OGAM: Connecting Systematic Testing to Runtime Assurance through Object-Grounded Attention Monitoring for VLA Policies
cs.LG, cs.AI, cs.RO
Submitted: 2026-10-05
Updated: 2026-10-05
Sources
- LIBERO-Para: A Diagnostic Benchmark and Metrics for Paraphrase Robustness in VLA Models
- HazardArena: Evaluating Semantic Safety in Vision-Language-Action Models
- LADEV: A Language-Driven Testing and Evaluation Platform for Vision-Language-Action Models in Robotic Manipulation
- ActProbe: Action-Space Probe for Early Failure Detection of Generative Robot Policies
- Your Vision-Language-Action Model Already Has Attention Heads For Path Deviation Detection
- Your Model Already Knows: Attention-Guided Safety Filter for Vision-Language-Action Models
- DTP: A Simple yet Effective Distracting Token Pruning Framework for Vision-Language Action Models
- VLA-Trace: Diagnosing Vision-Language-Action Models through Representation and Behavior Tracing
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks