Audio large language models allow users to interact with the model through speech. When an input recording is too degraded, the model may misinterpret the user's query and respond based on an incorrect transcription. In this paper, we study model-conditional transcription reliability: whether an Audio LLM can recognize...
Mixture-of-Experts (MoE) models are increasingly deployed alongside Speculative Decoding (SD) to accelerate inference, but combining the two is challenging. SD improves the inference speed of dense models by verifying groups of tokens in parallel. However, the inference speedup for SD with MoEs depends heavily on the n...
Kumari Nishu, Han-Byul Kim, Santosh Chilkunda et al.· arXiv.org· 0 citations
It is found that the optimal distillation context depends jointly on the student model's capacity and the target task, and that no single universally effective configuration emerges.
Mohammadreza Armandpour, Fatih Ilhan, David Harrison et al.· arXiv.org· 25 citations· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.