Abstract

Robots are rapidly becoming part of our physical and social environments, driven by remarkable advances in vision-language and vision-language-action foundation models. Yet impressive demonstrations of learned skills do not necessarily translate into intelligent and trustworthy autonomy. Today, much of industry and academia focuses on scaling neural foundation models with larger models, more data, and increased computation-approaches that deliver increasingly powerful perception and action capabilities but often remain difficult to interpret, struggle with complex compositional reasoning, and make safety assurance challenging. In this talk, I will present our research at Monash on neuro-symbolic AI as a complementary direction for building robotic systems that are more intelligent, and interpretable. Rather than replacing neural foundation models, we combine their strengths in perception, grounding, and language understanding with explicit world representations, symbolic reasoning, and planning.

Short Bio

Dr. Hamid Rezatofighi is an Associate Professor in the Faculty of Information Technology at Monash University, Australia. His research spans computer vision, machine learning, robotics, and neuro-symbolic AI, with a particular focus on visual perception and reasoning for intelligent autonomous systems operating in complex, dynamic environments. His current research explores how neural foundation models can be integrated with symbolic reasoning and agentic planning to develop more capable, interpretable, and trustworthy embodied AI systems. Prior to joining Monash, he was awarded the prestigious Australian Government Endeavour Research Fellowship, supporting his research at Stanford University’s Vision and Learning Lab. He subsequently served as a Senior Research Fellow at the Australian Institute for Machine Learning (AIML), University of Adelaide, and received his PhD from the Australian National University in 2015. Dr. Rezatofighi has authored over 100 publications in top-tier venues across computer vision, machine learning, artificial intelligence, and robotics, attracting over 21,000 citations. His work on Generalized Intersection over Union (GIoU), introduced in 2019, has received over 9,500 citations and has been widely adopted in modern object detection systems. [https://vl4ai.erc.monash.edu/]