Most VLAs Lose Their Vision-Language Skills After Pretraining
A study by Ville Kuosmanen et al. finds that most vision-language-action models lose much of their underlying VLM's vision-language skills after robot pretraining, as shown by evaluating isolated VLM weights on eight vision-language benchmarks.
2026-11-16 ~ 2026-11-16 · 2 related posts
- Most VLAs lose their base VLM's vision-language skills during robot pre-training, eval shows — DJiafei · 2026-11-16
- Most VLAs lose their VLM's vision-language skills during pretraining — DJiafei · 2026-11-16