Embodied AI TopConf · ICLR2026

Align-Then-stEer: Adapting the Vision-Language Action Models through Unified Latent Guidance

ICLR2026 / Vision-Language-Action Models

VLA感知
新标签打开 AlphaXiv
Align-Then-stEer: Adapting the Vision-Language Action Models through Unified Latent Guidance figure
AlphaXiv 中文论文页面（可滚动查看）