Ravi Mangal
2 papers · Latest:
Machine Learning
Concept-Based Abductive and Contrastive Explanations for Behaviors of Vision Models
Introduces concept-based abductive and contrastive explanations to identify minimal sets of high-level concepts causally relevant for vision model behaviors.
2605.06640
Artificial IntelligenceInterval POMDP Shielding for Imperfect-Perception Agents
This paper introduces an Interval POMDP shielding method to enhance safety in autonomous systems with imperfect perception by blocking unsafe actions.
2604.20728
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.