arXiv (All)
open access
AudioTETRIS: Token Elimination via Transitional Importance Signals for Efficient Audio LLMs
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
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- AudioTETRIS: Token Elimination via Transitional Importance Signals for Efficient Audio LLMs#1291851
- Libra: Taming Attention Workload Skew in Long-Context LLM Training with Bounded Sequence Pool#1014774
- AVOC: Enhancing Hour-Level Audio-Video Understanding in Omni-Modal LLMs via Retrieval-Inspired Token Compression#1202121
- Libra: Taming Attention Workload Skew in Long-Context LLM Training with Bounded Sequence Pool#405615
- Data-Free Pruning of Self-Attention Layers in LLMs#1141466
Record · ID 1297952
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive