Tag
This study explores adding Greek to a Cosmos3 vision-language-action robot policy, revealing challenges in measurement and showing that bilingual training improves performance but overfits to translator phrasing. The results emphasize the need for null baselines and seed replication in low-resource localization.
This paper investigates the impact of data scale versus latency on cross-lingual transfer for streaming ASR, finding that multilingual initialization benefits are data-limited, not latency-limited, and diminish as target-language data increases.