Full Seminar Details

Shuang Ao

Knowledge Media Institute

 Shuang Ao
Building Trustworthy AI: Uncertainty Quantification and Failure Detection in Large Vision-Language Models
This event took place on Tuesday 28 May 2024 at 11:30

Although AI systems, especially LLMs, have been applied in various fields and achieved impressive performance, their safety and reliability are still a big concern. It is especially important for safety-critical tasks. One shared characteristic of these critical tasks is their risk sensitivity, where small mistakes can cause big consequences and even endanger life. Specifically, the current AI algorithms are unable to identify common causes for failure detection, as well as wrong predictions and OOD samples in inference. Furthermore, additional techniques are required to quantify the quality of predictions. All these contribute to inaccurate uncertainty quantification, which lowers trust in predictions. Hence obtaining accurate model uncertainty quantification and its further improvement are challenging. As vision and language are the most typical data types and have many open-source benchmark datasets, my work focuses on vision-language data processing for tasks like classification, image captioning, and vision question answering. My work aims to build a safeguard by developing techniques to ensure accurate model uncertainty for safety-critical tasks.

Watch the webcast replay >>

View all past events

Maven of the month logo - Photo of Prof. Ricardo Baeza-Yates

Maven of the Month

We are also inviting top experts in AI and Knowledge Technologies to discuss major socio-technological topics with an audience that comprises both members of the Knowledge Media Institute, as well as the wider staff at The Open University. Differently from our seminar series, these events follow a Q&A format.

Past events


Knowledge Media Institute
The Open University
Walton Hall
Milton Keynes
United Kingdom

Tel: +44 (0)1908 653800

Fax: +44 (0)1908 653169

Email: KMi Support


If you have any comments, suggestions or general feedback regarding our website, please email us at the address below.

Email: KMi Development Team