SafeBranch: Branch-Pair Safety Alignment for Embodied Agents
Ranking
Overall
79
Content
95
Popularity
42
Observed public metrics from 1 member.
Merged summary
TL;DR - SafeBranch trains embodied vision-language agents to avoid unsafe actions using tightly controlled branch pairs that differ only at a safety-critical step. It improves safety without requiring a critic during deployment or sacrificing task success.
- Builds training pairs by rolling unsafe trajectories back to the violation-causing step and generating a safe alternative action.
- Isolates the safety signal more precisely than imitating safe trajectories or contrasting unrelated safe and unsafe rollouts.
- Evaluations cover IS-Bench, SafetyALFRED, and out-of-distribution settings with unseen tasks and objects.
- Achieves roughly 10Ă— more safe successes than the untrained baseline on the unseen-object variant.
Sources (1)
SafeBranch: Branch-Pair Safety Alignment for Embodied Agents
Public signals
Semantic Scholar citations 0 · Semantic Scholar influential citations 0
TL;DR - SafeBranch trains embodied vision-language agents to avoid unsafe actions using tightly controlled branch pairs that differ only at a safety-critical step. It improves safety without requiring a critic during deployment or sacrificing task success.
- Builds training pairs by rolling unsafe trajectories back to the violation-causing step and generating a safe alternative action.
- Isolates the safety signal more precisely than imitating safe trajectories or contrasting unrelated safe and unsafe rollouts.
- Evaluations cover IS-Bench, SafetyALFRED, and out-of-distribution settings with unseen tasks and objects.
- Achieves roughly 10Ă— more safe successes than the untrained baseline on the unseen-object variant.