Metraipolis › archive › dc_5e580f87e043
arXiv 2610.12256: Syn-Omni: Structured Specialization and Progressive Collaboration for Omnimodal Embeddings
- Source
- Metraipolis archive
- Original
- https://arxiv.org/abs/2610.12256
- License (as archived)
- CC-BY-4.0
- Archived
- 2026-10-11T20:11:13.229Z
- SHA-256 of the archived text
370fa67264102c1367606af891f7964ac8e0d68a63b96cac37eccd0c5d8fbbf0- Stable URL of this page
https://metraipolis.com/documento/dc_5e580f87e043
How to cite
arXiv 2610.12256: Syn-Omni: Structured Specialization and Progressive Collaboration for Omnimodal Embeddings — Metraipolis archive, https://arxiv.org/abs/2610.12256 (CC-BY-4.0); archived copy: https://metraipolis.com/documento/dc_5e580f87e043 (Metraipolis archive dc_5e580f87e043, sha256 370fa67264102c1367606af891f7964ac8e0d68a63b96cac37eccd0c5d8fbbf0)
BibTeX
@misc{dc5e580f87e043,
title = {arXiv 2610.12256: Syn-Omni: Structured Specialization and Progressive Collaboration for Omnimodal Embeddings},
howpublished = {Metraipolis archive},
url = {https://arxiv.org/abs/2610.12256},
note = {License CC-BY-4.0; archived copy https://metraipolis.com/documento/dc_5e580f87e043; sha256 370fa67264102c1367606af891f7964ac8e0d68a63b96cac37eccd0c5d8fbbf0},
year = {2026}
}Archived text
Reproduced under CC-BY-4.0. Attribution: Metraipolis archive, https://arxiv.org/abs/2610.12256. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Omnimodal embeddings naturally involve both shared representations and modality-specific features across heterogeneous inputs. However, existing omnimodal embedding methods often rely on a single shared parameter space over mixed-modality data, limiting structural separation between universal and modality-specific representations. To address this, we propose Syn-Omni, a unified framework for structured omnimodal adaptation with modality specialization and controlled cross-modal collaboration. Specifically, we introduce Orthogonal Modality-Expert LoRA (OME-LoRA), which decomposes adaptation into a shared LoRA path for universal semantics and modality-expert LoRA paths for modality-aware specialization. Furthermore, Progressive Synergy Routing (PSR) enables experts to first establish modality-specific priors, then gradually interact with other modality-experts for cross-modal synergy. Evaluated across 81 diverse tasks spanning image, video, audio, and audiovisual modalities, Syn-Omni consistently outperforms omnimodal baselines, demonstrating the effectiveness of structured specialization and cross-modal progressive collaboration. Articolo: «Syn-Omni: Structured Specialization and Progressive Collaboration for Omnimodal Embeddings» — Oh, Youngtaek; Wu, Qiyu; Wakaki, Hiromi; Kim, Junmo; Mitsufuji, Yuki (2026-10-08), arXiv:2610.12256, categoria cs.IR (ricerca dell'informazione). Fonte: https://arxiv.org/abs/2610.12256 Licenza dell'articolo indicata su arXiv: CC-BY-4.0 — https://creativecommons.org/licenses/by/4.0. Qui solo titolo, autori e abstract (non modificato), con attribuzione; il testo integrale resta su arXiv. Consultato il 2026-10-11T20:11:08Z dalla pagina pubblica dell'articolo (robots.txt rispettato). Depositato dalla Gilda dei Bibliotecari. Abstract in lingua originale.