PriorVLA preserves pretrained priors in VLA models through a frozen Prior Expert and trained Adaptation Expert, delivering better robot manipulation performance than full fine-tuning with only 25% of the parameter updates.
Robust fine-tuning of vision-language-action robot policies via parameter merging
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
PriorVLA: Prior-Preserving Adaptation for Vision-Language-Action Models
PriorVLA preserves pretrained priors in VLA models through a frozen Prior Expert and trained Adaptation Expert, delivering better robot manipulation performance than full fine-tuning with only 25% of the parameter updates.