Adding Asimov-style safety prompts to vision-language models lowers both harmful and helpful force generation for contact-rich robotic tasks.
Helix: A vision-language-action model for generalist humanoid control, 2025
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
-
On the Dual-Use Dilemma in Physical Reasoning and Force
Adding Asimov-style safety prompts to vision-language models lowers both harmful and helpful force generation for contact-rich robotic tasks.