Li-Fei Liu

This work develops a Carbon-Aware AI Procurement Framework (CAAPF), a Green IS design artifact that operationalizes sustainable AI governance for enterprise procurement, and suggests that environmental responsibility and decision quality can be mutually reinforcing.

Co-signed DAGs can prevent unauthorized bindings after key compromises, offering a breakthrough in secure multi-agent delegation.

Retrieval harm can significantly impact performance, and simple baselines often outperform complex models in Active RAG systems.

Achieving high accuracy while reducing model size, MIS-HCC compresses medical image segmentation networks without sacrificing performance.

Operational reframing emerges as a critical risk signal, revealing that compliance can vary significantly across models and scenarios, challenging the notion of stable safety metrics in multi-agent LLMs.