I am a Senior Research Scientist at Google DeepMind. My goal is to build intelligent agents and robots that can act in virtual and physical environments.

Previously, I was a postdoctoral researcher and a PhD student with Ingmar Posner at the Oxford Robotics Institute. My PhD was funded by an EPSRC DTA studentship and a Google studentship. Before that, I completed my undergraduate studies in engineering with a specialisation in electronic and information engineering at the University of Oxford.

Publications

I have co-authored papers on: sparse convolutions for object detection and segmentation in 3D point clouds [1, 2, 3], learning functions on sets [4, 5], object-centric representation learning and image generation [6, 7, 8, 9, 10], quadruped locomotion [11, 12, 13], path planning for robot arms [14], agents that follow language instructions in video games [15], and active information gathering with foundation models [16].

The full list of publications can be found here. Talks can be found here.

Service

I have served as a conference reviewer for CVPR, NeurIPS, ICRA, IROS, and RSS and as a journal reviewer for IJCV and RA-L.