Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Denis Kuznedelev
Observed name:
Kuznedelev, Denis
Observed institutions:
Skolkovo Institute of Science and Technology,
Institute of Science and Technology Austria,
University of Washington,
Yandex (Russia)
ORCID:
0009-0005-2420-9620
Observed ORCID:
0009-0005-2420-9620
OpenAlex ID:
A5063706079
SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression
2023
·
Dettmers, Tim
, Svirschevski, Ruslan
, et al.
·
arXiv (Cornell University)
·
40
PDF
A critical look at the evaluation of GNNs under heterophily: Are we really making progress?
2023
·
Platonov, Oleg
, Kuznedelev, Denis
, et al.
·
arXiv (Cornell University)
·
29
PDF
Characterizing Graph Datasets for Node Classification: Homophily-Heterophily Dichotomy and Beyond
2023
·
Oleg Platonov
, Denis Kuznedelev
, et al.
·
neural information processing systems
·
21
PDF
Sparse Fine-Tuning for Inference Acceleration of Large Language Models
2025
·
Eldar Kurtic
, Denis Kuznedelev
, et al.
·
Machine translation
·
8
PDF
Extreme Compression of Large Language Models via Additive Quantization
2024
·
Egiazarian, Vage
, Panferov, Andrei
, et al.
·
arXiv (Cornell University)
·
8
PDF
PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression
2024
·
Vladimir Malinovskii
, Denis Mazur
, et al.
·
neural information processing systems
·
4
PDF
CAP: Correlation-Aware Pruning for Highly-Accurate Sparse Vision Models
2023
·
Denis Kuznedelev
, Eldar Kurtic
, et al.
·
neural information processing systems
·
4
PDF
Does Diffusion Beat GAN in Image Super Resolution?
2024
·
Kuznedelev, Denis
, Startsev, Valerii
, et al.
·
arXiv (Cornell University)
·
3
PDF
Vision Models Can Be Efficiently Specialized via Few-Shot Task-Aware Compression
2023
·
Kuznedelev, Denis
, Tabesh, Soroush
, et al.
·
arXiv (Cornell University)
·
2
PDF
YaART: Yet Another ART Rendering Technology
2025
·
Sergey Kastryulin
, Artem Konev
, et al.
·
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)
·
1
PDF
Accurate Neural Network Pruning Requires Rethinking Sparse Optimization
2023
·
Kuznedelev, Denis
, Kurtic, Eldar
, et al.
·
arXiv (Cornell University)
·
1
PDF
Evaluating Robustness and Uncertainty of Graph Models Under Structural Distributional Shifts
2023
·
Gleb Bazhenov
, Denis Kuznedelev
, et al.
·
neural information processing systems
·
1
PDF
Representation-Space MMD for Diffusion Language Models
2026
·
Drobyshevskiy, Ilya
, Sudakov, Ilia
, et al.
·
arXiv (Cornell University)
PDF
KV Cache Offloading for Context-Intensive Tasks
2026
·
Bocharnikov, Andrey
, Ermakov, Ivan
, et al.
·
arXiv (Cornell University)
PDF
Asynchronous Reasoning: Training-Free Interactive Thinking LLMs
2025
·
Yakushev, George
, Babina, Nataliia
, et al.
·
arXiv (Cornell University)
PDF
Scale-wise Distillation of Diffusion Models
2025
·
Starodubcev, Nikita
, Drobyshevskiy, Ilya
, et al.
·
arXiv (Cornell University)
PDF
Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models
2025
·
Shutova, Alina
, Malinovskii, Vladimir
, et al.
·
arXiv (Cornell University)
PDF
Hogwild! Inference: Parallel LLM Generation via Concurrent Attention
2025
·
Gleb Rodionov
, Roman Garipov
, et al.
·
neural information processing systems
PDF
Machine Translation: Technologies and Applications
2025
·
Kurtic, Eldar
, Kuznedelev, Denis
, et al.
·
Institute of Science and Technology Austria
Label Privacy in Split Learning for Large Models with Parameter-Efficient Training
2024
·
Zmushko, Philip
, Mansurov, Marat
, et al.
·
arXiv (Cornell University)
PDF
Switti: Designing Scale-Wise Transformers for Text-to-Image Synthesis
2024
·
Voronov, Anton
, Kuznedelev, Denis
, et al.
·
arXiv (Cornell University)
PDF
EvoPress: Accurate Dynamic Model Compression via Evolutionary Search
2024
·
Sieberling, Oliver
, Kuznedelev, Denis
, et al.
·
arXiv (Cornell University)
PDF
Accurate Compression of Text-to-Image Diffusion Models via Vector Quantization
2024
·
Egiazarian, Vage
, Kuznedelev, Denis
, et al.
·
arXiv (Cornell University)
PDF
The Iterative Optimal Brain Surgeon: Faster Sparse Recovery by Leveraging Second-Order Information
2024
·
Diyuan Wu
, Ionut-Vlad Modoranu
, et al.
·
neural information processing systems
PDF
A view of mini-batch SGD via generating functions: conditions of convergence, phase transitions, benefit from negative momenta
2022
·
Velikanov, Maksim
, Kuznedelev, Denis
, et al.
·
arXiv (Cornell University)
PDF
Show more works
View as search
Works count:
26
Citation count:
122
H-index:
5
I10-index:
3
Year
Topic
Type
