Showing cs.SDShow all
2 papers · 1 filter
cs.SD2026
Audio Token Attention Is Predictable Before the Language Model Runs
Kyoungjun Park, Yunzhe Li, Lili Qiu
A large audio language model (LALM) turns a minute of speech into 750-1,500 tokens and prefills every one. Image-token pruning often cuts after the language model's first layers, w…
cs.SD2026
ASD: Accelerating On-Demand Audio Understanding on Mobile Devices
Yunzhe Li, Kyoungjun Park, Hongzi Zhu +1
Speculative decoding accelerates autoregressive generation by using a smaller drafter to propose tokens for batched verification by a larger target. However, conventional speculati…