Search papers, labs, and topics across Lattice.
2
0
6
A staggering 8.8-18.4 point performance gap in AI agents reveals that multilingual capabilities are not just a nice-to-have, but a critical oversight in current evaluations.
Naively applying RL to code generation models can *hurt* cross-language transfer, but a clever pre-training trick using "parallel programs" unlocks better generalization.
