4 citations · 6 across the 9 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.LG2023★ 2 cited
Weight subcloning: direct initialization of transformers using larger pretrained ones
Mohammad Samragh, Mehrdad Farajtabar, Sachin Mehta +5
Training large transformer models from scratch for a target task requires lots of data and is computationally demanding. The usual practice of transfer learning overcomes this chal…
cs.SD2023★ 4 cited
Improving vision-inspired keyword spotting using dynamic module skipping in streaming conformer encoder
Alexandre Bittar, Paul Dixon, Mohammad Samragh +2
Using a vision-inspired keyword spotting framework, we propose an architecture with input-dependent dynamic depth capable of processing streaming audio. Specifically, we extend a c…