Program SubpagePlenary Session
EIRConference WebsiteEIR 2026
Program / Plenary Session

Plenary Sessions

Plenary Session 1

David Hsu

Date: Thursday, 6 August 2026
Time: 9:15 AM - 10:00 AM
Affiliation: National University of Singapore (NUS)
David Hsu

Title: To be announced

Abstract: To be announced.

Biography

David Hsu is a Provost's Chair Professor in the Department of Computer Science, National University of Singapore (NUS) and the Director of Smart Systems Institute. He received BSc in computer science & mathematics from The University of British Columbia and PhD in computer science from Stanford University. At NUS, he co-founded NUS Advanced Robotics Center in 2013. He founded the NUS AI Laboratory (NUSAIL) in 2019 and served as the founding director. He held visiting positions in MIT Aeronautics & Astronautics Department and CMU Robotics Institute. He is an IEEE Fellow.

His research interests span robotics, AI, and computational structural biology. In recent years, he has been working on robot planning and learning under uncertainty and human-robot collaboration. His work won several international awards, including, most recently, Test of Time Award at Robotics: Science & Systems (RSS) in 2021 and JCAI-JAIR Best Paper Prize in 2022. More information on his research is available on the Adaptive Computing Laboratory (AdaComp) web site.

He has chaired or co-chaired several major international robotics conferences, including WAFR 2004 and 2010, RSS 2015, ICRA 2016, and CoRL 2021. He also served on the editorial boards of IEEE Transactions on Robotics, International Journal of Robotics Research, and Journal of Artificial Intelligence Research.

Plenary Session 2

Zhibin Li

Date: Friday, 7 August 2026
Time: 9:00 AM - 9:45 AM
Affiliation: Department of Computer Science, University College London (UCL)
Zhibin Li

Title: Physical AI: Learning Dexterous Robotic Skills

Keywords: Robotic manipulation; embodied foundation models; reinforcement learning

Abstract: Recent advances in dexterous manipulation, vision-language-action models, and large-scale human data are accelerating the development of robots capable of precise and adaptable real-world interaction. This talk reviews the progression from sensorimotor skill learning and sim-to-real reinforcement learning to data-driven manipulation using tactile demonstrations, teleoperation, multimodal datasets, and human video. It concludes by examining generalist embodied foundation models that integrate large-scale learning, shared autonomy, and human demonstrations to enable reliable dexterous manipulation across complex tasks.

Biography

Prof Zhibin Li is an Associate Professor in Robotics & AI Professor advancing the frontier of embodied intelligence, with flagship research published in Science Robotics and Nature Machine Intelligence. His work spans dexterous manipulation, vision language action (VLA) models, and real world robot learning, driving robots toward superhuman precision, agility, and autonomy.

He has authored 130+ publications, including major contributions such as RoboBallet (Science Robotics, 2025), ROMAN (Nature Machine Intelligence, 2023), Hierarchical Generative Modelling (Nature Machine Intelligence, 2023), and Multi Expert Learning of Adaptive Locomotion (Science Robotics, 2020). His recent work leads the emerging field of VLA driven dexterous manipulation, combining human video learning, shared autonomy, and zero shot sim to real transfer to enable robots to perform fine grained, real world manipulation tasks with unprecedented reliability.

He has played key roles in major EU/UK programmes including HARMONY, ORCA Hub, and Fair Space Hub. His research has been featured widely in BBC News, Wired, Gizmodo, TechXplore, New Scientist, and DeepTech Reports.