← Back to Model Beat
Research·3d ago·all news from November 18, 2026

DaisyRose-27B: Pushing the Frontier of Post-Training Efficiency

Researchers have released DaisyRose-27B, a new language model optimized for post-training efficiency. By utilizing specialized fine-tuning techniques, the developers aim to improve output quality while reducing the computational resources typically required for model deployment.

Covered by 1 source

Related stories

ResearchOur first phase of embedded assessmentsNov 16 · 4 sourcesResearchResearch acceleration: The jagged frontierNov 17 · 4 sourcesResearchTop AI Models Regularly Identify Civilians as Military Targets in TestsNov 17 · 4 sourcesResearchCombatting adversarial distillationNov 20