LA4VLA: Learning to Act without Seeing via Language-Action Pretraining
- Published
- Source
- arXiv
- Paper number
- 508
- Field
- Robotics
- arXiv ID
- 2606.27295
Key points
- It provides a systematic analysis of vision-language asymmetry in VLA training at both the data level and the input level.
- It automatically builds 33K LA episodes from existing demonstrations without collecting extra data, in LA4-33K.
- LA-only pretraining consistently outperforms VLA-only pretraining at the same scale.
- Mixed LA-VLA pretraining reaches 87.53% on MetaWorld, 96.28% on LIBERO, and 83.3% on real robots.
- Under visual noise, the LA-pretrained policy achieves a success rate that is 25 percentage points higher than VLA-only.
- t-SNE analysis of the LA-pretrained policy shows clearly separated representations by command direction.
Paper links
External research summaries. These are not HDATF publications or measured product results.