NeurIPS 2025 Explorer
Concepts
Authors
Glossary
johnsanterre.github.io
failure detection
4 papers
Monitoring Risks in Test-Time Adaptation
PAC Bench: Do Foundation Models Understand Prerequisites for Executing Manipulation Policies?
SAFE: Multitask Failure Detection for Vision-Language-Action Models
STRATUS: A Multi-agent System for Autonomous Reliability Engineering of Modern Clouds