Human-AI Teaming

I am an Associate Professor in the School of Computer Science at the University of Nottingham in UK. The university of part of the Russell Group, which includes top UK universities like Cambridge and Oxford. I am the co-director of School’s Visualisation Research Group (VisTAG), and an organiser of the Visualisation Interest Group at the Alan Turing Institute, UK’s national institute for data science and artificial intelligence.

My main research interest is Data Science, particularly Data Visualisation, i.e., presenting data visually to facilitate pattern discovery using human cognition and domain knowledge (some examples). I believe this works best when combining with computational methods such as Machine Learning and Artificial Intelligence. I published widely on these topics and organised many related events. My current work focuses on building the interactive visual interfaces between users and ML/AI systems.

I have worked on a wide range of data science projects (funded), both academic and consulting. The total project budget is over £12 million, and supported by both the UK/EU research council (such as EPSRC and EU Framework Program) and government (such as Ministry of Defence/Dstl and Department of Homeland Security) and industry (such as Microsoft and British Telecom).

If you are a company or academic that wants to discuss anything visualisation, please drop me an email at kai.xu@nottingham.ac.uk. I am very good at replying emails 🙂 Also, you can book a slot for a Teams chat with this link.

If you are a student looking for an intern or PhD, please see the Projects page for the possible project ideas and scholarship opportunities. You can see how the student projects are usually run here.

Funding

RAMP VIS – Visual Analytics for Covid-19 (2021-2022, £430,000)15 February 2021
EPSRC, 2021-2022, £430,000 This is a collaborative efforts with many visualisation researchers across the UK to provide visual analytics support in the fight against Covid-19. It started as a volunteer… Read more: RAMP VIS – Visual Analytics for Covid-19 (2021-2022, £430,000)
God, the Oracle, and the Nightclub Bouncer: Can human dignity be modelled in an AI-based decision support system for post-Covid health certification (2020-2021, £50,000)6 December 2020
Funder: ESPRC Network Plus SPRITE+ Date: 2020 – 2021 Funding: £50,000 Partner: Birmingham City University, King’s College London, Cardiff University, University of Exeter, Trilateral Research Ltd. In this project we… Read more: God, the Oracle, and the Nightclub Bouncer: Can human dignity be modelled in an AI-based decision support system for post-Covid health certification (2020-2021, £50,000)
Behaviour analytics for defence and security (2019, £80,000)8 November 2020
Funder: Defence Science and Technology Laboratory (Dstl), UK Date: 2019 Funding: £80,000 Partner: MASS Ltd In this project, we use the human-machine teaming approach to design a new visual analytics… Read more: Behaviour analytics for defence and security (2019, £80,000)

Papers

Visualization for epidemiological modelling: challenges, solutions, reflections and recommendations15 August 2022
Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences (Impact Factor 5.0) Open access: https://royalsocietypublishing.org/doi/full/10.1098/rsta.2021.0299 We report on an ongoing collaboration between epidemiological modellers and visualization researchers… Read more: Visualization for epidemiological modelling: challenges, solutions, reflections and recommendations
Visual Analytics of Contact Tracing Policy Simulations During an Emergency Response29 July 2022
EuroVis 2022 🏆 Best Paper Honorable Mention/ Computer Graphic Forum Open access: https://onlinelibrary.wiley.com/doi/full/10.1111/cgf.14520 Epidemiologists use individual-based models to (a) simulate disease spread over dynamic contact networks and (b) to investi-… Read more: Visual Analytics of Contact Tracing Policy Simulations During an Emergency Response
Provectories: Embedding-based Analysis of Interaction Provenance Data23 November 2021
IEEE Transaction on Visualisation and Computer Graphics (TVCG) Understanding user behavior patterns and visual analysis strategies is a long-standing challenge. Existing approaches rely largely on time-consuming manual processes such as… Read more: Provectories: Embedding-based Analysis of Interaction Provenance Data

Services

1st IEEE Workshop on Visualization and Provenance Across Domains1 March 2023
October 22nd, 2023 at IEEE VIS in Melbourne, Australia https://visxprov.github.io/ Our ambition is to build this into a series of workshops, targeting a different research community outside visualization each year,… Read more: 1st IEEE Workshop on Visualization and Provenance Across Domains
Dagstuhl Seminar: Human-Centered Approaches for Provenance in Automated Data Science1 February 2023
Sep 10 – Sep 15, 2023, Dagstuhl, Germany https://www.dagstuhl.de/23372 This Dagstuhl Seminar aims to bring together an interdisciplinary group of researchers and practitioners, spanning Data Science (DS) and Machine Learning… Read more: Dagstuhl Seminar: Human-Centered Approaches for Provenance in Automated Data Science
VizTIG: The Visualization interest group at the Alan Turing Institute1 January 2023
https://www.turing.ac.uk/research/interest-groups/visualization Visualization research and innovation has become critical to data science, it bridges the gap between digital data and human cognition. It is also emerging as an important methodology for… Read more: VizTIG: The Visualization interest group at the Alan Turing Institute

Projects

Visual Analytic for Sensemaking18 September 2023
Background Data Visualisation and Sensemaking The goal of this project is to support ‘Sensemaking‘ with Data Visualisation and/or Machine Learning. What is ‘Sensemaking’? This is a video of me explaining… Read more: Visual Analytic for Sensemaking
Human-AI Teaming18 September 2023
Background The recent breakthrough in Large Language Models (LLMs), such as chatGPT, and generative models, such as Stable Diffusion, can be tremendously valuable in supporting analysis and creative tasks. While… Read more: Human-AI Teaming
LLM for User Interaction Understanding17 September 2023
Background This project closely relates to the Visual Analytics for Sensemaking project. Please check that project webpage for the introduction on sensemaking. A published paper describing the idea and a… Read more: LLM for User Interaction Understanding
Data Science Provenance16 September 2023
Background While there are some efforts to automate the process of build machine learning model (commonly known as ‘AutoML‘), there are many tasks in the different stages of a data… Read more: Data Science Provenance
LLM for Automated Trading15 September 2023
The project aims to use the power of Large Language Models (LLMs) to achieve better automated trading. The main approach is to use LLM to analyse the sentiment of the… Read more: LLM for Automated Trading