2 papers
cs.RO2026
PIER-Flow: Physics-Informed Efficient Rectified Flow for Real-Time Mobile Robot Navigation
Shibo Li, Zhongcheng Wang, Jiahe Cao +2
Autonomous navigation in dense and highly dynamic environments requires both physically feasible control and low-latency replanning. Optimization-based methods such as Model Predic…
cs.LG2026
Multi-Fidelity Flow Matching: Cascaded Refinement of PDE Solutions
Sipeng Chen, Junliang Liu, Hewei Tang +1
The source distribution in conditional flow matching is a design parameter that can be calibrated to data, not a default isotropic prior. We exploit this in Multi-Fidelity Flow Mat…