By amplifying a few semantic 'value vectors' in a vision-language-action transformer, the authors steered a robot's speed and height at inference time, without retraining.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Mechanistic interpretability for steering vision-language-action models
By amplifying a few semantic 'value vectors' in a vision-language-action transformer, the authors steered a robot's speed and height at inference time, without retraining.