Search papers, labs, and topics across Lattice.
University of Maryland
3
0
7
Users can significantly enhance their understanding of machine translation limitations by leveraging surface-level cues and practice, reshaping how we approach user training in AI systems.
MINARD generates humanlike, paper-faithful narrations for scientific figures, bridging a critical gap in understanding complex visual data.
Humans miss 3.9% of opportunities to leverage correct AI suggestions while also over-relying on misleading outputs, highlighting critical gaps in trust and decision-making in human-AI collaboration.
