Search papers, labs, and topics across Lattice.
3
6
5
6
Grounding linguistic explanations in mathematically interpretable units can boost the trustworthiness of AI in medical applications by enhancing both visual localization and reasoning quality.
VLMs are prone to critical failures that vary significantly across cultures, exposing the inadequacy of Western-centric safety benchmarks.
A global consensus on AI safety risks and capabilities has emerged from a panel of 100+ independent experts, representing a landmark effort in international collaboration.
