Runjia Li

DPhil Student · University of Oxford

Runjia Li

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.

Physical Intelligence2026

Research Intern

Hosted by Xudong Wang

Meta2026

Research Scientist Intern

Hosted by Shikun Liu

Snap Inc.2025

Research Scientist Intern

Hosted by Willi Menapace

OverSeer: Multi-Agent World Models Beyond What Agents See

Runjia Li, Kam Woh Ng, Minghao Chen, Junlin Han, Jianyuan Wang, Zhaochong An, Juan-Manuel Perez-Rua, Andrea Vedaldi†, Shikun Liu†

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.