Metraipolis › archive › dc_b77dcbfd5572
Structured Latent Modeling for Supervised Multimodal Information Decomposition — arXiv:2609.35502
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.35502
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T22:39:10.294Z
- SHA-256 of the archived text
12599c82b3b8b0703047b37381f08d12db50ec00b8442ff8e84201b0fde3b421- Stable URL of this page
https://metraipolis.com/documento/dc_b77dcbfd5572
How to cite
Structured Latent Modeling for Supervised Multimodal Information Decomposition — arXiv:2609.35502 — arXiv (en), https://arxiv.org/abs/2609.35502 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b77dcbfd5572 (Metraipolis archive dc_b77dcbfd5572, sha256 12599c82b3b8b0703047b37381f08d12db50ec00b8442ff8e84201b0fde3b421)
BibTeX
@misc{dcb77dcbfd5572,
title = {Structured Latent Modeling for Supervised Multimodal Information Decomposition — arXiv:2609.35502},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.35502},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b77dcbfd5572; sha256 12599c82b3b8b0703047b37381f08d12db50ec00b8442ff8e84201b0fde3b421},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35502. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multimodal prediction relies on diverse forms of evidence: information repeated across modalities, cues specific to a single source, and complex cross-modal dependencies that emerge only when inputs are considered together. While recent methods promote richer interactions, they lack a principled way to isolate these target-relative contributions within learned continuous representations. We introduce a framework that applies contrastive or masked objectives at intermediate layers, coupled with source-wise invertible normalizing flows and a supervised, low-rank latent variable model. This architecture explicitly factorizes the joint distribution into shared task-relevant variation, modality-specific predictive variation, and task-irrelevant dependence. Drawing connections to prior multimodal learning assumptions, our approach evaluates how modalities independently and jointly contribute to the target. Ultimately, this framework unites intermediate representation learning with structured likelihood-based guidance, offering a practical latent-variable lens for characterizing continuous multimodal interactions. Empirically, we demonstrate the effectiveness of our approach across diverse multimodal benchmarks, showing robust improvements in predictive performance. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.35502 — 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 2026-10-07T22:14:28.456Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).