Wenxiao Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Wenxiao Zhang has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Jin Bum Hong
Department of Computer Science and Software Engineering, The University of Western Australia, Perth, WA, Australia
5 shared publications - Yanbing Liu
Institute of Information Engineering,Chinese Academy of Sciences, Beijing, Beijing, China and School of Cyber Security, University of Chinese Academy of Sciences, Beijing, Beijing, China
4 shared publications - Yu Liu
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, Beijing, China and School of Cyber Security, University of Chinese Academy of Sciences, Beijing, Beijing, China
4 shared publications - Cong Cao
Institute of Information Engineering,Chinese Academy of Sciences, Beijing, Beijing, China
3 shared publications - Fangfang Yuan
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, Beijing, China
3 shared publications - Qiang Sun
The University of Western Australia, Perth, WA, Australia
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6854-6863
MIRAGE: How Conversation State Shapes Historical Evidence Use in Multimodal Personal Agents
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6854-6863
Open AccessMIRAGE: How Conversation State Shapes Historical Evidence Use in Multimodal Personal Agents
- Open Access
- 28 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 69-72
STIndex: A Context-Aware Multi-Dimensional Spatiotemporal Information Extraction System
Extracting structured knowledge from unstructured data still faces practical limitations: entity and event extraction pipelines remain brittle, knowledge graph construction requires costly ontology engineering, and cross-domain generalization is rarely production-ready. In contrast, space and time provide universal contextual anchors that naturally align heterogeneous information and benefit downstream tasks such as retrieval and reasoning. We introduce STIndex, an end-to-end system that structures unstructured content into a multidimensional spatiotemporal data warehouse. Users define domain-specific analysis dimensions with configurable hierarchies, while large language models perform context-aware extraction and grounding. STIndex integrates document-level memory, geocoding correction, and quality validation, and offers an interactive analytics dashboard for visualization, clustering, burst detection, and entity network analysis. In evaluation on a public health benchmark, STIndex improves spatiotemporal entity extraction F1 by 4.37% (GPT-4o-mini) and 3.60% (Qwen3-8B). A live demonstration and open-source code are available at https://stindex.ai4wa.com/dashboard.
- 28 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 69-72
Open AccessSTIndex: A Context-Aware Multi-Dimensional Spatiotemporal Information Extraction System
Extracting structured knowledge from unstructured data still faces practical limitations: entity and event extraction pipelines remain brittle, knowledge graph construction requires costly ontology engineering, and cross-domain generalization is rarely production-ready. In contrast, space and time provide universal contextual anchors that naturally align heterogeneous information and benefit downstream tasks such as retrieval and reasoning. We introduce STIndex, an end-to-end system that structures unstructured content into a multidimensional spatiotemporal data warehouse. Users define domain-specific analysis dimensions with configurable hierarchies, while large language models perform context-aware extraction and grounding. STIndex integrates document-level memory, geocoding correction, and quality validation, and offers an interactive analytics dashboard for visualization, clustering, burst detection, and entity network analysis. In evaluation on a public health benchmark, STIndex improves spatiotemporal entity extraction F1 by 4.37% (GPT-4o-mini) and 3.60% (Qwen3-8B). A live demonstration and open-source code are available at https://stindex.ai4wa.com/dashboard.
- 10 May 2026
- Published by Springer Nature
- p. 571-587
Trans-RAG: Query-Centric Vector Transformation for Secure Cross-Organizational Retrieval
- 10 May 2026
- Published by Springer Nature
- p. 571-587
Trans-RAG: Query-Centric Vector Transformation for Secure Cross-Organizational Retrieval
- Open Access
- 8 September 2025
- Published by Elsevier in Journal of Systems and Software
- Vol. 231
Enhancing reliability in LLM-integrated robotic systems: A unified approach to security and safety
- 8 September 2025
- Published by Elsevier in Journal of Systems and Software
- Vol. 231
Open AccessEnhancing reliability in LLM-integrated robotic systems: A unified approach to security and safety
- Open Access
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 801-804
Docs2KG: A Human-LLM Collaborative Approach to Unified Knowledge Graph Construction from Heterogeneous Documents
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 801-804
Open AccessDocs2KG: A Human-LLM Collaborative Approach to Unified Knowledge Graph Construction from Heterogeneous Documents
- Open Access
SafeEmbodAI: a Safety Framework for Mobile Robots in Embodied AI Systems
Embodied AI systems, including AI-powered robots that autonomously interact with the physical world, stand to be significantly advanced by Large Language Models (LLMs), which enable robots to better understand complex language commands and perform advanced tasks with enhanced comprehension and adaptability, highlighting their potential to improve embodied AI capabilities. However, this advancement also introduces safety challenges, particularly in robotic navigation tasks. Improper safety management can lead to failures in complex environments and make the system vulnerable to malicious command injections, resulting in unsafe behaviours such as detours or collisions. To address these issues, we propose \textit{SafeEmbodAI}, a safety framework for integrating mobile robots into embodied AI systems. \textit{SafeEmbodAI} incorporates secure prompting, state management, and safety validation mechanisms to secure and assist LLMs in reasoning through multi-modal data and validating responses. We designed a metric to evaluate mission-oriented exploration, and evaluations in simulated environments demonstrate that our framework effectively mitigates threats from malicious commands and improves performance in various environment settings, ensuring the safety of embodied AI systems. Notably, In complex environments with mixed obstacles, our method demonstrates a significant performance increase of 267\% compared to the baseline in attack scenarios, highlighting its robustness in challenging conditions.
Open AccessSafeEmbodAI: a Safety Framework for Mobile Robots in Embodied AI Systems
Embodied AI systems, including AI-powered robots that autonomously interact with the physical world, stand to be significantly advanced by Large Language Models (LLMs), which enable robots to better understand complex language commands and perform advanced tasks with enhanced comprehension and adaptability, highlighting their potential to improve embodied AI capabilities. However, this advancement also introduces safety challenges, particularly in robotic navigation tasks. Improper safety management can lead to failures in complex environments and make the system vulnerable to malicious command injections, resulting in unsafe behaviours such as detours or collisions. To address these issues, we propose \textit{SafeEmbodAI}, a safety framework for integrating mobile robots into embodied AI systems. \textit{SafeEmbodAI} incorporates secure prompting, state management, and safety validation mechanisms to secure and assist LLMs in reasoning through multi-modal data and validating responses. We designed a metric to evaluate mission-oriented exploration, and evaluations in simulated environments demonstrate that our framework effectively mitigates threats from malicious commands and improves performance in various environment settings, ensuring the safety of embodied AI systems. Notably, In complex environments with mixed obstacles, our method demonstrates a significant performance increase of 267\% compared to the baseline in attack scenarios, highlighting its robustness in challenging conditions.