Workshop Overview

This workshop explores the use of synthetic data as a catalyst for robotic learning, enabling progress across reinforcement learning, system identification, evaluation, and reasoning. By bringing together methodologies from control, machine learning, and computer graphics, the workshop highlights how synthetic data can accelerate development, improve robustness, and expand the versatility of embodied AI systems. Discussions will address both the opportunities and challenges of leveraging synthetic data, including domain transfer, realism tradeoffs, and alignment with real-world deployment. The scope spans a broad spectrum of applications, from manipulation to legged robots, with invited speakers offering diverse perspectives on how synthetic data can shape the future of reliable, adaptable, and trustworthy robotic intelligence. 

Tentative Program

Morning Session

09:00 – 09:10 Opening Remarks

09:10 – 09:30 Justin Carpentier (INRIA Paris)

09:30 – 09:50 Ming Lin (University of Maryland & Amazon)

09:50 – 10:10 Jiajun Wu (Stanford University)

10:10 – 10:40 Coffee Break and Poster Session

10:40 – 11:00 Sergey Zakharov (Toyota Research Institute)

11:00 – 12:00 Panel Discussion

12:00 – 12:30 Paper Presentations

12:30 – 13:40 Lunch Break

Afternoon Session

13:40 – 14:00 Angela Schoellig (Technical University of Munich)

14:00 – 14:20 Jason Peng (Simon Fraser University & NVIDIA)

14:20 – 14:50 Coffee Break and Poster Session

14:50 – 15:10 Mansur Arief (Stanford University)

15:10 – 15:30 Hugo Talbot (INRIA Nancy)

15:30 – 15:50 Maurizio Chiaramonte (Meta)

15:50 – 16:50 Panel Discussion

16:50 – 17:00 Closing Remarks