A joint low-rank and mixed-precision quantization method that assigns rank and bit-width per transformer layer under a memory constraint, showing state-of-the-art compression accuracy.
BERT: Pre-training of deep bidirectional trans- formers for language understanding
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
MLoRQ: Bridging Low-Rank and Quantization for Transformer Compression
A joint low-rank and mixed-precision quantization method that assigns rank and bit-width per transformer layer under a memory constraint, showing state-of-the-art compression accuracy.