← Search

Kevin Wells

2 accepted papers

2026

Coverage-Constrained Human-AI Cooperation with Multiple Experts

AAAI 2026technical

Human-AI cooperative classification (HAI-CC) aims to develop hybrid intelligent systems that enhance decision-making in various high-stakes real-world scenarios by leveraging both human expertise and AI capabilities. Current HAI-CC methods primarily focus on learning-to-defer (L2D), where decisions

Cited by 0SourcePDFScholar
2024

Learning to Complement and to Defer to Multiple Users

ECCV 2024poster

"With the development of Human-AI Collaboration in Classification (HAI-CC), integrating users and AI predictions becomes challenging due to the complex decision-making process. This process has three options: 1) AI autonomously classifies, 2) learning to complement, where AI collaborates with users,…