顶级会议ICML 2026收录，揭秘构建强视觉-语言-动作（VLA）模型的实用配方与技巧。
arXiv:2602.18532v2 Announce Type: replace Abstract: Following the rise of large foundation models, Vision-Language-Action models (VLAs) emerged, lever…
机器人基础模型新突破：通用姿态预训练让视觉-语言-动作策略泛化能力飙升，已被RSS 2026接收。
arXiv:2602.19710v2 Announce Type: replace-cross Abstract: Existing Vision-Language-Action (VLA) models often suffer from feature collapse and low trai…
揭示VLA训练中VLM多模态能力系统退化的“具身税”现象，提出双流新视角UAM
arXiv:2605.15735v1 Announce Type: cross Abstract: Vision--language--action (VLA) models are typically built by fine-tuning a pretrained vision--langua…
提出概率块掩码机制，直击VLA强化学习后训练计算瓶颈，显著提升效率。
arXiv:2605.16154v1 Announce Type: new Abstract: Reinforcement learning (RL) allows vision-language-action (VLA) policies to generalize beyond their tr…
从人类自我中心视频提取物理常识监督，助力机器人学习更广物理理解的新方法
arXiv:2605.15298v1 Announce Type: cross Abstract: Vision-language-action models have advanced rapidly, but robot trajectories alone provide limited co…