2 papers
cs.LG2026
RPO: Decoupling Rollout and Inference Policies for LLM Reasoning
Jingchu Wang, Bingbing Xu, Yige Yuan +4
Existing reinforcement learning methods for LLM reasoning implicitly assume that the policy generating training trajectories should coincide with the one producing inference respon…
eess.SY2026
Scalable Optimization for Mobility-Aware Coordinated Electric Vehicle Charging in Distribution Power Networks
Yi Ju, Lunlong Li, Jingchun Wang +1
Rapid growth in electric-vehicle (EV) charging demand is placing increasing stress on power distribution networks (PDNs), whose hosting capacity is often limited and spatially unev…