Yiwen Xing

ORCID: 0000-0003-1521-6616
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Data Visualization and Analytics
  • Computational and Text Analysis Methods
  • Image Retrieval and Classification Techniques
  • Semantic Web and Ontologies
  • Multimedia Communication and Technology
  • Acupuncture Treatment Research Studies
  • Advanced Text Analysis Techniques
  • Virtual Reality Applications and Impacts
  • Augmented Reality Applications
  • Healthcare and Venom Research
  • Digital Storytelling and Education
  • Robotics and Automated Systems
  • Digital Humanities and Scholarship
  • Traditional Chinese Medicine Studies
  • Technology Adoption and User Behaviour
  • Explainable Artificial Intelligence (XAI)
  • Smart Cities and Technologies
  • Video Analysis and Summarization
  • Natural Language Processing Techniques

Shanxi University of Traditional Chinese Medicine
2025

King's College London
2023-2024

In natural language processing (NLP), text classification tasks are increasingly fine-grained, as datasets fragmented into a larger number of classes that more difficult to differentiate from one another. As consequence, the semantic structures have become complex, and model decisions explain. Existing tools, suited for coarse-grained classification, falter under these additional challenges. response this gap, we worked closely with NLP domain experts in an iterative design-and-evaluation...

10.48550/arxiv.2403.15492 preprint EN arXiv (Cornell University) 2024-03-21

Visualizing event timelines for collaborative text writing is an important application navigating and understanding such data, as time passes the size complexity of both timeline increase. They are often employed by applications code repositories editors. In this paper, we present a visualization tool to explore historical records legislative texts, which were discussed voted on assembly representatives. Our focuses from documents that involve multiple people different topics, allowing...

10.1109/tvcg.2024.3376406 article EN IEEE Transactions on Visualization and Computer Graphics 2024-01-01

Abstract In natural language processing (NLP), text classification tasks are increasingly fine‐grained, as datasets fragmented into a larger number of classes that more difficult to differentiate from one another. As consequence, the semantic structures have become complex, and model decisions explain. Existing tools, suited for coarse‐grained classification, falter under these additional challenges. response this gap, we worked closely with NLP domain experts in an iterative...

10.1111/cgf.15098 article EN cc-by Computer Graphics Forum 2024-06-01

This paper introduces VIVRA (Voice Interactive Virtual Reality Annotation), a VR application combining multimodal interaction with large language models (LLMs) to transform users' ideas into interactive 3D visualizations. converts verbalized thoughts "idea balloons" that summarize and expand on detected topics by an LLM. allows users verbalize their in real time or record display the later. We evaluated effectiveness of exploratory study 29 participants user 10 participants. Our results show...

10.48550/arxiv.2409.15033 preprint EN arXiv (Cornell University) 2024-09-23

In mixed reality (MR) environments, understanding space and creating virtual objects is crucial to providing an intuitive rich user experience. This paper introduces sMoRe (Spatial Mapping Object Rendering Environment), MR application that combines Generative AI (GenAI) with large language models (LLMs) assist users in creating, placing, managing within physical spaces. allows use voice or typed text commands create place using GenAI while specifying spatial constraints. The system leverages...

10.48550/arxiv.2411.11752 preprint EN arXiv (Cornell University) 2024-11-18

Abstract Historical records from democratic processes and negotiation of constitutional texts are a complex type data to navigate due the many different elements that constantly interacting with one another: people, timelines, proposed documents, changes such voting approve or reject those changes. In particular, can offer various insights about relationships between people note in historical context, as alliances form dissolve over time unusual behavior. this paper, we present toolset...

10.1111/cgf.14824 article EN cc-by Computer Graphics Forum 2023-06-01

The circulation of historical books has always been an area interest for historians. However, the data used to represent journey a book across different places and times can be difficult domain experts digest due buried geographical chronological features within text-based presentations. This situation provides opportunity collaboration between visualization researchers paper describes design study where variant Nine-Stage Framework [46] was employed develop Visual Analytics (VA) tool called...

10.1109/tvcg.2023.3326923 article EN IEEE Transactions on Visualization and Computer Graphics 2023-01-01
Coming Soon ...