Metraipolis › archive › dc_ff0eda99fca1

NeuCME: Toward Dynamic Multimodal Continual Learning via Neural Combinatorics of Multiple Experts — arXiv:2609.07009

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.07009
License (as archived): CC0-1.0
Archived: 2026-10-16T13:57:36.723Z
SHA-256 of the archived text: dfa5cf76fc7f909493a8a51a43f8c4681a2dcce841a305addd99ab508817df73
Stable URL of this page: https://metraipolis.com/documento/dc_ff0eda99fca1

How to cite

NeuCME: Toward Dynamic Multimodal Continual Learning via Neural Combinatorics of Multiple Experts — arXiv:2609.07009 — arXiv (en), https://arxiv.org/abs/2609.07009 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ff0eda99fca1 (Metraipolis archive dc_ff0eda99fca1, sha256 dfa5cf76fc7f909493a8a51a43f8c4681a2dcce841a305addd99ab508817df73)

BibTeX

@misc{dcff0eda99fca1,
  title = {NeuCME: Toward Dynamic Multimodal Continual Learning via Neural Combinatorics of Multiple Experts — arXiv:2609.07009},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.07009},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ff0eda99fca1; sha256 dfa5cf76fc7f909493a8a51a43f8c4681a2dcce841a305addd99ab508817df73},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07009. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multimodal continual learning has recently shown great potential for developing agents with human-like intelligence by continuously learning new tasks across multiple modalities. However, existing methods typically assume that the set of modalities per task is predefined and fixed. In this paper, we investigate a more realistic learning setting, referred to as dynamic multimodal continual learning, in which the set of modalities may vary across tasks rather than remaining fixed. This setting involves two primary challenges: (i) spatio-temporal catastrophic forgetting and (ii) adaptive multimodal fusion. To address these challenges, we propose NeuCME (as shorthand for \textbf{Neu}ral \textbf{C}ombinatorics of \textbf{M}ultiple \textbf{E}xperts), a novel framework designed to effectively learn and integrate knowledge across tasks with varying modalities. The proposed NeuCME model comprises three key components, namely modality-combinational rehearsal, multi-gated mixture-of-experts, and task relevance-guided distillation. Furthermore, we formulate an evaluation metric to quantify the dynamism of task sequences and then set up a comprehensive benchmark with different degrees of dynamism. Extensive experiments using four real-world datasets demonstrate that the proposed NeuCME outperforms state-of-the-art methods markedly.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.07009 — 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 2026-10-16T13:39:42.928Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).