Track the frontier, from condensed matter to cosmology.
Search papers, labs, and topics across Lattice.
Affiliation:
4
0
8
LLM agents trained on function calling forget nearly 25% of their capability when action names are perturbed, but a simple self-supervised regularization recovers over half of that loss.
Achieving over 96% navigation success while reducing operational steps by nearly a third, this framework redefines efficiency in autonomous endovascular procedures.
Current AI agents only manage to complete 20.6% of complex real-world tasks, revealing a stark gap in their capabilities compared to human users.
A human-AI collaboration framework offers a path to more trustworthy and comparable sustainability ratings by creating benchmark datasets that expose inconsistencies in existing methodologies.