PROBEACT is a plug-and-play intervention framework that combines hidden-state probing, kinematic failure detection, and CBF-based correction to boost success rates of pre-trained VLA models on the LIBERO-plus benchmark from 69.6% to 74.1%.
Cyclevla: Proactive self-correcting vision-language-action models via subtask backtracking and minimum bayes risk decoding,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Progress-enhanced VLA model raises simulated bimanual furniture assembly success from 48% to 80% across three furniture types and shows 16% drop on real Kinova robot.
VLA-FAIL introduces last-layer Mahalanobis distance and action chunk consistency detectors that together enable early, reliable failure detection in finetuned VLAs without failure data or expensive sampling.
citing papers explorer
-
ProbeAct: Probe-Guided Training-Free Failure Recovery in Vision-Language-Action Models
PROBEACT is a plug-and-play intervention framework that combines hidden-state probing, kinematic failure detection, and CBF-based correction to boost success rates of pre-trained VLA models on the LIBERO-plus benchmark from 69.6% to 74.1%.
-
FurnitureVLA: Learning Long-Horizon Bimanual Furniture Assembly with Vision-Language-Action Model
Progress-enhanced VLA model raises simulated bimanual furniture assembly success from 48% to 80% across three furniture types and shows 16% drop on real Kinova robot.
-
VLA-FAIL: Efficient Task Failure Detection for Finetuned Vision-Language-Action Models
VLA-FAIL introduces last-layer Mahalanobis distance and action chunk consistency detectors that together enable early, reliable failure detection in finetuned VLAs without failure data or expensive sampling.