Salvato in:
Dettagli Bibliografici
Autori principali: Luo, Jiale, Liang, Xiaoyu, Hu, Haoji
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2605.25179
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911714586394624
author Luo, Jiale
Liang, Xiaoyu
Hu, Haoji
author_facet Luo, Jiale
Liang, Xiaoyu
Hu, Haoji
contents Audio-language models (ALMs) are increasingly used for audio captioning, question answering, and open-ended audio understanding, but their inference cost remains high when audio inputs are represented as long prefix-token sequences. These audio prefixes consume context budget, increase memory usage, and make deployment harder in resource-constrained or latency-sensitive settings. Existing training-free audio-token reduction methods mainly rely on fixed pooling or score-based pruning. Fixed pooling is content-agnostic, while score-based pruning can preserve isolated salient tokens but discard nearby acoustic context. We propose Local Temporal Bipartite Merging (LTBM), a training-free encoder-space compression method that merges similar nearby audio tokens under an explicit temporal window constraint. Beyond introducing LTBM, we use a controlled Global Merge variant to isolate whether temporal locality itself is a useful inductive bias for audio-token compression. Experiments on AudioCaps, Clotho, and MMAU with Qwen2-Audio show evidence of a task-dependent locality effect: locality-aware merging is more favorable for captioning at several compression settings, especially under stronger compression, while global matching is more competitive for multiple-choice audio understanding. A cross-backbone validation on Audio Flamingo 3 further supports the captioning-side advantage of locality-aware merging under moderate and aggressive compression.
format Preprint
id arxiv_https___arxiv_org_abs_2605_25179
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Locality Matters for Training-Free Audio Token Compression in Audio-Language Models
Luo, Jiale
Liang, Xiaoyu
Hu, Haoji
Computation and Language
Audio-language models (ALMs) are increasingly used for audio captioning, question answering, and open-ended audio understanding, but their inference cost remains high when audio inputs are represented as long prefix-token sequences. These audio prefixes consume context budget, increase memory usage, and make deployment harder in resource-constrained or latency-sensitive settings. Existing training-free audio-token reduction methods mainly rely on fixed pooling or score-based pruning. Fixed pooling is content-agnostic, while score-based pruning can preserve isolated salient tokens but discard nearby acoustic context. We propose Local Temporal Bipartite Merging (LTBM), a training-free encoder-space compression method that merges similar nearby audio tokens under an explicit temporal window constraint. Beyond introducing LTBM, we use a controlled Global Merge variant to isolate whether temporal locality itself is a useful inductive bias for audio-token compression. Experiments on AudioCaps, Clotho, and MMAU with Qwen2-Audio show evidence of a task-dependent locality effect: locality-aware merging is more favorable for captioning at several compression settings, especially under stronger compression, while global matching is more competitive for multiple-choice audio understanding. A cross-backbone validation on Audio Flamingo 3 further supports the captioning-side advantage of locality-aware merging under moderate and aggressive compression.
title Locality Matters for Training-Free Audio Token Compression in Audio-Language Models
topic Computation and Language
url https://arxiv.org/abs/2605.25179