Search papers, labs, and topics across Lattice.
4
0
4
0
Interference, measured by task vector variance, predicts LLM merge collapse and guides repair, revealing that sign conflict statistics are anti-predictive.
Turning text into images cuts reranking token overhead by up to 50% and yields a 1.70× throughput boost—all while outperforming standard sub-4B text rerankers across BEIR.
CRPO reveals that leveraging English preference data can dramatically enhance LLM performance in low-resource languages, outperforming traditional methods.
Reranking documents by language coherence can dramatically improve retrieval performance, as shown by LAMAR's superior results across multiple languages.
