Track the frontier, from condensed matter to cosmology.
Search papers, labs, and topics across Lattice.
3
0
6
Clinical MLLMs can be significantly improved by optimizing for AUROC via pairwise instance rankings, reversing accuracy-based prompt evolution's performance degradation.
Orthonormal initialization can transform low-rank adaptation in RLVR, outperforming established methods and stabilizing training dynamics.
Prompt optimization can significantly enhance multi-agent LLM systems, but its effectiveness hinges on the specific configuration of the agents and their interactions.