Marcelo Gennari do Nascimento
4 papers · 2019–2024 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
๐
Conference Polyglot ยท Bronze
๐
Academic Marathon ยท Sprint
๐
Interdisciplinary Bridge ยท Bronze
๐ฃ
Hot Topic Early Bird
Top co-authors
Research topics
Keywords
model quantization
(1)
efficient training
(1)
knowledge distillation
(1)
neural network optimization
(1)
gradient computation
(1)
convolutional neural network
(1)
post-training compression
(1)
inference speedup
(1)
model sparsification
(1)
integer arithmetic
(1)
neural network
(1)
block floating point
(1)
convolution operator
(1)
parameter removal
(1)
embedding dimension reduction
(1)
quantization scheme
(1)
transformer compression
(1)
Papers
SliceGPT: Compress Large Language Models by Deleting Rows and Columns
ICLR 2024
Hyperblock Floating Point: Generalised Quantization Scheme for Gradient and Inference Computation
WACV 2023
Finding Non-Uniform Quantization Schemes using Multi-Task Gaussian Processes
ECCV 2020
DSConv: Efficient Convolution Operator
ICCV 2019