Metraipolis › archive › dc_c28ef87a89bc

Lluna: Collaborative Unimodal Models for Missing-Modality Inference — arXiv:2610.20526

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.20526
License (as archived): CC0-1.0
Archived: 2026-10-15T21:58:21.244Z
SHA-256 of the archived text: 7e3b31aedb1323687ffefc1232727546ff2014a95b6c9e9f1118762eda66fdc4
Stable URL of this page: https://metraipolis.com/documento/dc_c28ef87a89bc

How to cite

Lluna: Collaborative Unimodal Models for Missing-Modality Inference — arXiv:2610.20526 — arXiv (en), https://arxiv.org/abs/2610.20526 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c28ef87a89bc (Metraipolis archive dc_c28ef87a89bc, sha256 7e3b31aedb1323687ffefc1232727546ff2014a95b6c9e9f1118762eda66fdc4)

BibTeX

@misc{dcc28ef87a89bc,
  title = {Lluna: Collaborative Unimodal Models for Missing-Modality Inference — arXiv:2610.20526},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.20526},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c28ef87a89bc; sha256 7e3b31aedb1323687ffefc1232727546ff2014a95b6c9e9f1118762eda66fdc4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20526. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Pretrained unimodal models offer a flexible route to multimodal prediction through collaboration, but this collaboration can become less accurate than a surviving unimodal model when modalities are missing. We study this setting using fixed surviving-model anchors and find that collaborative gains can weaken or reverse as inputs disappear, even when the anchor's own input is unchanged. Our diagnostics further reveal reduced recovery of modality-specific information after aggregation and state-dependent collaborative representations. We propose Lluna, which combines a direct private prediction path from adapted unimodal features with a common graph-based collaboration branch that provides a residual correction. Progressive Collaboration Consistency organizes richer-to-poorer guidance along single-modality removals, aligning normalized common representations while task supervision adapts predictions to the available evidence. Across eight datasets spanning affective computing, scene understanding, and medical prediction, Lluna achieves the best evaluated average performance over non-full input states, improving Mean-Missing by 4.26\% on average relative to the strongest evaluated baseline. The fixed-anchor diagnostic also shows positive gains in mean collaboration under minimal inputs on all eight tasks. Code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MM, nuovi lavori del giorno).
Categorie arXiv: Multimedia (cs.MM).
Pagina del lavoro: https://arxiv.org/abs/2610.20526 — 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 2026-10-15T21:39:29.400Z dalla pagina https://arxiv.org/list/cs.MM/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).