Jingxian Lu

2 accepted papers

2026

When would Vision-Proprioception Policies Fail in Robotic Manipulation?

Jingxian Lu, Wenke Xia, Yuxuan Wu, Zhiwu Lu, Di Hu

ICLR 2026poster

Proprioceptive information is critical for precise servo control by providing real-time robotic states. Its collaboration with vision is highly expected to enhance performances of the manipulation policy in complex tasks. However, recent studies have reported inconsistent observations on the general…

Cited by 0 Source ↗code ↗Scholar ↗

2024

KOI: Accelerating Online Imitation Learning via Hybrid Key-state Guidance

Jingxian Lu, Wenke Xia, Dong Wang, Zhigang Wang, Bin Zhao, Di Hu +1

CoRL 2024poster

Online Imitation Learning methods struggle with the gap between extensive online exploration space and limited expert trajectories, which hinder efficient exploration due to inaccurate task-aware reward estimation. Inspired by the findings from cognitive neuroscience that task decomposition coul…

Cited by 0 Source ↗Scholar ↗