3 papers
cs.RO2026
SimPT: An Automated Simulation Framework for Intervention-Based VLA Post-Training
Caicheng Wang, Zipeng Ye, Zhexuan Zhou +3
Human-in-the-loop (HIL) post-training improves vision-language-action (VLA) policies through expert corrections, but costly human supervision and repeated real-robot evaluation lim…
cs.LG2026
Design for Manufacturing: A Manufacturability Knowledge-Integrated Reinforcement Learning Framework for Free-Form Pipe Routing in Aeroengines
Caicheng Wang, Zili Wang, Shuyou Zhang +4
Design for manufacturing plays a critical role in advanced aeroengine development, where complex components necessitate careful consideration of manufacturability. However, current…
cs.LG2025
A self-learning framework for adaptive free-form pipe routing in aeroengines
Caicheng Wang, Zili Wang, Shuyou Zhang +3
Pipe routing is a highly complex, time-consuming, and no-deterministic polynomial-time hard (NP-hard) problem in aeroengine design. Despite extensive research efforts in optimizing…