Search papers, labs, and topics across Lattice.
3
0
5
0
A 32B model in Marathi performs like a 10B model in English, revealing how model size and reasoning can bridge language resource gaps in cross-lingual transfer.
Machine translation benchmarks have functionally saturated, but pairing human-authored failure cases with deterministic verification rules reveals critical multimodal blind spots that automated metrics consistently miss.
Train your reward model on English preferences and unlock effective preference tuning across a diverse range of languages, even without language-specific annotations.
