I am a first year CS PhD student at University College London (UCL) supervised by Edward Grefenstette and Tim Rocktäschel, as well as a PhD Researcher at Meta AI Labs. I do research in deep reinforcement learning, currently focusing on world models, generalization and data efficiency.
Before starting my PhD, I studied CS and Math at Rice University and also spent some time working on applied ML in the bay area.
Y. Xu, J. Parker-Holder, A. Pacchiano, P. J. Ball, O. Rybkin, S. J. Roberts, T. Rocktäschel, E. Grefenstette (2022). Learning General World Models in a Handful of Reward-Free Deployments. In NeurIPS.
B. Chen, Y. Xu, A. Shrivastava (2019). LGD: Fast and Accurate Stochastic Gradient Estimation. In NeurIPS.
A. Beller, Y. Xu, S. Linderman, T. Gerstenberg (2022). Looking into the past: Eye-tracking mental simulation in physical inference. In Cognitive Science.