DPhil Student · University of Oxford
I work on consistent, physically-plausible, and interactive video generation.
I am a DPhil student at the University of Oxford, supervised by Andrea Vedaldi and Philip Torr, and generously funded by the Clarendon Scholarship. Before that I completed my undergraduate studies in Engineering Science, also at Oxford. I am fortunate to collaborate with Tomas Jakab and Yushi Lan.
NeurIPS 2026
Turns a pretrained video encoder into an action encoder with zero action labels, keeping what moved and discarding the scene, so the motion from one video can drive a world model in any other.
arXiv 2026
A multi-agent world model that generates each agent's view together with fixed auxiliary cameras, which anchor the shared world and keep agents consistent; a δ-VAE codes these static views cheaply.
CVPR 2026
A dataset, a real-time streaming model, and a benchmark for instruction-based editing of egocentric video.
ICCV 2025 Highlight
Interactive scene generation that stays consistent as the camera revisits places, by indexing past views with surfels and recalling only the ones a new view actually needs.
3DV 2025
Generating 3D fantastical animals with distinct, correctly placed parts, by transferring part-aware knowledge from a 2D diffusion model into the 3D distillation process.
CVPR 2024
Training-free open-vocabulary segmentation: querying CLIP recurrently prunes away text prompts that are absent from the image and sharpens the masks for the ones that remain.
ICCV 2023
A large-scale dataset of humorous image captions, together with an evaluation of how well models can generate and judge humour.
Weights