Author name cluster

Zhipeng Wang

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.

12 papers

2 author rows

AAAI Conference 2026 Short Paper

Cumulant Attention in Vision Transformers (Student Abstract)

Yuto Morimoto
Zhipeng Wang
Koji Yasuda

Transformer models have achieved remarkable success across diverse deep learning fields, including natural language processing (NLP) and computer vision (CV). One drawback of these models is that the computational cost of the softmax attention, the core component of the transformer, exhibits quadratic complexity in both time and memory. As data scales up various attempts have been reported to overcome this bottleneck. The objective of this study is to propose a novel attention mechanism, "Cumulant Attention", that systematically balances efficiency and accuracy. This proposal introduces a statistical-mechanics perspective and a reliable approximation based on cumulant expansion into the attention layer. The low-order variant reduces computational complexity to linear order, similar to the linear attention, while keeping nonlinearity of the softmax attention. We evaluate several variants on CV tasks, including image classification with ViT on ImageNet-100 and video classification with ViViT on UCF-101. Experimental results demonstrate that the cumulant attention outperforms the linear attention and achieves accuracy comparable to the softmax attention. These findings validate the effectiveness of our approach and highlight future directions, including scaling to larger models, extending to other modalities, and optimizing implementations for GPU hardware.

PDF Details DOI

AAAI Conference 2026 Conference Paper

LungNoduleAgent: A Collaborative Multi-Agent System for Precision Diagnosis of Lung Nodules

Cheng Yang
Hui Jin
Xinlei Yu
Zhipeng Wang
Yaoqun Liu
Fenglei Fan
Dajiang Lei
Gangyong Jia

Diagnosing lung cancer typically involves physicians identifying lung nodules in Computed tomography (CT) scans and generating diagnostic reports based on their morphological features and medical expertise. Although advancements have been made in using multimodal large language models for analyzing lung CT scans, challenges remain in accurately describing nodule morphology and incorporating medical expertise. These limitations affect the reliability and effectiveness of these models in clinical settings. Collaborative multi-agent systems offer a promising strategy for achieving a balance between generality and precision in medical applications, yet their potential in pathology has not been thoroughly explored. To bridge these gaps, we introduce LungNoduleAgent, an innovative collaborative multi-agent system specifically designed for analyzing lung CT scans. LungNoduleAgent streamlines the diagnostic process into sequential components, improving precision in describing nodules and grading malignancy through three primary modules. The first module, the Nodule Spotter, coordinates clinical detection models to accurately identify nodules. The second module, the Radiologist, integrates localized image description techniques to produce comprehensive CT reports. Finally, the Doctor Agent System performs malignancy reasoning by using images and CT reports, supported by a pathology knowledge base and a multi-agent system framework. Extensive testing on two private datasets and the public LIDC-IDRI dataset indicates that LungNoduleAgent surpasses mainstream vision-language models, agent systems, and advanced expert models such as GPT-4o, Claude 3.7 Sonnet, LLaMA-3.2 Vision, Qwen2.5-VL, Med-R1, MedGemma, MedAgent-Pro, MedAgents, MDAgent and LLaVA-Med. These results highlight the importance of region-level semantic alignment and multi-agent collaboration in diagnosing nodules. LungNoduleAgent stands out as a promising foundational tool for supporting clinical analyses of lung nodules.

PDF Details DOI

EAAI Journal 2025 Journal Article

A robust framework for interference-resistant surface crack detection and measurement in engineering structures

Jiangfeng Liu
Shijia Ma
Zhipeng Wang
Zhijie Jian
Tengyuan Zhang
Ruinian Sun

Modern engineering structures demand efficient and precise structural health monitoring to ensure safety and longevity, particularly in civil engineering where the intelligent detection and analysis of apparent cracks is critical. This study presents an integrated framework that synergizes advanced artificial intelligence with innovative imaging techniques to achieve robust, interference-resistant detection and measurement of surface cracks in civil engineering. We refine a mobile imaging system, with industrial cameras, precision zoom lenses, and a laser rangefinder, to secure stable data acquisition and accurate pixel-to-size conversion under challenging conditions, thereby providing a foundation for artificial intelligence driven crack detection. On the algorithm side, two optimized deep learning architectures are developed, leveraging depthwise separable convolutions and compound scaling to enhance precision and robustness. Rigorous evaluations confirm that tailored loss functions significantly improve convergence and accuracy. Across various lighting and background conditions, the proposed framework achieves an average crack pixel extraction accuracy of over 90 %, showing strong resistance to visual interference. Comparative experiments in multiple real-world scenarios demonstrate that it outperforms seven existing approaches in both accuracy and efficiency. In addition, we introduce a morphological transformation, which based algorithm links pixel-level detection with measurement of crack geometry and branching. Unlike previous studies, we consider the impact of imaging distance and camera shaking during field operation. The results remain accurate and stable even when the camera swings within 26°at different distances, highlighting practical robustness. Overall, this work advances artificial intelligence applications in fault detection and analysis, offering a practical solution for engineering maintenance.

Details DOI

EAAI Journal 2025 Journal Article

Dual-stage manifold preserving mixed supervised learning for bogie fault diagnosis under variable conditions

Ning Wang
Limin Jia
Yong Qin
Dechen Yao
Jianwei Yang
Zhipeng Wang

Bogie fault diagnosis for bogie is crucial to the safety of rail systems. However, since bogies work under normal states most of the time, the sporadic faulty samples are often submerged in massive normal samples, which are difficult to be distinguished and labeled. Therefore, the labeled training data are always insufficient or even lack of some certain fault states (novel faults), which brings great challenges to fault diagnosis, especially under variable working conditions. Therefore, this paper proposes a new framework named dual-stage manifold preserving mixed supervised learning (d-MMSL) to simultaneously absorb from labeled and unlabeled data effectively. Firstly, manifold similarity (MSLP) is presented to cluster unlabeled samples according to one-off calculation of the manifold similarity. In MSLP, the Best-versus-Second-Best differences and uncertain values are utilized to measure manifold distance and maintain the inherent structure of data. Secondly, Local manifold regularization - broad learning system (LMR-BLS) is presented to o deal with the problem of linear and nonlinear function transformation using simple incremental structure, which could further separate fuzzy sets from MSLP and distinguish the operation conditions of known states accurately. The proposed framework has been verified by a classical dataset and actual vibration data collected from bogies, which achieves a F1-score of 0. 99. It is proven that this framework outperforms traditional methods in accuracy and efficiency.

Details DOI

IJCAI Conference 2025 Conference Paper

From End-to-end to Step-by-step: Learning to Abstract via Abductive Reinforcement Learning

Zilong Wang
Jiongda Wang
Xiaoyong Chen
Meng Wang
Ming Ma
Zhipeng Wang
Zhenyu Zhou
Tianming Yang

Abstraction is a critical technique in general problem-solving, allowing complex tasks to be decomposed into smaller, manageable sub-tasks. While traditional symbolic planning relies on predefined primitive symbols to construct structured abstractions, its reliance on formal representations limits applicability to real-world tasks. On the other hand, reinforcement learning excels at learning end-to-end policies directly from sensory inputs in unstructured environments but struggles with compositional generalization in complex tasks with delayed rewards. In this paper, we propose Abductive Abstract Reinforcement Learning (A2RL), a novel neuro-symbolic RL framework bridging the two paradigms based on Abductive Learning (ABL), enabling RL agents to learn abstractions directly from raw sensory inputs without predefined symbols. A2RL induces a finite state machine to represent high-level, step-by-step procedures, where each abstract state corresponds to a sub-algebra of the original Markov Decision Process (MDP). This approach not only bridges the gap between symbolic abstraction and sub-symbolic learning but also provides a natural mechanism for the emergence of new symbols. Experiments show that A2RL can mitigate the delayed reward problem and improve the generalization capability compared to traditional end-to-end RL methods.

PDF Details DOI

AAAI Conference 2025 Conference Paper

MUCD: Unsupervised Point Cloud Change Detection via Masked Consistency

Yue Wu
Zhipeng Wang
Yongzhe Yuan
Maoguo Gong
Hao Li
Mingyang Zhang
Wenping Ma
Qiguang Miao

3D Change Detection (3DCD) has gradually become another research hotspot after image change detection. Recent works focus on using artificial labels for supervised or weakly-supervised training of siamese networks to segment changed points. However, labeling every points of multi-temporal point clouds is very expensive and time-consuming. In addition, these works lack effective self-supervised signals, and existing self-supervised signals often fail to capture sufficiently rich change information. To solve this problem, we assume that the powerful representation of 3D objects should model the consistency information of unchanged regions and distinguish different objects. Based on this assumption, we propose a new unsupervised framework called MUCD to learn change information of multi-temporal point clouds through bidirectional optimization of change segmentor and feature extractor. The training of network is divided into two stages. We first design a foreknowledge point contrastive loss based on the characteristics of the 3DCD task to initialize the feature extractor, and then propose a masked consistency loss to further learn the shared geometric information of unchanged regions in the multi-temporal point clouds, utilizing it as a free and powerful supervised signal to train a change segmentor. In the inference stage, only the segmentor is used to take multi-temporal point clouds as input and produce change segmentation result. Extensive experiments are conducted on SLPCCD and Urb3DCD, two real-world datasets of streets and urban buildings, to verify that our proposed unsupervised method is highly competitive and even outperforms supervised methods in scenes where semantic information changes occur, exhibiting better performance in generalization ability and robustness.

PDF Details DOI

IJCAI Conference 2025 Conference Paper

Rotation Invariant Spatial Networks for Single-View Point Cloud Classification

Feng Luan
Jiarui Hu
Changshi Zhou
Zhipeng Wang
Jiguang Yue
Yanmin Zhou
Bin He

Point cloud classification is critical for three-dimensional scene understanding. However, in real-world scenarios, depth cameras often capture partial, single-view point clouds of objects with different poses, making their accurate classification a challenge. In this paper, we propose a novel point cloud classification network that captures the detailed spatial structure of objects by constructing tetrahedra, which is different from point-wise operations. Specifically, we propose a RISpaNet block to extract rotation-invariant features. A rotation-invariant property generation module is designed in RISpaNet for constructing rotation-invariant tetrahedron properties (RITPs). Meanwhile, a multi-scale pooling module and a hybrid encoder are used to process RITPs to generate integrated rotation-invariant features. Further, for single-view point clouds, a complete point cloud auxiliary branch and a part-whole correlation module are jointly employed to obtain complete point cloud features from partial point clouds. Experimental results show that this network performs better than other state-of-the-art methods, evaluated on four public datasets. We achieved an overall accuracy of 94. 7% (+2. 0%) on ModelNet40, 93. 4% (+5. 9%) on MVP, 94. 7% (+6. 3%) on PCN and 94. 8% (+1. 7%) on ScanObjectNN. Our project website is https: //luxurylf. github. io/RISpaNet_project/.

PDF Details DOI

UAI Conference 2024 Conference Paper

Neighbor Similarity and Multimodal Alignment based Product Recommendation Study

Zhiqiang Zhang
Yongqiang Jiang
Qian Gao
Zhipeng Wang

Existing multimodal recommendation research still faces some challenges, such as not being able to fully mine the implicit relevance information of neighbor nodes, and the unreasonable weight allocation to imbalanced nodes. To address the aforementioned challenges, this paper introduces a new multimodal recommendation model called NSMAR+. Specifically, the model firstly constructs a neighbor similarity graph convolutional network to capture the implicit relevance information and reasonably assigns the attention weights through the graph attention mechanism. Secondly, the model introduces a modal alignment and fusion mechanism by using a multilayer perceptron (MLP) to map image and text features into a shared space for comparison and fusion. In addition, the model constructs a user co-interaction graph and an item semantic graph based on the original information and performs graph convolution operations to enhance the preference information of users and items, and to better capture the interactions and internal features between users and items. Finally, MLP is employed to aggregate user and item representations and predict personalized recommendation rankings. To validate the experiment’s efficacy, this paper compares with several leading multimodal recommendation models on public datasets with a performance improvement of 1% to 3%. The experimental outcomes indicate that the model in this paper has good superiority and accuracy in multimodal recommendation tasks.

Details

ICRA Conference 2024 Conference Paper

Ultrafast capturing in-flight objects with reprogrammable working speed ranges

Yongkang Jiang
Xin Tong
Zhongqing Sun
Yaimiin Zhou
Zhipeng Wang
Shuo Jiang
Zhen Yin
Yulong Ding

In-flight high-speed object capturing is crucial in nature to improve survival and adaptation to the environment, such as the predation of frogs, leopards, and eagles. Despite its ubiquitousness in nature, capturing fast-moving objects is extremely challenging in engineering implementations. In this paper, we report an ultrafast gripper based on tunable bistable structures. Different from current designs which are only suitable for objects with certain speed ranges once the grippers are fabricated, the working range of object speed of the proposed gripper could be reprogrammed by controlling the sensitivity of the structures. We present the design and fabrication of the proposed gripper in detail. A theoretical model is introduced to construct the energy landscape of the structures and the force response of the gripper when programmed to different states. The results show that in the original state, the gripper is capable of capturing a flying table tennis ball with a high speed of 15 m/s in only 6 ms. When the proposed gripper is controlled to the ultra-sensitive state, a flying ball with only 1 m/s could also be captured. This work broadens the frontiers of in-flight capturing design, and we envision broader promising applications.

Details

IROS Conference 2023 Conference Paper

Interpretable Motion Planner for Urban Driving via Hierarchical Imitation Learning

Bikun Wang
Zhipeng Wang
Chenhao Zhu
Zhiqiang Zhang
Zhichen Wang
Penghong Lin
Jingchu Liu
Qian Zhang

Learning-based approaches have achieved remarkable performance in the domain of autonomous driving. Leveraging the impressive ability of neural networks and large amounts of human driving data, complex patterns and rules of driving behavior can be encoded as a model to benefit the autonomous driving system. Besides, an increasing number of data-driven works have been studied in the decision-making and motion planning module. However, the reliability and the stability of the neural network is still full of uncertainty. In this paper, we introduce a hierarchical planning architecture including a high-level grid-based behavior planner and a low-level trajectory planner, which is highly interpretable and controllable. As the high-level planner is responsible for finding a consistent route, the low-level planner generates a feasible trajectory. We evaluate our method both in closed-loop simulation and real world driving, and demonstrate the neural network planner has outstanding performance in complex urban autonomous driving scenarios.

Details

IJCAI Conference 2021 Conference Paper

Domain-Smoothing Network for Zero-Shot Sketch-Based Image Retrieval

Zhipeng Wang
Hao Wang
Jiexi Yan
Aming WU
Cheng Deng

Zero-Shot Sketch-Based Image Retrieval (ZS-SBIR) is a novel cross-modal retrieval task, where abstract sketches are used as queries to retrieve natural images under zero-shot scenario. Most existing methods regard ZS-SBIR as a traditional classification problem and employ a cross-entropy or triplet-based loss to achieve retrieval, which neglect the problems of the domain gap between sketches and natural images and the large intra-class diversity in sketches. Toward this end, we propose a novel Domain-Smoothing Network (DSN) for ZS-SBIR. Specifically, a cross-modal contrastive method is proposed to learn generalized representations to smooth the domain gap by mining relations with additional augmented samples. Furthermore, a category-specific memory bank with sketch features is explored to reduce intra-class diversity in the sketch domain. Extensive experiments demonstrate that our approach notably outperforms the state-of-the-art methods in both Sketchy and TU-Berlin datasets.

PDF Details DOI

AAAI Conference 2019 Conference Paper

Multiple Saliency and Channel Sensitivity Network for Aggregated Convolutional Feature

Xuanlu Xiang
Zhipeng Wang
Zhicheng Zhao
Fei Su

In this paper, aiming at two key problems of instance-level image retrieval, i. e. , the distinctiveness of image representation and the generalization ability of the model, we propose a novel deep architecture - Multiple Saliency and Channel Sensitivity Network(MSCNet). Specifically, to obtain distinctive global descriptors, an attention-based multiple saliency learning is first presented to highlight important details of the image, and then a simple but effective channel sensitivity module based on Gram matrix is designed to boost the channel discrimination and suppress redundant information. Additionally, in contrast to most existing feature aggregation methods, employing pre-trained deep networks, MSCNet can be trained in two modes: the first one is an unsupervised manner with an instance loss, and another is a supervised manner, which combines classification and ranking loss and only relies on very limited training data. Experimental results on several public benchmark datasets, i. e. , Oxford buildings, Paris buildings and Holidays, indicate that the proposed MSCNet outperforms the state-of-the-art unsupervised and supervised methods.

PDF Details