I am a 4th year CS PhD student at University College London (UCL) supervised by Edward Grefenstette and Tim Rocktäschel, as well as a PhD Researcher at FAIR London. My research focuses on deep reinforcement learning, world models, and LLM reasoning.
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.
**[Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning](https://arxiv.org/abs/2502.03275)** \
D. Su, H. Zhu, **Y. Xu**, J. Jiao, Y. Tian, Q. Zheng \
Under Review
**[Meta Motivo: Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Models](https://metamotivo.metademolab.com/)** \
A. Tirinzoni, A. Touati, J. Farebrother, M. Guzek, A. Kanervisto, **Y. Xu**, A. Lazaric, M. Pirotta \
ICLR 2025
**[H-GAP: Humanoid Control with a Generalist Planner]({% link hgap.markdown %})** \
Z. Jiang\*, **Y. Xu**\*, N. Wagener, Y. Luo, M. Janner, E. Grefenstette, T. Rocktäschel, Y. Tian \
ICLR 2024 Spotlight
**[IQL-TD-MPC: Implicit Q-Learning for Hierarchical Model Predictive Control](https://arxiv.org/abs/2306.00867)** \
R. Chitnis\*, **Y. Xu**\*, B. Hashemi, L. Lehnert, U. Dogan, Z. Zhu, O. Delalleau \
ICRA 2024
**[Learning General World Models in a Handful of Reward-Free Deployments]({% link cascade.markdown %})** \
**Y. Xu**\*, J. Parker-Holder\*, A. Pacchiano\*, P. J. Ball\*, O. Rybkin, S. J. Roberts, T. Rocktäschel, E. Grefenstette \
NeurIPS 2022
**[LGD: Fast and Accurate Stochastic Gradient Estimation](https://papers.nips.cc/paper/2019/hash/a1e865a9b1065392ed6035d8ccd072d9-Abstract.html)** \
B. Chen, **Y. Xu**, A. Shrivastava \
NeurIPS 2019
**[Looking into the past: Eye-tracking mental simulation in physical inference](https://escholarship.org/uc/item/7gk617ss)** \
A. Beller, **Y. Xu**, S. Linderman, T. Gerstenberg \
Cognitive Science 2022
