Metraipolis › archive › dc_7b51ea06bdbc

Exploring Heterogeneous Model Merging Approach for Complex Knowledge Transfer — arXiv:2609.39369

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.39369
License (as archived): CC0-1.0
Archived: 2026-10-07T13:13:47.286Z
SHA-256 of the archived text: 7704d7c895aa8c2ac830849cfd7ddf06207f7c2544b371005b1ef65fe054b4e4
Stable URL of this page: https://metraipolis.com/documento/dc_7b51ea06bdbc

How to cite

Exploring Heterogeneous Model Merging Approach for Complex Knowledge Transfer — arXiv:2609.39369 — arXiv (en), https://arxiv.org/abs/2609.39369 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7b51ea06bdbc (Metraipolis archive dc_7b51ea06bdbc, sha256 7704d7c895aa8c2ac830849cfd7ddf06207f7c2544b371005b1ef65fe054b4e4)

BibTeX

@misc{dc7b51ea06bdbc,
  title = {Exploring Heterogeneous Model Merging Approach for Complex Knowledge Transfer — arXiv:2609.39369},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.39369},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7b51ea06bdbc; sha256 7704d7c895aa8c2ac830849cfd7ddf06207f7c2544b371005b1ef65fe054b4e4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39369. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Specialized models encode task-oriented behavior, but transferring that behavior to a general language model usually requires training, distillation, or representation alignment. We study whether such ability can instead be transferred directly at the parameter level. We apply two existing training-free heterogeneous merging methods, previously shown to transfer knowledge between general language models, to specialist-to-general transfer, projecting a specialist donor into the recipient's shape and interpolating backbone parameters without gradient updates or semantic alignment. Intersection-Merge (IM) injects a prefix-aligned donor slice matching the recipient shape, while Activate-Prune-Merge (APM) uses forward-pass activation statistics to select which donor dimensions to retain before injection. Across embedding, reranking, reward modeling, and MoE code-specialist transfer, both methods improve the general recipient, showing that simple heterogeneous merging can move capabilities across diverse specialist roles.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.39369 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T12:44:51.817Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).