Metraipolis › archive › dc_3c9518eff4fe
Mizar: A 159M-Parameter Audio-Language Model for Audio Understanding — arXiv:2609.28344
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.28344
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T10:05:44.440Z
- SHA-256 of the archived text
d94671798d1b55a3a88d6a9525cb771b396395520bfbd7d8383c136ee046779b- Stable URL of this page
https://metraipolis.com/documento/dc_3c9518eff4fe
How to cite
Mizar: A 159M-Parameter Audio-Language Model for Audio Understanding — arXiv:2609.28344 — arXiv (en), https://arxiv.org/abs/2609.28344 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3c9518eff4fe (Metraipolis archive dc_3c9518eff4fe, sha256 d94671798d1b55a3a88d6a9525cb771b396395520bfbd7d8383c136ee046779b)
BibTeX
@misc{dc3c9518eff4fe,
title = {Mizar: A 159M-Parameter Audio-Language Model for Audio Understanding — arXiv:2609.28344},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.28344},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3c9518eff4fe; sha256 d94671798d1b55a3a88d6a9525cb771b396395520bfbd7d8383c136ee046779b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28344. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Audio-language models (ALMs) integrate acoustic perception with the knowledge encoded in language models, enabling contextual understanding of auditory events. Making these capabilities practical on devices with limited memory and computation motivates our focus on small ALMs with fewer than 200M parameters. We introduce a recipe that brings together architecture, data, and three-stage training to build Mizar, a 159.3M-parameter ALM. Its architecture connects a compact CED-Small audio encoder to SmolLM2-135M through a frequency-merging mapper. With supervision drawn from ReasonAQA, AudioMCQ, and AVQA, the model undergoes three training stages: audio-language alignment (Stage 1), audio-dependent fine-tuning (Stage 2), and post-training (Stage 3) aimed at strengthening weak skills while retaining learned capabilities. Across five random seeds, Mizar achieves mean accuracies of 52.92% on MMAU, 42.42% on MMAR, and 36.02% on ADQA-clean, surpassing the previous best-performing ALM below 200M parameters on all three benchmarks. It also supports local inference on a single CPU: on questions from the MMAU benchmark, the mean latency from opening the audio file to generating a complete answer is 1.09 seconds. Code and checkpoints are available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.CL). Categorie arXiv: Sound (cs.SD) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.28344 — 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 2026-10-08T09:11:49.697Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).