Proceedings of the AAAI Conference on Artificial Intelligence 2026 / 强化学习方法

Balancing Signal and Variance: Adaptive Offline RL Post-Training for VLA Flow Models

作者：Hongyin Zhang, Shiyuan Zhang, Junxi Jin, Qixin Zeng, Yifan Qiao, Hongchao Lu, Donglin Wang · 会议/期刊：Proceedings of the AAAI Conference on Artificial Intelligence 2026 · 方向：强化学习方法 · 发布日期：2025-09-04

视觉语言动作强化学习方法高效训练强化学习
新标签打开 AlphaXiv
Balancing Signal and Variance: Adaptive Offline RL Post-Training for VLA Flow Models figure
AlphaXiv 中文概览（可滚动查看）