Search papers, labs, and topics across Lattice.
2
0
4
MiniMax-M2 proves that massive parameter counts don't always translate to better agentic performance; strategic activation of a smaller subset can unlock frontier-level intelligence.
A spin-adapted neural network achieves state-of-the-art accuracy on the notoriously difficult FeMo-cofactor, outperforming even DMRG while using fewer computational resources.
