利用人类反馈训练语言模型遵循指令
Training language models to follow instructions with human feedback
利用人类示范与偏好反馈改进语言模型遵循指令的能力。
THE RESEARCH ATLAS
MolmoAct：能够进行空间推理的动作推理模型
将深度感知、空间规划与底层动作预测组织成明确的动作推理流程。
MolmoAct: Action Reasoning Models that can Reason in Space
为什么值得读
研究中间空间规划如何成为观察和引导机器人行为的接口。
引用
@misc{lee2025molmoact,
title = {MolmoAct: Action Reasoning Models that can Reason in Space},
author = {Jason Lee and Jiafei Duan and Haoquan Fang and Yuquan Deng and Shuo Liu and Boyang Li and Bohan Fang and Jieyu Zhang and Yi Ru Wang and Sangho Lee and Winson Han and Wilbert Pumacay and Angelica Wu and Rose Hendrix and Karen Farley and Eli VanderBilt and Ali Farhadi and Dieter Fox and Ranjay Krishna},
year = {2025},
eprint = {2508.07917},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2508.07917}
}论文与代码版权归原作者；引用及许可请以原始来源为准。
相关研究
宪法式 AI：从 AI 反馈中学习无害性
Constitutional AI: Harmlessness from AI Feedback
以明确原则引导模型自我批评、修订及生成偏好反馈，用于对齐训练。
直接偏好优化：你的语言模型其实也是奖励模型
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
通过偏好优化目标直接训练语言模型，省去单独训练奖励模型的阶段。