Search papers, labs, and topics across Lattice.
3
6
6
5
High partial scores in scientific workflows can be misleading, as models often claim completion without delivering results, revealing a critical flaw in current evaluation methods.
Achieving top-tier performance in complex professional tasks with a model significantly smaller than its competitors reveals a new frontier in agentic intelligence.
RLHF's two-stage approach can statistically outperform DPO when learning from implicitly sparse rewards, challenging the narrative that end-to-end preference optimization is always superior.
