STEERACT: Unlocking Action Models Through Few-Shot Temporal Steering
CoRL Learn@Deploy 2026 Spotlight
Under review
I conduct postdoctoral research at Harvard University and the MIT Media Lab under the joint supervision of Paul Liang, Yilun Du, and Mengyu Wang. I am currently visiting the Stanford Vision and Learning Lab (SVL) at Stanford University, where I work with Jiajun Wu.
Previously, I earned my Ph.D. in Computer Science at the University of Oxford under the supervision of Prof. Niki Trigoni and Prof. Andrew Markham, and graduated with First Class Honours (Top 10%) from the Department of Computing at Imperial College London, where I worked with Prof. Yike Guo.
If you are interested in my research, please feel free to reach out via email — I am always happy to chat and collaborate.
I build models that understand, predict, and act in the dynamic 3D world.
Recovering geometry, motion, and spatial relationships from sensory observations to understand changing physical environments.
Developing world models that retain scene knowledge and use geometric constraints to generate coherent, physically plausible futures.
Enabling robots to learn from multimodal feedback and execution experience, correct errors, and adapt their behavior through interaction.
See my Google Scholar for the full list.
CoRL Learn@Deploy 2026 Spotlight
Under review
ECCV OpenSUN3D 2026 Best Paper Finalist
ECCV 2026 · CVPR WMAS 2026 Best Paper Finalist
CVPR 2026 · CVPR GCV 2026 Best Paper Finalist
ACM MobiSys 2025 · Best Paper Nominee
IROS 2024 · Finalist, Best Application Paper Award
Wonderful students I work with / have worked with.