On-policy distillation gains efficiency from early foresight in module allocation and update directions, which the proposed EffOPD method exploits for 3x faster training with comparable performance.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Hy-MT2 is a new family of fast multilingual translation models that claim to outperform several open-source LLMs and commercial APIs across diverse evaluation settings while supporting efficient on-device deployment.
citing papers explorer
-
Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation
On-policy distillation gains efficiency from early foresight in module allocation and update directions, which the proposed EffOPD method exploits for 3x faster training with comparable performance.
-
Hy-MT2: A Family of Fast, Efficient and Powerful Multilingual Translation Models in the Wild
Hy-MT2 is a new family of fast multilingual translation models that claim to outperform several open-source LLMs and commercial APIs across diverse evaluation settings while supporting efficient on-device deployment.