Skip to content

Mizar: A 159M-Parameter Audio-Language Model for Audio Understanding

Sep 2026 · arXiv.org · Vol abs/2609.28344 · 0 citations · 26 references
Computer Science

TL;DR

Mizar, a 159.3M-parameter ALM, is introduced, a recipe that brings together architecture, data, and three-stage training to build Mizar, a 159.3M-parameter ALM that surpasses the previous best-performing ALM below 200M parameters on all three benchmarks.

Abstract

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 https://github.com/KaiyangLi1992/Mizar_159M.

View source

Similar papers

Preprint Oct 2026

TS-SP: Learning Speaker-Preserving Representations in Audio Large Language Models

Audio large language models (ALLMs) can understand speech content, yet their ability to use speaker identity for verification remains limited. We propose TS-SP (Two-Stage Speaker Preservation), a parameter-efficient framework for learning speaker-preserving representations and making them accessible to an ALLM's langua...

Jun-Jie Li, Zheng Liang, Zhe Li et al. · 0 citations

What Did the MLLM Hear? Token-Level Spectro-Temporal Grounding for Audio MLLM Explainability

STAG is introduced, to the authors' knowledge the first post-hoc framework for token-level spectro-temporal grounding of captions generated by audio-based MLLMs, and provides behavioral support for the faithfulness and selectivity of the explanations.

Lucia Cascone, Valeria Fraenza, Michele Nappi et al. · 0 citations
#natural language process... Preprint Sep 2026

Qwen-Audio-3.0-ASR Technical Report

Qwen-Audio-3.0-ASR is presented, a Mixture-of-Experts (MoE) LLM-based ASR system designed to address production demands through a unified, instruction-following framework and demonstrates state-of-the-art or highly competitive recognition performance across a broad range of evaluation conditions.

Chuan-Meng Bian, Da-Ren Chen, Pei-Xin Chen et al. · 3 citations
#artificial intelligence Preprint Sep 2026

Heard but Not Heeded: Paralinguistic Information Encoding and Loss in Audio-Language Models

A mechanistic analysis of paralinguistic information in four open source models using the Expresso dataset with controlled speaking styles identifies a gap between what models encode and what they use, highlighting a key limitation in current audio language models.

Bhuvan Koduru, Dareen Alharthi, Rita Singh et al. · 3 citations · ⚡1
Preprint Aug 2026

FireRedAudio: A General-Purpose Audio Language Model with Decoupled Continuous Representations for Understanding and Generation

FireRedAudio is introduced, a general-purpose audio language model with a shared 9B-parameter LLM that achieves competitive or leading performance in audio understanding and multilingual ASR, strong content accuracy and speaker preservation in zero-shot TTS, leading instruction following in Instruct TTS, and substantia...

Fei-Yu Shen, Fenglong Xie, Junjie Li et al. · 3 citations · ⚡1

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.