The remarkable capabilities of machine learning (ML) models, especially foundation models like GPT, have transformed numerous domains. However, these systems often falter in real-world settings, where they encounter unknown or out-of-distribution (OOD) inputs, and generate overconfident predictions or unreliable outputs. Ensuring their reliability is not only a technical challenge but also a fundamental requirement for their safe deployment.
In this talk, I will discuss my research on teaching ML models what they don’t know by developing foundational frameworks for reliable decision-making in the open world. This involves three core aspects: (1) designing novel algorithms for unknown-aware learning through adaptive outlier synthesis, enabling models to handle unfamiliar inputs without explicit knowledge of unknowns; (2) leveraging unlabeled data in the wild to detect and generalize across diverse real-world reliability challenges; and (3) addressing reliability blind spots in foundation models, such as hallucinations, malicious prompts, and noisy alignment data, through innovative mitigation strategies.
Through fundamental algorithmic development, theoretical insights, and practical applications, my research contributes to the responsible deployment of AI technologies. The talk will conclude with a forward-looking perspective on interdisciplinary collaborations and the roadmap for achieving robust, reliable AI systems that adapt to an ever-changing world.
Speaker Bio
Sean (Xuefeng) Du is an incoming Assistant Professor at College of Computing and Data Science (CCDS), Nanyang Technological University, Singapore. He obtained his Ph.D. in Computer Sciences at UW-Madison advised by Prof. Sharon Li. His research interest is in reliable machine learning and the applications to foundation models and AI safety. His first-author papers have been recognized with multiple oral and spotlight presentations at NeurIPS and CVPR. He is a recipient of the Jane Street Graduate Research Fellowship, and Rising Stars in Data Science award.
More Details
- When: June 26 2025, at 1-2pm (Brisbane time)
- Speaker: Sean (Xuefeng) Du (incoming Assistant Professor in NTU)
- Host: Yujun Cai
- Zoom: https://uqz.zoom.us/j/89394692123
Reasoning with Language Models