Denis Kuznedelev
11 papers · 2023–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (14) π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (3) π Cross-Pollinator (12)
π
Triple Crown
β‘
Prolific Year
(5)
π
Century Club
(11)
β
The Questioner
Conferences
NIPS (5)
ICLR (3)
ICML (3)
Top co-authors
Keywords
graph neural network
(2)
node classification
(2)
model compression
(2)
uncertainty quantification
(1)
graph structure
(1)
neural network optimization
(1)
message passing
(1)
vector quantization
(1)
second-order optimization
(1)
straight-through estimator
(1)
distributional shift
(1)
parameter quantization
(1)
bit-width reduction
(1)
robustness evaluation
(1)
quantization-aware training
(1)
heterophilous graph
(1)
optimal brain surgeon
(1)
large language model
(1)
homophily measure
(1)
label informativeness
(1)
Papers
Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models
ICML 2025
EvoPress: Accurate Dynamic Model Compression via Evolutionary Search
ICML 2025
The Iterative Optimal Brain Surgeon: Faster Sparse Recovery by Leveraging Second-Order Information
NIPS 2024
SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression
ICLR 2024
Extreme Compression of Large Language Models via Additive Quantization
ICML 2024
PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression
NIPS 2024
A critical look at the evaluation of GNNs under heterophily: Are we really making progress?
ICLR 2023
CAP: Correlation-Aware Pruning for Highly-Accurate Sparse Vision Models
NIPS 2023
Evaluating Robustness and Uncertainty of Graph Models Under Structural Distributional Shifts
NIPS 2023
Characterizing Graph Datasets for Node Classification: Homophily-Heterophily Dichotomy and Beyond
NIPS 2023
A view of mini-batch SGD via generating functions: conditions of convergence, phase transitions, benefit from negative momenta.
ICLR 2023