My Name is Jiading Fang (方家鼎). I am currently a PhD student from Toyota Technological Institute at Chicago (TTIC) at Robot Intelligence through Perception Lab (RIPL). My advisors are Matthew Walter and Greg Shakhnarovich.

My long-term research goal is to enable "Embodied Reasoning in 3D Scenes". I believe for general intelligence to make impacts in real world, it has to be grounded, meaning that it needs to understand all sorts of signals from the physical environment and be aware of the robotic affordance to make feasible decisions. My work has made first steps towards this goal. For visual understanding, I have built a series of works that constitutes "Scalable scene representation with self-supervision"; and for language understanding, I have developed "Embodied Reasoning with Large Language Models" including applying large language models (LLMs) on long-term planning, navigation and 3D referring reasoning tasks which reveals "Hidden challenges towards builing 3D robotic foundation models". My next step is to build multi-modality robotic foundation models with physical common sense.

I am currently looking for research scientist/engineer jobs in industry and postdoc positions at academia. If you are interested, please do not hesitate to reach out.