Publications (*: indicates equal contribution)
|
Learning to Drive with Two Minds: A Competitive Dual-Policy Approach in Latent World Models
Xiaoji Zheng*,
Ziyuan Yang*,
Yuhang Peng,
Yanhao Chen,
Yuanrong Tang,
Gengyuan Liu,
Bokui Chen,
Jiangtao Gong,
ArXiv, 2025
Paper
/
Code
/
Project Page
Propose a competitive dual-policy framework that enables IL and RL agents to interact during training. This method introduces a competition-based mechanism that facilitates knowledge exchange while preventing gradient conflicts.
|
Embodied Cognition Augmented End2End Autonomous Driving
Ling Niu,
Xiaoji Zheng,
Han Wang,
Ziyuan Yang,
Chen Zheng,
Bokui Chen,
Jiangtao Gong,
NeurIPS, 2025
Paper
Propose a novel paradigm to advocate cross-modal self-supervised learning between visual feature extraction networks and a general EEG large model, in order to learn latent human driving cognition for enhancing end-to-end planning.
|
|