SkillWeave partitions LLM capabilities into compressible skillpacks to deliver strong multi-domain performance with a 9B model that outperforms larger monolithic LLMs and achieves up to 4x speedup on benchmarks.
Simo Ryu, Seunghyun Seo, and Jaejun Yoo
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Skill Weaving: Efficient LLM Improvement via Modular Skillpacks
SkillWeave partitions LLM capabilities into compressible skillpacks to deliver strong multi-domain performance with a 9B model that outperforms larger monolithic LLMs and achieves up to 4x speedup on benchmarks.