Li

Two AI systems with nearly identical performance can have drastically different human oversight needs, revealing hidden costs in deployment readiness.

Sigmoid attention, while less effective in dense modeling, dramatically improves KV-cache eviction performance, challenging conventional wisdom about attention mechanisms.

Tighter bounds on instance encoding invertibility reveal that deterministic encoders can be just as secure as their randomized counterparts, transforming our understanding of data privacy techniques.

A hands-on framework that transforms AI education in power systems, making complex concepts accessible to newcomers and practitioners alike.