Search papers, labs, and topics across Lattice.
3
0
7
Reasoning-aware retrieval can boost language model performance by surfacing diverse solution strategies that traditional methods overlook.
Instead of all-or-nothing certification, CROP offers statistical guarantees on the *longest correct prefix* of a reasoning trace, enabling more effective error localization and repair.
LLMs can autonomously discover novel neural architectures that achieve state-of-the-art performance in specialized domains, suggesting a path towards automated scientific discovery.
