Weyl Lu — accepted AI-conference papers

2025

Neural Motion Simulator Pushing the Limit of World Models in Reinforcement Learning

Chenjie Hao, Weyl Lu, Yifan Xu, Yubei Chen

CVPR 2025poster

An embodied system must not only model the patterns of the external world but also understand its own motion dynamics. A motion dynamic model is essential for efficient skill acquisition and effective planning. In this work, we introduce the neural motion simulator (MoSim), a world model that predic…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2024

RA-PbRL: Provably Efficient Risk-Aware Preference-Based Reinforcement Learning

Yujie Zhao, Jose Efraim Aguilar Escamilla, Weyl Lu, Huazheng Wang

NeurIPS 2024poster

Reinforcement Learning from Human Feedback (RLHF) has recently surged in popularity, particularly for aligning large language models and other AI systems with human intentions. At its core, RLHF can be viewed as a specialized instance of Preference-based Reinforcement Learning (PbRL), where the pref…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗