I am a first-year PhD student at the School of Artificial Intelligence, Nanjing University, advised by Prof. Yang Yu. Before that, I received my bachelor’s degree from the same school with the GPA of 4.84/5.00 (rank 1/96).
My research interests lie in reinforcement learning, world models, and embodied intelligence.
* Equal contribution.
arXiv preprint, 2026
U-GROW uses policy uncertainty to focus world-model rollouts on states with greater potential for improvement, enabling more efficient and effective reinforcement learning for VLA policies.
RSS Workshop on Diffusion for Robot Learning, 2026
UA-OPD uses teacher uncertainty to guide on-policy distillation, reducing reliance on unreliable teacher predictions when training embodied policies.
ICML, 2026
VLA-MBPO trains robot policies inside learned world models, combining consistent multi-view predictions with short, branched rollouts to make reinforcement learning more data-efficient.
arXiv preprint, 2026
An anticipation model adapts future subgoals as a task unfolds, guiding a goal-conditioned VLA policy through long-horizon robot tasks.
arXiv preprint, 2026
A perspective on evaluating world models through their usefulness for intervention, policy evaluation, planning, and policy improvement.