# Locality Matters for Training-Free Audio Token Compression in Audio-Language Models

arXiv: https://arxiv.org/abs/2605.25179 · HTML: https://mlsanity.com/paper/2605.25179/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Audio and omni-modal token compression, one of 12 directions in Efficient LLM inference and serving.
- Builds on 16 of its 25 references that are in the map.
- First posted on arXiv 24 May 2026.

## Placed in

- Efficient LLM inference and serving / [Audio and omni-modal token compression](https://mlsanity.com/inference/audio-and-omni-modal-token-compression/)

## Builds on (most cited first, 16 of 16)

- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models](https://mlsanity.com/paper/2311.07919/) (2023)
- [Clotho: An Audio Captioning Dataset](https://mlsanity.com/paper/1910.09387/) (2019)
- [MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark](https://mlsanity.com/paper/2410.19168/) (2024)
- [Pengi: An Audio Language Model for Audio Tasks](https://mlsanity.com/paper/2305.11834/) (2023)
- [Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models](https://mlsanity.com/paper/2507.08128/) (2025)
- [Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities](https://mlsanity.com/paper/2402.01831/) (2024)
- [Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More](https://mlsanity.com/paper/2502.11494/) (2025)
- [Prompting Large Language Models with Speech Recognition Abilities](https://mlsanity.com/paper/2307.11795/) (2023)
- [Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities](https://mlsanity.com/paper/2503.03983/) (2025)
- [Token Pruning in Multimodal Large Language Models: Are We Solving the Right Problem?](https://mlsanity.com/paper/2502.11501/) (2025)
- [Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification](https://mlsanity.com/paper/2412.00876/) (2024)
- [AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning](https://mlsanity.com/paper/2412.03248/) (2024)
- [Towards Audio Token Compression in Large Audio Language Models](https://mlsanity.com/paper/2511.20973/) (2025)
- [Segmentwise Pruning in Audio-Language Models](https://mlsanity.com/paper/2511.14293/) (2025)
- [LFTR: Learning-Free Token Reduction for Multimodal Large Language Models](https://mlsanity.com/paper/2501.17391/) (2025)

## Built on by (most cited first, 3 of 3)

- [AS2D: Accelerating On-Demand Audio Understanding on Mobile Devices](https://mlsanity.com/paper/2609.37617/) (2026)
- [Audio Token Attention Is Predictable Before the Language Model Runs](https://mlsanity.com/paper/2609.38878/) (2026)
- [AudioTETRIS: Token Elimination via Transitional Importance Signals for Efficient Audio LLMs](https://mlsanity.com/paper/2610.13600/) (2026)

## Abstract (arXiv)

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.