arXiv AI
AudioTETRIS: Token Elimination via Transitional Importance Signals for Efficient Audio LLMs
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Aug 21
Towards Audio Token Compression in Large Audio Language Models
arXiv:2511. 20973v2 Announce Type: replace-cross Abstract: Large Audio Language Models (LALMs) deliver strong performance across speech and audio tasks, but their audio encoders generate high-rate token sequences (e.
arXiv AI
Aug 11
VoxZip: Semantic-Anchored Temporal KV Cache Compression for Long-Context Audio Inference
arXiv:2608. 08569v1 Announce Type: new Abstract: Recent advancements in Speech Large Language Models have demonstrated remarkable capabilities in understanding complex audio tasks.
arXiv AI
Jul 7
OmniFocus: Query-Guided Modality-Balanced Token Compression for Omni-Modal Large Language Models
arXiv:2607. 03050v1 Announce Type: cross Abstract: Omni modal large language models (OmniLLMs) have attracted wide attention for their ability to jointly process audio and video, but they generate large token sequences under audio-visual inputs, leading to substantial inference cost.
arXiv AI
Jul 9
DASH: Dynamic Audio-Driven Semantic Chunking for Efficient Omnimodal Token Compression
arXiv:2603. 15685v2 Announce Type: replace-cross Abstract: Omnimodal large language models (OmniLLMs) jointly process audio and visual streams, but the resulting long multimodal token sequences make inference prohibitively expensive.
arXiv Computation and Language
Sep 1
A Simple Method to Enhance Pre-trained Language Models with Speech Tokens for Classification
arXiv:2512.07571v3 Announce Type: replace Abstract: This paper presents a simple method that allows to easily enhance textual pre-trained large language models with speech information, when fine-tune...
arXiv Machine Learning
Jul 24
Encode Once, Decode Never: Reusing Audio LM Internals for Efficient Temporal Localization
arXiv:2602. 10230v2 Announce Type: replace Abstract: Audio language models process input audio into rich frame-level representations, but the standard approach to temporal localization generates timestamps as sequences of text tokens, which discards the frame-level representations in favor of autoregressive decoding.