Search papers, labs, and topics across Lattice.
Technical University of Munich, Munich, Germany
4
1
7
45
Hidden safety risks in AI systems may be more dangerous than the visible failures we obsess over, revealing a critical need for a new framework to diagnose them.
AI coding agents can achieve or surpass human methodological diversity while exposing vulnerabilities in interpretive bias that human analysts do not share.
Unlock privacy-preserving eye-tracking analysis with garbled circuits, enabling secure scanpath comparison without revealing sensitive gaze data.
Glint matching in eye tracking gets a major reproducibility boost with a new constellation-based method that treats corneal reflections like stars in the night sky.
