From the 2 of 27 linked papers with an AI index.
13 papers · 1 filter
Compress the Cache, Not the Speech Embedding: KV Compression for Efficient Speech LLMs
Ke-Han Lu, Keqi Deng, Ruchao Fan +2
Speech large language models (Speech LLMs) typically encode speech into sequences far longer than text, creating a major efficiency bottleneck during autoregressive decoding. A com…
CAAD: Contrastive Audio-Aware Distillation for Efficient Speech Language Models
Chun-Wei Chen, Tzu-Quan Lin, Ke-Han Lu +2
Speech Language Models achieve reasoning capabilities, but are often hindered by massive parameter counts and a tendency to prioritize linguistic priors over acoustic features. Whi…
How Auditory Knowledge in LLM Backbones Shapes Audio Language Models: A Holistic Evaluation
Ke-Han Lu, Szu-Wei Fu, Chao-Han Huck Yang +13
Large language models (LLMs) have been widely used as knowledge backbones of Large Audio Language Models (LALMs), yet how much auditory knowledge they encode through text-only pre-…
DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment
Ke-Han Lu, Zhehuai Chen, Szu-Wei Fu +25
We introduce DeSTA2.5-Audio, a general-purpose Large Audio Language Model (LALM) designed for robust auditory perception and instruction-following. Recent LALMs augment Large Langu…
TAU: A Benchmark for Cultural Sound Understanding Beyond Semantics
Yi-Cheng Lin, Yu-Hua Chen, Jia-Kai Dong +12
Large audio-language models are advancing rapidly, yet most evaluations emphasize speech or globally sourced sounds, overlooking culturally distinctive cues. This gap raises a crit…
Reducing Object Hallucination in Large Audio-Language Models via Audio-Aware Decoding
Tzu-wen Hsu, Ke-Han Lu, Cheng-Han Chiang +1
Large Audio-Language Models (LALMs) can take audio and text as the inputs and answer questions about the audio. While prior LALMs have shown strong performance on standard benchmar…