AI
Verifiable abstention makes AI leak diagnosis accountable in water distribution networks
Researchers have developed a method to make AI-powered leak diagnosis in water distribution networks...
AI
ORBITER: Conflict-Aware Decision-Making for Agentic Last-Mile Delivery
Researchers have developed a system called ORBITER for making decisions in last-mile delivery scenar...
AI
SkillGate: Training In-Policy Skill Selection in Long-Horizon Agents
Researchers have proposed a new method called SkillGate to improve the performance of long-horizon a...
AI
DentAgent: Evidence-Centric Multi-Agent Coordination for Multimodal Dental Reasoning
Researchers have developed DentAgent, a multi-agent framework for dental reasoning that integrates e...
AI
Training-Free Inference-Time Self-Reflection and Cost-Bounded Early Stopping for Large Language Models
Researchers have developed a protocol called EvoResearcher that allows large lan...
AI
Syntactic Simplification of OWL Class Expressions
Researchers have developed a new algorithm called Class Expression Simplifier (C...
AI
\textsc{TestifAI}: Tomography-Based Testing for Deep Learning Systems
Researchers have developed a testing framework called TestifAI to evaluate the r...
AI
Breaking the weakest link to evade vision language models
Researchers have found that vision language models (VLMs) can be easily manipula...