KXKai Xu

Kai Xu

*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


Kai Xu has a total of 29 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    NotebookRAG: Retrieving Multiple Notebooks to Augment the Generation of EDA Notebooks for Crowd-Wisdom

    by Yi Shan, Yixuan He, Zekai Shao, Kai Xu, Siming Chen

    High-quality exploratory data analysis (EDA) is essential in the data science pipeline, but remains highly dependent on analysts' expertise and effort. While recent LLM-based approaches partially reduce this burden, they struggle to generate effective analysis plans and appropriate insights and visualizations when user intent is abstract. Meanwhile, a vast collection of analysis notebooks produced across platforms and organizations contains rich analytical knowledge that can potentially guide automated EDA. Retrieval-augmented generation (RAG) provides a natural way to leverage such corpora, but general methods often treat notebooks as static documents and fail to fully exploit their potential knowledge for automating EDA. To address these limitations, we propose NotebookRAG, a method that takes user intent, datasets, and existing notebooks as input to retrieve, enhance, and reuse relevant notebook content for automated EDA generation. For retrieval, we transform code cells into context-enriched executable components, which improve retrieval quality and enable rerun with new data to generate updated visualizations and reliable insights. For generation, an agent leverages enhanced retrieval content to construct effective EDA plans, derive insights, and produce appropriate visualizations. Evidence from a user study with 24 participants confirms the superiority of our method in producing high-quality and intent-aligned EDA notebooks.

  • Open Access

    PromptMap: Supporting Exploratory Text-to-Image Generation

    by Yuhan Guo, Xingyou Liu, Xiaoru Yuan, Kai Xu

    Text-to-image generative models can be tremendously valuable in supporting creative tasks by providing inspirations and enabling quick exploration of different design ideas. However, one common challenge is that users may still not be able to find anything useful after many hours and hundreds of images. Without effective help, users can easily get lost in the vast design space, forgetting what has been tried and what has not. In this work, we first propose the Design-Exploration model to formalize the exploration process. Based on this model, we create an interactive visualization system, PromptMap, to support exploratory text-to-image generation. Our system provides a new visual representation that better matches the non-linear nature of such processes, making them easier to understand and follow. It utilizes novel visual representations and intuitive interactions to help users structure the many possibilities that they can explore. We evaluated the system through in-depth interviews with users.


  • Open Access

    A Scoping Review of Mixed Initiative Visual Analytics in the Automation Renaissance

    by Shayan Monadjemi, Yuhan Guo, Kai Xu, Alex Endert, Anamaria Crisan

    Artificial agents are increasingly integrated into data analysis workflows, carrying out tasks that were primarily done by humans. Our research explores how the introduction of automation re-calibrates the dynamic between humans and automating technology. To explore this question, we conducted a scoping review encompassing twenty years of mixed-initiative visual analytic systems. To describe and contrast the relationship between humans and automation, we developed an integrated taxonomy to delineate the objectives of these mixed-initiative visual analytics tools, how much automation they support, and the assumed roles of humans. Here, we describe our qualitative approach of integrating existing theoretical frameworks with new codes we developed. Our analysis shows that the visualization research literature lacks consensus on the definition of mixed-initiative systems and explores a limited potential of the collaborative interaction landscape between people and automation. Our research provides a scaffold to advance the discussion of human-AI collaboration during visual data analysis.

  • Open Access

    Beyond the Broadcast: Enhancing VR Tennis Broadcasting through Embedded Visualizations and Camera Techniques

    by Jun-Hsiang Yao, Jielin Feng, Xinfang Tian, Kai Xu, Gulshat Amirkhanova, Siming Chen

    Virtual Reality (VR) broadcasting has emerged as a promising medium for providing immersive viewing experiences of major sports events such as tennis. However, current VR broadcast systems often lack an effective camera language and do not adequately incorporate dynamic, in-game visualizations, limiting viewer engagement and narrative clarity. To address these limitations, we analyze 400 out-of-play segments from eight major tennis broadcasts to develop a tennis-specific design framework that effectively combines cinematic camera movements with embedded visualizations. We further refine our framework by examining 25 cinematic VR animations, comparing their camera techniques with traditional tennis broadcasts to identify key differences and inform adaptations for VR. Based on data extracted from the broadcast videos, we reconstruct a simulated game that captures the players' and ball's motion and trajectories. Leveraging this design framework and processing pipeline, we develope Beyond the Broadcast, a VR tennis viewing system that integrates embedded visualizations with adaptive camera motions to construct a comprehensive and engaging narrative. Our system dynamically overlays tactical information and key match events onto the simulated environment, enhancing viewer comprehension and narrative engagement while ensuring perceptual immersion and viewing comfort. A user study involving tennis viewers demonstrate that our approach outperforms traditional VR broadcasting methods in delivering an immersive, informative viewing experience.

  • Open Access

    vitaLITy 2: Reviewing Academic Literature Using Large Language Models

    by Hongye An, Arpit Narechania, Emily Wall, Kai Xu

    Academic literature reviews have traditionally relied on techniques such as keyword searches and accumulation of relevant back-references, using databases like Google Scholar or IEEEXplore. However, both the precision and accuracy of these search techniques is limited by the presence or absence of specific keywords, making literature review akin to searching for needles in a haystack. We present vitaLITy 2, a solution that uses a Large Language Model or LLM-based approach to identify semantically relevant literature in a textual embedding space. We include a corpus of 66,692 papers from 1970-2023 which are searchable through text embeddings created by three language models. vitaLITy 2 contributes a novel Retrieval Augmented Generation (RAG) architecture and can be interacted with through an LLM with augmented prompts, including summarization of a collection of papers. vitaLITy 2 also provides a chat interface that allow users to perform complex queries without learning any new programming language. This also enables users to take advantage of the knowledge captured in the LLM from its enormous training corpus. Finally, we demonstrate the applicability of vitaLITy 2 through two usage scenarios. vitaLITy 2 is available as open-source software at https://vitality-vis.github.io.


  • Open Access

    PrompTHis: Visualizing the Process and Influence of Prompt Editing during Text-to-Image Creation

    by Yuhan Guo, Hanning Shao, Can Liu, Kai Xu, Xiaoru Yuan

    Generative text-to-image models, which allow users to create appealing images through a text prompt, have seen a dramatic increase in popularity in recent years. However, most users have a limited understanding of how such models work and it often requires many trials and errors to achieve satisfactory results. The prompt history contains a wealth of information that could provide users with insights into what have been explored and how the prompt changes impact the output image, yet little research attention has been paid to the visual analysis of such process to support users. We propose the Image Variant Graph, a novel visual representation designed to support comparing prompt-image pairs and exploring the editing history. The Image Variant Graph models prompt differences as edges between corresponding images and presents the distances between images through projection. Based on the graph, we developed the PrompTHis system through co-design with artists. Besides Image Variant Graph, PrompTHis also incorporates a detailed prompt-image history and a navigation mini-map. Based on the review and analysis of the prompting history, users can better understand the impact of prompt changes and have a more effective control of image generation. A quantitative user study with eleven amateur participants and qualitative interviews with five professionals and one amateur user were conducted to evaluate the effectiveness of PrompTHis. The results demonstrate PrompTHis can help users review the prompt history, make sense of the model, and plan their creative process.


  • Open Access

    Latent Space Explorer: Visual Analytics for Multimodal Latent Space Exploration

    by Bum Chul Kwon, Samuel Friedman, Kai Xu, Steven A Lubitz, Anthony Philippakis, Puneet Batra, Patrick T Ellinor, Kenney Ng

    Machine learning models built on training data with multiple modalities can reveal new insights that are not accessible through unimodal datasets. For example, cardiac magnetic resonance images (MRIs) and electrocardiograms (ECGs) are both known to capture useful information about subjects' cardiovascular health status. A multimodal machine learning model trained from large datasets can potentially predict the onset of heart-related diseases and provide novel medical insights about the cardiovascular system. Despite the potential benefits, it is difficult for medical experts to explore multimodal representation models without visual aids and to test the predictive performance of the models on various subpopulations. To address the challenges, we developed a visual analytics system called Latent Space Explorer. Latent Space Explorer provides interactive visualizations that enable users to explore the multimodal representation of subjects, define subgroups of interest, interactively decode data with different modalities with the selected subjects, and inspect the accuracy of the embedding in downstream prediction tasks. A user study was conducted with medical experts and their feedback provided useful insights into how Latent Space Explorer can help their analysis and possible new direction for further development in the medical domain.