Search papers, labs, and topics across Lattice.
2
0
6
LLMs can achieve high compilation rates in formal reasoning by either fabricating axioms during proof generation or subtly mistranslating premises, revealing a critical gap between proof validity and formalization faithfulness.
Training a 70B parameter open-source LLM on a supercomputer reveals the hidden engineering hurdles and infrastructure adaptations needed to democratize large-scale AI development beyond the private sector.
