Tri-Info uses three information theory signals on action diversity, temporal consistency, and state coupling to predict VLA model failures with cross-domain generalization to 83% real-world accuracy.
arXiv preprint arXiv:2102.06746 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.RO 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
Hide-and-Seek uses contrastive objectives on trajectories to localize failure signals in VLA models from trajectory-level supervision alone.
Temporal difference calibration aligns uncertainty estimates in vision-language-action models with their value functions for better sequential performance.
citing papers explorer
-
Tri-Info: Generalizable, Interpretable Failure Prediction for VLA Models via Information Theory
Tri-Info uses three information theory signals on action diversity, temporal consistency, and state coupling to predict VLA model failures with cross-domain generalization to 83% real-world accuracy.
-
Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoring
Hide-and-Seek uses contrastive objectives on trajectories to localize failure signals in VLA models from trajectory-level supervision alone.
-
Temporal Difference Calibration in Sequential Tasks: Application to Vision-Language-Action Models
Temporal difference calibration aligns uncertainty estimates in vision-language-action models with their value functions for better sequential performance.