Currently browsing: Items authored or edited by Shuang Ao https://orcid.org/0000-0003-2648-3082

Ao, Shuang (2025). Building Trustworthy AI: Uncertainty Quantification and Failure Detection in Large Vision-Language Models. Doctor of Philosophy (PhD) thesis The Open University.

• Download Final Version (PDF / 2MB)

Ao, Shuang; Rüger, Stefan and Siddharthan, Advaith (2024). CSS: Contrastive Semantic Similarities for Uncertainty Quantification of LLMs. In: Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence (Kiyavash, Negar and Mooij, Joris M. eds.), Proceedings of Machine Learning Research, pp. 77–87.

• Download Published Version (PDF / 660kB)

Ao, Shuang; Rueger, Stefan and Siddharthan, Advaith (2023). Two Sides of Miscalibration: Identifying Over and Under-Confidence Prediction for Network Calibration. In: UAI '23: Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence Vol. 216, Proceedings of Machine Learning Research (PMLR), Pittsburgh, pp. 77–87.

• Download Published Version (PDF / 368kB)

Ao, Shuang (2023). Building Safe and Reliable AI systems for Safety Critical Tasks with Vision-Language Processing. In: Advances in Information Retrieval. ECIR 2023. Lecture Notes in Computer Science, vol 13982, Springer.

• Download Accepted Manuscript (PDF / 242kB)

Ao, Shuang; Rüger, Stefan and Siddharthan, Advaith (2023). Empirical Optimal Risk to Quantify Model Trustworthiness for Failure Detection. In: CEUR Workshop Proceedings, CEUR-WS, 3505.

• Download Published Version (PDF / 747kB)

Ao, Shuang; Rüger, Stefan and Siddharthan, Advaith (2022). Confidence-Aware Calibration and Scoring Functions for Curriculum Learning. In: 2022 15th International Conference on Machine Vision., 18-20 Nov 2022, Rome, Italy.

• Download Published Version (PDF / 351kB)

Ao, Shuang (2022). AI in safety-critical tasks: To trust or not to trust, that is a question. Postgraduate Research Poster Competition, The Open University.

• Download Research Poster (PDF / 1MB)