The One About Assurance and Federated Learning
*As the programme is still being finalized, do note that details are subject to change.
More About the Sharings
Xin Xin (Founder & CEO, Ailantis) will share on "Engineering AI Assurance: How to Test and Stress-Test AI Systems for Production”
He will introduce practical approaches for evaluating and stress-testing AI systems in real-world deployments. Xin Xin will cover key techniques such as red teaming, adversarial testing, hallucination detection, and risk quantification, with a focus on how these methods can be systematically integrated into engineering workflows for reliable and trustworthy AI systems.
Marie Siew (Lecturer and Researcher,Singapore University of Technology and Design (SUTD) will share on "Fair Concurrent Training of Multiple Models in Privacy-Preserving Settings"
Federated learning (FL) enables collaborative AI model training across different clients (eg users, devices, organizations), in a privacy preserving manner, without the need for centralizing data. While most FL research focuses on training a single task, real-world deployments increasingly require multiple FL tasks to run concurrently over a shared client pool - a setting we call Multiple-Model Federated Learning (MMFL). In this talk, Marie'll provide an overview about federated learning algorithms, approaches to ensuring fairness over clients with heterogeneous data distributions, and introduce our solution which achieves fairness over tasks with heterogeneous difficulty levels. This project bridges distributed optimization, mechanism design, and practical FL systems
More About the Speakers
Xin Xin is founder and CEO at Ailantis, specialising in AI model and application testing. He holds a Master’s degree from the National University of Singapore (NUS) and a Ph.D. from the School of Computing Science, University of Glasgow (UofG). Previously, he was a Research Engineer at the Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR) Singapore, where he focused on distributed computing and social cognition computing. He later joined TÜV SÜD Digital Service as a Principal Engineer, leading the development of a run-time verification engine that assesses Cyber-Physical Systems (CPSs) run-time trustworthiness
Marie Siew is a Lecturer and Researcher at the Singapore University of Technology and Design (SUTD), working at the intersection of wireless communications and networking, AI, and mathematics. Her research centers on distributed edge intelligence (edge computing, federated learning, wireless network optimization and LLM agents). Previously, she was a postdoctoral researcher at Carnegie Mellon University. Her research has received the AAAI ML4Wireless 2026 Best Student Paper Award, IEEE ICDCS 2024 Best Poster Award, and the IEEE/ACM IPSN 2023 Best Poster Award. She received her PhD from SUTD, and her BSc in Mathematical Sciences from Nanyang Technological University.
More About the Series
AI Wednesdays is Lorong AI’s weekly gathering, bringing together practitioners, researchers and innovators for technical discussions on research insights, product development and engineering practices.
Get involved: Learn more about Lorong AI | Speaker Sign-up | WhatsApp Community | LinkedIn | X