Denis Kuznedelev

37 papers A* 11Journal 25Unranked 1

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Asynchronous Reasoning: Training-Free Interactive Thinking LLMs. CoRR George Yakushev, Nataliia Babina, Masoud Vahid Dastgerdi, Vyacheslav Zhdanovskiy, Alina Shutova, Denis Kuznedelev
2025	J	`jnl`	Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization. CoRR Vage Egiazarian, Roberto L. Castro, Denis Kuznedelev, Andrei Panferov, Eldar Kurtic, Shubhra Pandit, Alexandre Noll Marques, Mark Kurtz, Saleh Ashkboos, Torsten Hoefler, Dan Alistarh
2025	A*	`conf`	Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models. ICML Alina Shutova, Vladimir Malinovskii, Vage Egiazarian, Denis Kuznedelev, Denis Mazur, Nikita Surkov, Ivan Ermakov, Dan Alistarh
2025	J	`jnl`	Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models. CoRR Alina Shutova, Vladimir Malinovskii, Vage Egiazarian, Denis Kuznedelev, Denis Mazur, Nikita Surkov, Ivan Ermakov, Dan Alistarh
2025	A*	`conf`	EvoPress: Accurate Dynamic Model Compression via Evolutionary Search. ICML Oliver Sieberling, Denis Kuznedelev, Eldar Kurtic, Dan Alistarh
2025	J	`jnl`	Hogwild! Inference: Parallel LLM Generation via Concurrent Attention. CoRR Gleb Rodionov, Roman Garipov, Alina Shutova, George Yakushev, Vage Egiazarian, Anton Sinitsin, Denis Kuznedelev, Dan Alistarh
2025	J	`jnl`	Scale-wise Distillation of Diffusion Models. CoRR Nikita Starodubcev, Denis Kuznedelev, Artem Babenko, Dmitry Baranchuk
2025	J	`jnl`	TACO Vision Models Can Be Efficiently Specialized via Few-Shot Task-Aware Compression. Trans. Mach. Learn. Res. Denis Kuznedelev, Soroush Tabesh, Kimia Noorbakhsh, Elias Frantar, Sara Beery, Eldar Kurtic, Dan Alistarh
2025	—	`conf`	YaART: Yet Another ART Rendering Technology. KDD (1) Sergey Kastryulin, Artem Konev, Alexander Shishenya, Eugene Lyapustin, Artem Khurshudov, Alexander Tselousov, Nikita Vinokurov, Denis Kuznedelev, Alexander Markovich, Grigoriy Livshits, Alexey Kirillov, Anastasiia Tabisheva, Liubov Chubarova, Marina Kaminskaia, Alexander Ustyuzhanin, Artemii Shvetsov, Daniil Shlenskii, Valerii Startsev, Dmitrii Kornilov, Mikhail Romanov, Dmitry Baranchuk, Artem Babenko, Sergei Ovcharenko, Valentin Khrulkov
2024	J	`jnl`	Accurate Compression of Text-to-Image Diffusion Models via Vector Quantization. CoRR Vage Egiazarian, Denis Kuznedelev, Anton Voronov, Ruslan Svirschevski, Michael Goin, Daniil Pavlov, Dan Alistarh, Dmitry Baranchuk
2024	J	`jnl`	Accurate Neural Network Pruning Requires Rethinking Sparse Optimization. Trans. Mach. Learn. Res. Denis Kuznedelev, Eldar Kurtic, Eugenia Iofinova, Elias Frantar, Alexandra Peste, Dan Alistarh
2024	J	`jnl`	Does Diffusion Beat GAN in Image Super Resolution? CoRR Denis Kuznedelev, Valerii Startsev, Daniil Shlenskii, Sergey Kastryulin
2024	J	`jnl`	EvoPress: Towards Optimal Dynamic Model Compression via Evolutionary Search. CoRR Oliver Sieberling, Denis Kuznedelev, Eldar Kurtic, Dan Alistarh
2024	A*	`conf`	Extreme Compression of Large Language Models via Additive Quantization. ICML Vage Egiazarian, Andrei Panferov, Denis Kuznedelev, Elias Frantar, Artem Babenko, Dan Alistarh
2024	J	`jnl`	Extreme Compression of Large Language Models via Additive Quantization. CoRR Vage Egiazarian, Andrei Panferov, Denis Kuznedelev, Elias Frantar, Artem Babenko, Dan Alistarh
2024	J	`jnl`	Label Privacy in Split Learning for Large Models with Parameter-Efficient Training. CoRR Philip Zmushko, Marat Mansurov, Ruslan Svirschevski, Denis Kuznedelev, Max Ryabinin, Aleksandr Beznosikov
2024	A*	`conf`	PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression. NeurIPS Vladimir Malinovskii, Denis Mazur, Ivan Ilin, Denis Kuznedelev, Konstantin Burlachenko, Kai Yi, Dan Alistarh, Peter Richtárik
2024	J	`jnl`	PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression. CoRR Vladimir Malinovskii, Denis Mazur, Ivan Ilin, Denis Kuznedelev, Konstantin Burlachenko, Kai Yi, Dan Alistarh, Peter Richtárik
2024	A*	`conf`	SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression. ICLR Tim Dettmers, Ruslan Svirschevski, Vage Egiazarian, Denis Kuznedelev, Elias Frantar, Saleh Ashkboos, Alexander Borzunov, Torsten Hoefler, Dan Alistarh
2024	J	`jnl`	Switti: Designing Scale-Wise Transformers for Text-to-Image Synthesis. CoRR Anton Voronov, Denis Kuznedelev, Mikhail Khoroshikh, Valentin Khrulkov, Dmitry Baranchuk
2024	A*	`conf`	The Iterative Optimal Brain Surgeon: Faster Sparse Recovery by Leveraging Second-Order Information. NeurIPS Diyuan Wu, Ionut-Vlad Modoranu, Mher Safaryan, Denis Kuznedelev, Dan Alistarh
2024	J	`jnl`	The Iterative Optimal Brain Surgeon: Faster Sparse Recovery by Leveraging Second-Order Information. CoRR Diyuan Wu, Ionut-Vlad Modoranu, Mher Safaryan, Denis Kuznedelev, Dan Alistarh
2024	J	`jnl`	YaART: Yet Another ART Rendering Technology. CoRR Sergey Kastryulin, Artem Konev, Alexander Shishenya, Eugene Lyapustin, Artem Khurshudov, Alexander Tselousov, Nikita Vinokurov, Denis Kuznedelev, Alexander Markovich, Grigoriy Livshits, Alexey Kirillov, Anastasiia Tabisheva, Liubov Chubarova, Marina Kaminskaia, Alexander Ustyuzhanin, Artemii Shvetsov, Daniil Shlenskii, Valerii Startsev, Dmitrii Kornilov, Mikhail Romanov, Artem Babenko, Sergei Ovcharenko, Valentin Khrulkov
2023	A*	`conf`	A critical look at the evaluation of GNNs under heterophily: Are we really making progress? ICLR Oleg Platonov, Denis Kuznedelev, Michael Diskin, Artem Babenko, Liudmila Prokhorenkova
2023	J	`jnl`	A critical look at the evaluation of GNNs under heterophily: are we really making progress? CoRR Oleg Platonov, Denis Kuznedelev, Michael Diskin, Artem Babenko, Liudmila Prokhorenkova
2023	A*	`conf`	A view of mini-batch SGD via generating functions: conditions of convergence, phase transitions, benefit from negative momenta. ICLR Maksim Velikanov, Denis Kuznedelev, Dmitry Yarotsky
2023	J	`jnl`	Accurate Neural Network Pruning Requires Rethinking Sparse Optimization. CoRR Denis Kuznedelev, Eldar Kurtic, Eugenia Iofinova, Elias Frantar, Alexandra Peste, Dan Alistarh
2023	A*	`conf`	CAP: Correlation-Aware Pruning for Highly-Accurate Sparse Vision Models. NeurIPS Denis Kuznedelev, Eldar Kurtic, Elias Frantar, Dan Alistarh
2023	A*	`conf`	Characterizing Graph Datasets for Node Classification: Homophily-Heterophily Dichotomy and Beyond. NeurIPS Oleg Platonov, Denis Kuznedelev, Artem Babenko, Liudmila Prokhorenkova
2023	A*	`conf`	Evaluating Robustness and Uncertainty of Graph Models Under Structural Distributional Shifts. NeurIPS Gleb Bazhenov, Denis Kuznedelev, Andrey Malinin, Artem Babenko, Liudmila Prokhorenkova
2023	J	`jnl`	Evaluating Robustness and Uncertainty of Graph Models Under Structural Distributional Shifts. CoRR Gleb Bazhenov, Denis Kuznedelev, Andrey Malinin, Artem Babenko, Liudmila Prokhorenkova
2023	J	`jnl`	SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression. CoRR Tim Dettmers, Ruslan Svirschevski, Vage Egiazarian, Denis Kuznedelev, Elias Frantar, Saleh Ashkboos, Alexander Borzunov, Torsten Hoefler, Dan Alistarh
2023	J	`jnl`	Sparse Fine-tuning for Inference Acceleration of Large Language Models. CoRR Eldar Kurtic, Denis Kuznedelev, Elias Frantar, Michael Goin, Dan Alistarh
2023	J	`jnl`	Vision Models Can Be Efficiently Specialized via Few-Shot Task-Aware Compression. CoRR Denis Kuznedelev, Soroush Tabesh, Kimia Noorbakhsh, Elias Frantar, Sara Beery, Eldar Kurtic, Dan Alistarh
2022	J	`jnl`	A view of mini-batch SGD via generating functions: conditions of convergence, phase transitions, benefit from negative momenta. CoRR Maksim Velikanov, Denis Kuznedelev, Dmitry Yarotsky
2022	J	`jnl`	Characterizing Graph Datasets for Node Classification: Beyond Homophily-Heterophily Dichotomy. CoRR Oleg Platonov, Denis Kuznedelev, Artem Babenko, Liudmila Prokhorenkova
2022	J	`jnl`	oViT: An Accurate Second-Order Pruning Framework for Vision Transformers. CoRR Denis Kuznedelev, Eldar Kurtic, Elias Frantar, Dan Alistarh