Metraipolis › archive › dc_dc8e77f8696e

Task-disentangled Low-Rank Adaptation for Versatile Audio-visual Multi-modal Learning Tasks within a Unified Framework — arXiv:2608.24209

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.24209
License (as archived)
CC0-1.0
Archived
2026-10-18T07:02:40.873Z
SHA-256 of the archived text
69016ae218c30270f23f1873c10f79b870f019277769462f8cdfb50126853e63
Stable URL of this page
https://metraipolis.com/documento/dc_dc8e77f8696e

How to cite

Task-disentangled Low-Rank Adaptation for Versatile Audio-visual Multi-modal Learning Tasks within a Unified Framework — arXiv:2608.24209 — arXiv (en), https://arxiv.org/abs/2608.24209 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dc8e77f8696e (Metraipolis archive dc_dc8e77f8696e, sha256 69016ae218c30270f23f1873c10f79b870f019277769462f8cdfb50126853e63)
BibTeX
@misc{dcdc8e77f8696e,
  title = {Task-disentangled Low-Rank Adaptation for Versatile Audio-visual Multi-modal Learning Tasks within a Unified Framework — arXiv:2608.24209},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.24209},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dc8e77f8696e; sha256 69016ae218c30270f23f1873c10f79b870f019277769462f8cdfb50126853e63},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.24209. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Inspired by human multi-modal perception, Audio-Visual Multi-Modal Learning (AVMML) integrates auditory and visual information to leverage complementary cross-modal cues, enabling more robust and comprehensive scene perception. Existing studies predominantly tackle each AVMML task in isolation, which stands in stark contrast to humans' unified cognitive capacity for handling versatile perception. However, naive joint training across multiple AVMML tasks often suffers from mutual interference, arising from the intricate inter-task relationships. To address this, we propose a unified framework that simultaneously accommodates versatile AVMML tasks. Specifically, benefiting from powerful representation and generalization capabilities of large language models, we design a task-disentangled Low-Rank Adaptation (LoRA) mechanism that enables dynamic integration of both task-specific and task-shared knowledge, thereby facilitating effective multi-task collaboration. The proposed task-disentangled LoRA comprises three components: a task-general low-rank matrix, task-specific modulation matrices, and cross-task collaboration experts, which respectively capture universal audio-visual knowledge, decouple task-specific pattern, and exploit inherent inter-task correlations. By unifying explicit collaboration from both model and task perspectives, our approach not only surpasses existing unified audio-visual models across multiple AVMML tasks, but also outperforms most task-specific models on certain AVMML tasks.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-26 in cs.MM).
Categorie arXiv: Multimedia (cs.MM).
Pagina del lavoro: https://arxiv.org/abs/2608.24209 — 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 2026-10-18T07:00:47.824Z dalla pagina https://arxiv.org/catchup/cs.MM/2026-08-26?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).