KXKaiwen Xue

Kaiwen Xue

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Kaiwen Xue has a total of 101 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • VAMoRPH: Visual-Intent Adaptive Modular Routing with Plug-in Hazard Experts for Open-Scene Industrial Hazard Recognition

    by Qingzhi Yu, Kaiwen Xue, Ye Duan, Xuezhao Ding, Zhanqi Zhang, Dong Wang, Zhonghong Ou, Kaize Shi, Yifan Zhu

  • Open Access

    From Instruction Following to Cognitive Navigation: A Survey on the Evolution of Vision-and-Language Navigation

    by Kailin Lyu, Kangyi Wu, Pengna Li, Wenxuan Song, Di Wu, Jianwei He, Junting Chen, Ning Yang, Zebin Han, Kaiwen Luo, et al.

    Vision-and-Language Navigation (VLN) requires embodied agents to ground natural language instructions in visual perception and make navigation decisions in complex 3D environments, making it a central problem in embodied artificial intelligence. Since the introduction of the Room-to-Room (R2R) benchmark, VLN has made substantial progress. In recent years, as research settings have gradually expanded from closed and single indoor benchmark scenarios to open-world environments, the field has undergone a profound paradigm shift from passive instruction following on fixed benchmarks to autonomous cognitive navigation in open-world settings. However, existing surveys mainly organize prior work according to technical taxonomies, lacking a systematic characterization of this paradigm evolution. To address this gap, this survey proposes an evolution-centered unified analytical framework that reviews contemporary VLN research across four progressive layers: perception, cognition, learning, and generalization. It reveals the intrinsic connections and evolutionary logic among different technical lines, identifies key open challenges at each dimension, and outlines future research directions. This survey aims to provide VLN researchers with a clear panoramic view of capability evolution, while offering the broader embodied intelligence community a systematic roadmap from closed-benchmark evaluation toward trustworthy open-world deployment.

  • Open Access

    BIF-RCNN: Fusing Background Information for Rotated Object Detection

    by Jianbin Zhao, Xing Xu, Shaoying Wang, Pengfei Zhang, Shengyi Shen, Hui Zeng, Xiangshuai Bu, Yiran Shen, Kaiwen Xue, Ping Zong, et al.

    Rotated object detection aims to achieve precise localization by strictly aligning bounding boxes with object orientations, thereby minimizing background interference. Existing methods predominantly focus on extracting intra-object features within rotated bounding boxes. However, these approaches often overlook the discriminative contextual information from the surrounding background, leading to classification ambiguity when internal features are indistinguishable. To address this limitation, we propose Background Information Fusion R-CNN (BIF-RCNN), a novel rotated object detection framework that strategically re-integrates the background context from the object’s horizontal enclosing region to validate its category, turning previously discarded “noise” into auxiliary discriminative cues. Specifically, we introduce a dual-level rotation-horizontal feature fusion module (DFM), which leverages horizontal bounding boxes enclosing the rotated objects to extract contextual background features. These features are then adaptively fused with the internal object features to enhance the overall representation capability of the model. In addition, we design a Prediction Difference and Entropy-Constrained Loss (PDE Loss), which guides the model to focus on hard-to-classify samples that are prone to confusion due to similar feature representations. This loss function improves the model’s robustness and discriminative power. Extensive experiments conducted on the DOTA benchmark dataset demonstrate the effectiveness of the proposed method. Notably, our approach achieves up to a 4.02% AP improvement in single-category detection performance compared to a strong baseline, highlighting its superiority in rotated object detection tasks.

  • Open Access

    CreBench: Human-Aligned Creativity Evaluation from Idea to Process to Product

    by Kaiwen Xue, Chenglong Li, Zhonghong Ou, Guoxin Zhang, Kaoyan Lu, Shuai Lyu, Yifan Zhu, Ping Zong Junpeng Ding, Xinyu Liu, Qunlin Chen, et al.

    Human-defined creativity is highly abstract, posing a challenge for multimodal large language models (MLLMs) to comprehend and assess creativity that aligns with human judgments. The absence of an existing benchmark further exacerbates this dilemma. To this end, we propose CreBench, which consists of two key components: 1) an evaluation benchmark covering the multiple dimensions from creative idea to process to products; 2) CreMIT (Creativity Multimodal Instruction Tuning dataset), a multimodal creativity evaluation dataset, consisting of 2.2K diverse-sourced multimodal data, 79.2K human feedbacks and 4.7M multi-typed instructions. Specifically, to ensure MLLMs can handle diverse creativity-related queries, we prompt GPT to refine these human feedbacks to activate stronger creativity assessment capabilities. CreBench serves as a foundation for building MLLMs that understand human-aligned creativity. Based on the CreBench, we fine-tune open-source general MLLMs, resulting in CreExpert, a multimodal creativity evaluation expert model. Extensive experiments demonstrate that the proposed CreExpert models achieve significantly better alignment with human creativity evaluation compared to state-of-the-art MLLMs, including the most advanced GPT-4V and Gemini-Pro-Vision.


  • Open Access

    LogEDL: Log Anomaly Detection via Evidential Deep Learning

    by Yunfeng Duan, Kaiwen Xue, Hao Sun, Haotong Bao, Yadong Wei, Zhangzheng You, Yuantian Zhang, Xiwei Jiang, Sangning Yang, Jiaxing Chen, et al.

    With advancements in digital technologies such as 5G communications, big data, and cloud computing, the components of network operation systems have become increasingly complex, significantly complicating system monitoring and maintenance. Correspondingly, automated log anomaly detection has become a crucial means to ensure stable network operation and protect networks from malicious attacks or failures. Conventional machine learning and deep learning methods assume consistent distributions between the training and testing data, adhering to a closed-set recognition paradigm. Nevertheless, in realistic scenarios, systems may encounter new anomalies that were not present in the training data, especially in log anomaly detection. Inspired by evidential learning, we propose a novel anomaly detector called LogEDL, which supervises the training of the model through an evidential loss function. Unlike traditional loss functions, the evidential loss function not only focuses on correct classification but also quantifies the uncertainty of predictions. This enhances the robustness and accuracy of the model in handling anomaly detection tasks while achieving functionality similar to open-set recognition. To evaluate the proposed LogEDL method, we conduct extensive experiments on three datasets, i.e., HDFS, BGL, and Thunderbird, to detect anomalous log sequences. The experimental results demonstrate that our proposed LogEDL achieves state-of-the-art performance in anomaly detection.


  • Open Access

    LogEDL: Log Anomaly Detection via Evidential Deep Learning

    by Yunfeng Duan, Kaiwen Xue, Hao Sun, Haotong Bao, Yadong Wei, Zhangzheng You, Yuantian Zhang, Xiwei Jiang, Sangning Yang, Jiaxing Chen, et al.

    With advancements in digital technologies such as 5G communications, big data, and cloud computing, the components of network operation systems have become increasingly complex, significantly complicating system monitoring and maintenance. Correspondingly, automated log anomaly detection has become a crucial means to ensure stable network operation and protect them from malicious attacks or failures. Conventional machine learning and deep learning methods assume consistent distributions between the training and testing data, adhering to a closed-set recognition paradigm. Nevertheless, in realistic scenarios, systems may encounter new anomalies that were not present in the training data, especially in log anomaly detection. Inspired by evidential learning, we propose a novel anomaly detector called LogEDL, which supervises training of the model through an evidential loss function. Unlike traditional loss functions, the evidential loss function not only focuses on correct classification, but also quantifies the uncertainty of predictions. This enhances the robustness and accuracy of the model in handling anomaly detection tasks, while achieving functionality similar to open-set recognition. To evaluate the proposed LogEDL method, we conduct extensive experiments on three datasets, i.e., HDFS, BGL, and Thunderbird, to detect anomalous log sequences. Experimental results demonstrate that our proposed LogEDL achieves state-of-the-art performance in anomaly detection.


  • Open Access

    Learning to Diagnose: Meta-Learning for Efficient Adaptation in Few-Shot AIOps Scenarios

    by Yunfeng Duan, Haotong Bao, Guotao Bai, Yadong Wei, Kaiwen Xue, Zhangzheng You, Yuantian Zhang, Bin Liu, Jiaxing Chen, Shenhuan Wang, et al.

    With the advancement of technologies like 5G, cloud computing, and microservices, the complexity of network management systems and the variety of technical components have greatly increased. This rise in complexity has rendered traditional operations and maintenance methods inadequate for current monitoring and maintenance demands. Consequently, artificial intelligence for IT operations (AIOps), which harnesses AI and big data technologies, has emerged as a solution. AIOps plays a crucial role in enhancing service quality and customer satisfaction, boosting engineering productivity, and reducing operational costs. This article delves into the primary tasks involved in AIOps, such as anomaly detection, and log fault analysis and classification. A significant challenge identified in many AIOps tasks is the scarcity of fault sample data, indicating a natural alignment of these tasks with few-shot learning. Inspired by model-agnostic meta-learning (MAML), we propose a new anomaly detector, MAML-KAD, for application in various AIOps tasks. Observations confirm that meta-learning algorithms effectively enhance AIOps tasks, showcasing the wide-ranging application prospects of meta-learning algorithms in the field of AIOps. Moreover, we introduced an AIOps platform that embeds meta-learning within its diagnostic core and features streamlined log collection, caching, and alerting to automate the AIOps workflow.