Metraipolis › archive › dc_b3f804b34860

In-Context Adapter Generation for Compositional Generalization in Large Audio Language Models — arXiv:2610.34413

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.34413
License (as archived)
CC0-1.0
Archived
2026-10-27T08:01:24.640Z
SHA-256 of the archived text
f3bff7ba0a731d5e8e63b147c081ded2ccccb320515aaf5e0370cf07df2637ea
Stable URL of this page
https://metraipolis.com/documento/dc_b3f804b34860

How to cite

In-Context Adapter Generation for Compositional Generalization in Large Audio Language Models — arXiv:2610.34413 — arXiv (en), https://arxiv.org/abs/2610.34413 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b3f804b34860 (Metraipolis archive dc_b3f804b34860, sha256 f3bff7ba0a731d5e8e63b147c081ded2ccccb320515aaf5e0370cf07df2637ea)
BibTeX
@misc{dcb3f804b34860,
  title = {In-Context Adapter Generation for Compositional Generalization in Large Audio Language Models — arXiv:2610.34413},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.34413},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b3f804b34860; sha256 f3bff7ba0a731d5e8e63b147c081ded2ccccb320515aaf5e0370cf07df2637ea},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.34413. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large audio language models (LALMs) have achieved strong performance on standard speech and audio understanding tasks, yet their ability to systematically generalize to novel task compositions remains underexplored. Taking a meta-learning view, we extend Text-to-LoRA (T2L) to LALMs, generating instruction-conditioned LoRA adapters with a Transformer hypernetwork rather than learning a single fixed adapter shared across instructions. To exploit fine-grained task information, we introduce in-context adapter generation (ICAG), a token-level hypernetwork architecture; we call the resulting method T2L-ICAG. We evaluate this approach on two representative LALMs using SIFT-50M for supervised fine-tuning and construct a controlled compositional evaluation suite covering five task classes. Across two LALM backbones, T2L-ICAG consistently improves over static LoRA and also the global embedding-based T2L baseline. Coverage and capacity analyses further show that these gains are larger on structurally out-of-domain tasks and cannot be explained by parameter count alone. These results suggest that generating task-specific adapters from instructions is a promising direction for improving compositional generalization of LALMs.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Audio and Speech Processing (eess.AS) ; Artificial Intelligence (cs.AI); Sound (cs.SD).
Pagina del lavoro: https://arxiv.org/abs/2610.34413 — 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 2026-10-27T07:55:30.902Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).