cs.SD · 2026-10-13 · No. 142
Sound, 2026-10-13.
1 new papers in cs.SD. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
1 entries-
01
AudioTETRIS: Token Elimination via Transitional Importance Signals for Efficient Audio LLMs
Shreya Sajid, Anna Vettoruzzo, Joaquin Vanschoren
cs.SD · cs.AI · eess.AS
Large Audio Language Models (LALMs) achieve strong performance on speech-text tasks, but standard audio encoders produce hundreds of tokens for even short audio clips. Because self-attention scales quadratically in sequence length, this inflates inference-time compute substantially. Current training-free token compression methods prune or merge tokens based solely on coarse attention or feature similarity. However, treating audio tokens as...
This edition is part of The Daily Abstract — cs.SD archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.