|
Thao Le |
|
I am a Postdoctoral Research Associate at the School of
Computer Science and Engineering, University of New South Wales, working on an ARC Discovery
Project on developing skilled AI companions.
Prior to this position, I completed my PhD at the School of
Computing and Information Systems, University of Melbourne. My PhD
project focused on designing explainable AI-assisted decision-making systems that aim to help users make
better decisions.
My research interests lie at the intersection between AI and humans, where I work to incorporate AI
models and human psychology.
News
- 03/2025: I'm starting a Postdoc position at UNSW Sydney
- 02/2025: I give a talk at CSIRO's Data61
- 10-11/2024: I visit Max Planck Institute for Human Development in Berlin
- 10/2024: I present our paper at ECAI 2024 in Spain
|
[ECAI 2024] Towards the New XAI: A Hypothesis-Driven
Approach to Decision Support Using Evidence
Thao Le, Tim Miller, Liz Sonenberg, Ronal Singh European Conference on Artificial Intelligence (ECAI). Main Track. Acceptance Rate: 547/2,344 (23%). Santiago de Compostela. Spain. [Paper]
Describe and evaluate an approach for
hypothesis-driven XAI based on the Weight of Evidence
(WoE) framework.
|
|
[AAAI 2023] Explaining Model Confidence Using
Counterfactuals
Thao Le, Tim Miller, Ronal Singh, Liz Sonenberg Association for the Advancement of Artificial Intelligence (AAAI). Main Track. Acceptance Rate: 1,721/8,777 (19.6%). Washington DC, USA. [Paper]
Formalise counterfactual explanation of confidence and
showing that this explanation can help users better
understand and trust the model.
|
|
[JAIR 2021] Goal Recognition for Deceptive Human Agents
through Planning and Gaze
Thao Le, Ronal Singh, Tim Miller Journal of Artificial Intelligence Research. IJCAI 2022 Journal Track. [Paper]
Present new models for goal recognition under deception
using a combination of gaze behaviour and observed
movements of the agent.
|
|
The original source code of this website is from here. |