Embodied AI TopConf · ICLR2026

Actions as Language: Fine-Tuning VLMs into VLAs Without Catastrophic Forgetting

ICLR2026 / Vision-Language-Action Models

VLA感知
新标签打开 AlphaXiv
Actions as Language: Fine-Tuning VLMs into VLAs Without Catastrophic Forgetting figure
AlphaXiv 中文论文页面（可滚动查看）