Track the frontier, from condensed matter to cosmology.
Search papers, labs, and topics across Lattice.
2
0
4
3
Consolidating specialist LLMs into a single, more accurate generalist is possible with *zero* gradient updates, relying solely on forward passes and input statistics.
LLMs can achieve a "free lunch" in reasoning tasks, simultaneously improving accuracy and reducing token usage by simply training them to solve multiple problems in parallel.