNs) can capture quaternion features, which contain not only the contextual information among quaternion feature units but also utilize the quaternion algebra inside the quaternion feature units to express structural information. However, building efficient QCNNs for hyperspectral image (HSI) classification is a challenge due to the lack of methods to map real features into quaternion features and the missing key quaternion modules. This paper proposes methodologies to build QCNNs specifically for HSI classification and designs several key quaternion modules. Firstly, a novel quaternion feature encoder is presented to map real HSI features into quaternion features. Secondly, a paradigm is designed to conveniently modify classical convolutional neural networks to implement QCNNs for HSI classification. Thirdly, we propose a new separable quaternion convolutional neural network (SQNet) based on presented advanced quaternion modules, such as separable quaternion convolutions and quaternion attention mechanisms. In addition, the computational rules in quaternion neurons are improved to enhance the adaptability of QCNNs. Experiments conducted on four widely used HSI datasets indicate that the implemented QCNNs and the proposed SQNet achieve satisfactory results for HSI classification with limited training samples.

Details DOI