ROBOGATE applies adaptive boundary-focused sampling in simulation to discover robot policy failure boundaries, revealing a 97.65 percentage point performance gap for a VLA model between LIBERO and industrial scenarios.
SmolVLA: A small vision-language- action model.https://huggingface.co/ HuggingFaceTB/SmolVLA-Base, 2025
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
-
ROBOGATE: Adaptive Failure Discovery for Safe Robot Policy Deployment via Two-Stage Boundary-Focused Sampling
ROBOGATE applies adaptive boundary-focused sampling in simulation to discover robot policy failure boundaries, revealing a 97.65 percentage point performance gap for a VLA model between LIBERO and industrial scenarios.