Metraipolis › archive › dc_d396682d2aec
Tracing and Coordinating Cross-Layer Influence for Multimodal Model Merging — arXiv:2609.12897
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.12897
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T03:02:58.202Z
- SHA-256 of the archived text
46ff80230cb84c5e400589b71a6e2e326abc169b883e321d47dba9995380afe4- Stable URL of this page
https://metraipolis.com/documento/dc_d396682d2aec
How to cite
Tracing and Coordinating Cross-Layer Influence for Multimodal Model Merging — arXiv:2609.12897 — arXiv (en), https://arxiv.org/abs/2609.12897 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d396682d2aec (Metraipolis archive dc_d396682d2aec, sha256 46ff80230cb84c5e400589b71a6e2e326abc169b883e321d47dba9995380afe4)
BibTeX
@misc{dcd396682d2aec,
title = {Tracing and Coordinating Cross-Layer Influence for Multimodal Model Merging — arXiv:2609.12897},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.12897},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d396682d2aec; sha256 46ff80230cb84c5e400589b71a6e2e326abc169b883e321d47dba9995380afe4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12897. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multimodal model merging aims to consolidate task experts into a single model that retains their complementary capabilities. Most unimodal model merging methods combine expert updates within individual layers, and multimodal approaches largely follow this design. However, an expert update changes the representations passed to subsequent layers, allowing its influence to propagate across depth and affect how visual and textual information interact. When visual and language updates are combined, later updates act on inputs already modified by earlier ones, coupling their effects. This poses two challenges: (1) how to characterize the multimodal influence of individual expert updates across depth, and (2) how to jointly combine expert updates based on their multimodal influence. To address these challenges, we propose TAC-Merge for tracing and coordinating cross-layer influence in multimodal model merging. It contains two modules, i.e., multimodal influence mapping (MIM) and coupled merge control (CMC). MIM constructs graphs of update effects and uses Ricci curvature together with expert predictions to define a shared fusion objective. CMC models interactions among coefficient adjustments and jointly optimizes regional weights to synthesize one shared model. Experiments across diverse multimodal tasks demonstrate the effectiveness of TAC-Merge in consolidating complementary expert capabilities and supporting generalization to unseen tasks. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.12897 — 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 2026-10-16T02:51:27.827Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).