Julia Gusak
6 papers · 2020–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (11) π§ Keyword Pioneer π Conference Polyglot (4) π Academic Marathon (5) π£ Hot Topic Early Bird
π
Cross-Pollinator
(13)
π
Interdisciplinary Bridge
π
Trend Setter
Conferences
ICML (3)
ECCV (1)
IJCAI (1)
NIPS (1)
Top co-authors
Keywords
model compression
(1)
deep learning
(1)
continuous optimization
(1)
distributed training
(1)
piecewise constant approximation
(1)
memory efficiency
(1)
memory optimization
(1)
activation memory
(1)
activation function
(1)
memory footprint
(1)
adjoint method
(1)
neural ode
(1)
gradient quantization
(1)
gradient propagation
(1)
gradient checkpointing
(1)
mixed precision training
(1)
computational graph
(1)
large language model
(1)
activation checkpointing
(1)
interpolation technique
(1)
Papers
HiRemate: Hierarchical Approach for Efficient Re-materialization of Neural Networks
ICML 2025
Few-bit Backward: Quantized Gradients of Activation Functions for Memory Footprint Reduction
ICML 2023
Rockmate: an Efficient, Fast, Automatic and Generic Tool for Re-materialization in PyTorch
ICML 2023
Survey on Efficient Training of Large Neural Networks
IJCAI 2022
Interpolation Technique to Speed Up Gradients Propagation in Neural ODEs
NIPS 2020
Stable Low-rank Tensor Decomposition for Compression of Convolutional Neural Network
ECCV 2020