NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewards

作者：Chia-Yu Hung, Navonil Majumder, Haoyuan Deng, Liu Renhang, Yankang Ang, Amir Zadeh, Chuan Li, Dorien Herremans, Ziwei Wang, Soujanya Poria · 单位：Nanyang Technological University, Lambda Labs, Singapore University of Technology and Design · 会议/期刊：arXiv · 日期：2025-11-18 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with RL