Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Parametric Memory Decoding for Zero-Shot Routing in LoRA-Based External Parametric Memory
Fengxian Ji, Zhuohan Xie, Jingpu Yang +3
With the rise of parametric memory, LoRA-based External Parametric Memory (EPM) has emerged as a modular solution, but existing routing methods often introduce additional training,…
cs.LG2023
Efficient Reinforcement Learning via Decoupling Exploration and Utilization
Jingpu Yang, Helin Wang, Qirui Zhao +3
Reinforcement Learning (RL), recognized as an efficient learning approach, has achieved remarkable success across multiple fields and applications, including gaming, robotics, and…